CN102831200A - Commodity propelling method and device based on image character recognition - Google Patents
Commodity propelling method and device based on image character recognition Download PDFInfo
- Publication number
- CN102831200A CN102831200A CN2012102793672A CN201210279367A CN102831200A CN 102831200 A CN102831200 A CN 102831200A CN 2012102793672 A CN2012102793672 A CN 2012102793672A CN 201210279367 A CN201210279367 A CN 201210279367A CN 102831200 A CN102831200 A CN 102831200A
- Authority
- CN
- China
- Prior art keywords
- merchandise news
- weight
- merchandise
- commodity
- image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention provides a commodity propelling method and device based on image character recognition. The method comprises the following steps of: S1, acquiring a character area in images to be recognized; S2, carrying out character recognition on the character area; S3, inquiring a commodity warehouse based on the recognition result to acquire the commodity information corresponding to the recognition result; and S4, propelling a commodity inquiring list containing the commodity information. By the method and device, the commodity information can be directly acquired by uploading images without manfully searching the commodity information from a great amount of searching results through a search engine, so that the user operation is greatly reduced and convenience is brought.
Description
[technical field]
The present invention relates to the Computer Applied Technology field, particularly a kind of commodity method for pushing and device based on pictograph identification.
[background technology]
Along with developing rapidly of mobile Internet, the application of the image that collects based on mobile terminal camera more and more widely.Wherein the pictograph recognition technology is discerned the literal in the image, convert text into, thereby has alleviated the burden that the user imports corresponding Word message, makes things convenient for user storage, editor's word information relates.
In actual application, there is following situation; The user sees the relevant information of wanting to inquire about these commodity behind certain commodity; Where on sale or the like for example commodity purposes, producer, price,, existing mode are exactly the user through the manual input of search engine trade name etc. as query, and from a large amount of Search Results, look for the merchandise news of wanting; Obvious this mode is operated very loaded down with trivial details, needs a large amount of manual operationss.
[summary of the invention]
In view of this, the invention provides a kind of commodity method for pushing and device,, realize convenient so that reduce the operation that the user obtains merchandise news based on pictograph identification.
Concrete technical scheme is following:
A kind of commodity method for pushing based on pictograph identification, this method comprises:
S1, obtain the character area in the image to be identified;
S2, said character area is carried out literal identification;
S3, utilize recognition result inquiry commodity storehouse to obtain the corresponding merchandise news of recognition result;
S4, propelling movement comprise the merchandise query tabulation of said merchandise news.
According to one preferred embodiment of the present invention, said step S1 specifically comprises:
The image to be identified that the server mobile terminal receive sends extracts character area from said image to be identified; Perhaps,
The character area that the server mobile terminal receive extracts and sends from image to be identified.
According to one preferred embodiment of the present invention, said step S2 specifically comprises:
Character area is carried out binaryzation;
Character area after the binaryzation is divided into each block;
Extract the characteristic information of each block and mate, with the recognition result of matching result as each block with property data base;
Recognition result with each block makes up the recognition result that obtains said character area in order.
According to one preferred embodiment of the present invention, said commodity storehouse comprises the commodity storehouse of an above classification;
All commodity storehouses of inquiry in said step S3; Perhaps,
In said step S1, also obtain the personalization option content that the user selects, the corresponding commodity storehouse of personalization option content that the said user of inquiry selects in said step S3.
According to one preferred embodiment of the present invention, the corresponding merchandise news of said inquiry commodity storehouse acquisition recognition result specifically comprises:
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result, calculate the characters matching weight of merchandise news, n1 merchandise news was included in the merchandise query tabulation before the characters matching weight was come, and n1 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, the inquiry weight is come preceding n2 merchandise news be included in the merchandise query tabulation, n2 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, based on the selection weight of being calculated merchandise news by the inquiry situation of merchandise news, in conjunction with total weight of said inquiry weight and right to choose re-computation merchandise news; Total weighted value is come preceding n3 merchandise news generate the merchandise query tabulation, the positive integer of n3 for presetting.
According to one preferred embodiment of the present invention, the selection weight of said calculating merchandise news comprises:
The total degree that is queried to according to merchandise news calculates the selection weight of merchandise news, and total degree choice weighted value more is big more; Perhaps,
The total degree that utilizes merchandise news to be queried to is confirmed the commodity weight of merchandise news; The big more commodity weighted value of total degree is big more; Utilize the total degree that all merchandise newss of classification are checked by the active user under the merchandise news to confirm the user individual weight again, utilize the product of commodity weight and the user individual weight of merchandise news to confirm the selection weight of this merchandise news.
A kind of commodity pusher based on pictograph identification, this device comprises:
The zone acquiring unit is used for obtaining the character area of image to be identified;
Word recognition unit is used for said character area is carried out literal identification;
The merchandise query unit, the recognition result inquiry commodity storehouse that is used for said word recognition unit obtains the corresponding merchandise news of recognition result;
Push unit is used to push the merchandise query tabulation that comprises said merchandise news as a result.
According to one preferred embodiment of the present invention, the image to be identified that said regional acquiring unit mobile terminal receive sends extracts character area from said image to be identified; Perhaps, the mobile terminal receive character area that from image to be identified, extracts and send.
According to one preferred embodiment of the present invention; Said word recognition unit is specifically carried out: character area is carried out binaryzation; Character area after the binaryzation is divided into each block; Extract the characteristic information of each block and mate with property data base, with the recognition result of matching result as each block, the recognition result with each block makes up the recognition result that obtains said character area in order.
According to one preferred embodiment of the present invention, said commodity storehouse comprises the commodity storehouse of an above classification;
All commodity storehouses of inquiry, said merchandise query unit; Perhaps,
Said regional acquiring unit also obtains the personalization option content that the user selects, and the corresponding commodity storehouse of personalization option content that said user selects is inquired about in said merchandise query unit.
According to one preferred embodiment of the present invention, when said merchandise query unit obtains the merchandise news of recognition result correspondence in inquiry commodity storehouse, concrete:
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result, calculate the characters matching weight of merchandise news, n1 merchandise news was included in the merchandise query tabulation before the characters matching weight was come, and n1 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, the inquiry weight is come preceding n2 merchandise news be included in the merchandise query tabulation, n2 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, based on the selection weight of being calculated merchandise news by the inquiry situation of merchandise news, in conjunction with total weight of said inquiry weight and right to choose re-computation merchandise news; Total weighted value is come preceding n3 merchandise news generate the merchandise query tabulation, the positive integer of n3 for presetting.
According to one preferred embodiment of the present invention, said merchandise query unit is when calculating the selection weight of merchandise news, and is concrete:
The total degree that is queried to according to merchandise news calculates the selection weight of merchandise news, and total degree choice weighted value more is big more; Perhaps,
The total degree that utilizes merchandise news to be queried to is confirmed the commodity weight of merchandise news; The big more commodity weighted value of total degree is big more; Utilize the total degree that all merchandise newss of classification are checked by the active user under the merchandise news to confirm the user individual weight again, utilize the product of commodity weight and the user individual weight of merchandise news to confirm the selection weight of this merchandise news.
Can find out by above technical scheme; The present invention utilizes recognition result inquiry commodity storehouse to obtain the corresponding merchandise news of recognition result, and pushes the merchandise query tabulation that comprises merchandise news on the pictograph base of recognition; Thereby make the user directly to get access to merchandise news through the mode of uploading image; From a large amount of Search Results, search merchandise news and need not manual work through search engine, significantly reduced user's operation, realize convenient.
[description of drawings]
The commodity method for pushing process flow diagram that Fig. 1 provides for the embodiment of the invention based on pictograph identification;
The system construction drawing that Fig. 2 provides for the embodiment of the invention;
The commodity pusher structural drawing that Fig. 3 provides for the embodiment of the invention based on pictograph identification;
Two bandwagon effect synoptic diagram of the portable terminal that Fig. 4 and Fig. 5 provide for the embodiment of the invention.
[embodiment]
In order to make the object of the invention, technical scheme and advantage clearer, describe the present invention below in conjunction with accompanying drawing and specific embodiment.
Embodiment one,
The commodity method for pushing process flow diagram that Fig. 1 provides for the embodiment of the invention based on pictograph identification, as shown in Figure 1, this method can may further comprise the steps:
Step 101: obtain the character area in the image to be identified.
Server obtains the image that comprises Word message that portable terminal sends, and this image can be the original image that portable terminal photographs, and server extracts the character area in the image to be identified in this step.Perhaps, this image can be after portable terminal photographs original image and extracts the character area in the image to be identified, the character area in the image to be identified to be sent to server.
When extracting character area, can adopt existing mode, extract character area after removing image background, can adopt but be not limited to following mode:
Mode one, at first carry out colored Run-Length Coding according to colored Euclidean distance; Carry out color cluster then; Carry out the generation and the selection of character layer based on cluster result; For example keep the connected domain of area, generate each image aspect, confirm literal aspect, noise aspect or background aspect according to the relation of the number of pixels of the number of pixels of each image aspect and this layer segmentation threshold at last based on the Euclidean distance at connected domain and each color cluster center greater than certain value; Just obtain the character layer face after taking out noise aspect and background aspect at last, i.e. character area.
Mode two, select a large amount of literal sample images and do not contain the picture of literal, use the training sample of the marginal information of these two types of pictures of canny operator extraction as the rarefaction representation classifying dictionary; Two types of training sample input category rarefaction representation dictionary training algorithms are obtained literal rarefaction representation classifying dictionary and non-legible rarefaction representation classifying dictionary; Transfer image to be identified to gray level image, use the marginal information of canny operator extraction gray level image; Utilization is extracted the candidate character region in the gray-scale Image Edge information based on the rarefaction representation of classifying dictionary; Use the distance of swimming smoothing algorithm edge that candidate character region is isolated to be connected to bigger zone respectively in the horizontal direction with on the vertical direction; Carry out Projection Analysis again and find out corresponding literal line, cast out the isolated edge beyond the candidate character region Chinese words row simultaneously; Detected character area is identified out.
If portable terminal carries out the extraction of character area, then can adopt existing character area extraction software or manual mode to carry out the extraction of character area.
In addition, the character area that obtains in this step can be one, also can be more than two.Because the content in this step is a prior art, repeats no more at this.
Step 102: character area is carried out literal identification.
The process of wherein character area being carried out literal identification can adopt prior art equally, promptly may further comprise the steps: character area is carried out binaryzation; Character area after the binaryzation is divided into each block; Extract the characteristic information of each block and mate with property data base, with the recognition result of matching result as each block, the recognition result with each block makes up the recognition result that just obtains character area in order.
In addition, the literal identification mode is varied, except aforesaid way, can also adopt other can realize the literal identification mode arbitrarily, specifically repeats no more.
Step 103: utilize recognition result inquiry commodity storehouse to obtain the corresponding merchandise news of recognition result.
The commodity storehouse of inquiring about in this step can be the physical commodity storehouse, also can be the virtual goods storehouse, and these commodity storehouses can be local commodity storehouses, also can be the commodity storehouses of network, also can be the commodity storehouses that the third party has opened access interface.
The physical commodity storehouse can comprise but be not limited to comprise books merchandise news books commodity storehouse, comprise food merchandise news food commodity storehouse, comprise toggery information the toggery storehouse, comprise each entity class commodity storehouse such as medicine commodity storehouse of medicine information.The virtual goods storehouse can comprise but be not limited to comprise e-book merchandise news e-book commodity storehouse, comprise card of game points merchandise news card of game points commodity storehouse, comprise application software merchandise news application software commodity storehouse, comprise virtual type of commodity storehouse such as service commodity storehouse of service commodity information.
In query entity commodity storehouse or during the virtual goods storehouse; Calculate the characters matching weight of merchandise news Chinese words content and recognition result; This literal coupling weight depends on the semantic similarity between merchandise news and the recognition result, and the merchandise news that the characters matching weight is reached preset characters matching weight threshold is as Query Result.
Wherein the definite of semantic similarity can adopt prior art; Purpose is the word content and the recognition result that calculate merchandise news at semantically similarity degree; The method of confirming can adopt but be not limited to following mode: extract the crucial semantic vocabulary in the recognition result; The word content of inquiring information of goods obtains to mate crucial semantic vocabulary literal number successfully, with the definite basis of this number as semantic similarity.The big more expression semantic similarity of crucial semantic vocabulary literal number that matees successfully is big more, and corresponding character coupling weight is big more.
In addition; Singularity in view of physical commodity; Can there be image in physical commodity; When query entity commodity storehouse, can also further calculate the images match weight between the image in the merchandise news in image to be identified and commodity storehouse, this images match weight depends on the similarity between the image and image to be identified in the merchandise news.Combine merchandise news corresponding character coupling weight and the corresponding inquiry weight of images match weight calculation merchandise news then.Wherein when calculating the inquiry weight of merchandise news correspondence, can the product of characters matching weight and images match weight perhaps be sued for peace as corresponding inquiry weight.
The definite of similarity in the above-mentioned merchandise news between image and the image to be identified also can adopt prior art; Can adopt but be not limited to this method: the color histogram that extracts image to be identified and commodity image respectively; Calculate the Euclidean distance between the color histogram, confirm the similarity between two images based on this Euclidean distance.Similarity between more little two images of Euclidean distance is big more, and corresponding images match weight is big more.
A kind of implementation is after having inquired about all commodity storehouses, the characters matching weight to be come preceding n1 merchandise news be included in the merchandise query tabulation for returning to portable terminal.Distinguishingly, wherein can the inquiry weight be come for the merchandise news of physical commodity before n2 merchandise news be included in the merchandise query tabulation for returning to portable terminal.Wherein n1 and n2 are preset positive integer.
Another kind of implementation is; Portable terminal provides the personal settings option to the user;, sending server the option content that the user selects when sending image simultaneously, when server inquire about commodity storehouse of all categories in this step, and the commodity storehouse of the option content correspondence classification selected of inquiring user only.N1 merchandise news is included in the merchandise query tabulation for returning to portable terminal before then the characters matching weight being come.Distinguishingly, wherein can the inquiry weight be come for the merchandise news of physical commodity before n2 merchandise news be included in the merchandise query tabulation for returning to portable terminal.Wherein n1 and n2 are preset positive integer.
Give an example; Portable terminal provides personal settings options such as physical commodity, virtual goods to the user; Personal settings options such as books commodity, food commodity, toggery, e-book commodity, card of game points commodity, application software commodity, service commodity perhaps more specifically are provided; If the user has taken a kind of image of packaging for foodstuff through portable terminal, can select this option of food commodity, portable terminal sends to server with the option content of image and user's selection then; Server is when inquiring about the commodity storehouse to the literal recognition result of image; Just can only inquire about food commodity storehouse, the Query Result that obtains is generated the merchandise query tabulation, in step 104, return to portable terminal then.Certainly, the user also can select more than one option.
Also there is a kind of implementation; When inquiry commodity storehouse; Still inquire about the commodity storehouse of the corresponding classification of option content of all commodity storehouses or inquiring user selection; But when returning merchandise news, combine the inquiry weight of merchandise news and total weight of each merchandise news of right to choose re-computation, n3 merchandise news generated the merchandise query tabulation and supplies to return to portable terminal before total weighted value was come, and n3 is preset positive integer.
Wherein the selection weight of merchandise news can adopt but be not limited to following mode and confirm: the total degree that one of which, this merchandise news are queried to, this total degree choice weighted value more are big more, and the total degree here refers to the total degree that is arrived by all user inquirings.Two, utilize merchandise news by all user inquirings to total degree confirm the commodity weight that this merchandise news is corresponding; Utilize all merchandise newss of the affiliated classification of merchandise news to be checked again (after soon merchandise news will be pushed to portable terminal by the active user; The user can check the wherein merchandise news of some classification; For example food merchandise news and clothes merchandise news have been pushed to the user; If the user has checked food merchandise news wherein; Then can upgrade the number of times that food merchandise news is checked, be used to upgrade the user individual weight of food merchandise news) total degree confirm the user individual weight, utilize the product of commodity weight and the user individual weight of merchandise news to confirm the selection weight of this merchandise news.
After obtaining the selection weight of merchandise news, the selection weight that can utilize merchandise news and the product of inquiry weight obtain total weight of merchandise news, can certainly adopt mode such as summation to obtain total weight of merchandise news.
In addition, this step can be based on whole Word messages of recognition result when inquiry commodity storehouse, also can be based on recognition result being cut the crucial meaning Word message that obtains behind the speech.
Step 104: push the merchandise query tabulation that comprises corresponding goods information to portable terminal.
After server returned to portable terminal with merchandise news, the user just can get access to corresponding merchandise news from the demonstration of portable terminal.And; Merchandise news wherein possibly be more than one classifications, if the user has checked wherein some or several classifications, then can report to server; By the total degree of all user inquirings, upgrade the corresponding selection of the affiliated merchandise classification of merchandise news by each merchandise news of server update simultaneously.
In addition, except the merchandise query tabulation is returned to the portable terminal, can recognition result be returned to portable terminal simultaneously.
More than be the description that method provided by the present invention is carried out, be described in detail through two pairs of devices provided by the present invention of embodiment below.Understand for ease and at first the applied system of said method of the present invention is described, as shown in Figure 2, this system is made up of portable terminal and server; Wherein portable terminal can send to server as image to be identified with the image that comprises literal that photographs; Therefrom extract character area by server, perhaps, the image that comprises literal that portable terminal will photograph as image to be identified after; Therefrom extract character area, this literal field territory is sent to server.Server is carried out flow process shown in the embodiment one afterwards, returns the merchandise query tabulation to portable terminal.The device that the following embodiment two of the present invention is provided is arranged in the server, is used to accomplish flow process shown in the embodiment one.
Embodiment two,
The structure drawing of device of pictograph that Fig. 3 provides for the embodiment of the invention two identification, as shown in Figure 3, this device comprises: regional acquiring unit 301, word recognition unit 302, merchandise query unit 303 and push unit 304 as a result.
At first, regional acquiring unit 301 obtains the character area in the image to be identified.
Here, the image to be identified that regional acquiring unit 301 mobile terminal receives send extracts character area from image to be identified; Perhaps, the mobile terminal receive character area that from image to be identified, extracts and send.When extracting character area, can adopt the dual mode described in the step 101 among the embodiment one, because this partial content is a prior art, be not described in detail in this.
302 pairs of character areas of word recognition unit carry out literal identification then.Concrete identifying can comprise: character area is carried out binaryzation; Character area after the binaryzation is divided into each block; Extract the characteristic information of each block and mate with property data base; With the recognition result of matching result as each block, the recognition result with each block makes up the recognition result that obtains character area in order.
Because the commodity storehouse that relates among the present invention comprises the commodity storehouse of an above classification, promptly can be the commodity storehouse of a classification, also can be the commodity storehouse of a plurality of classifications, so in following any can be carried out in merchandise query unit 303 when inquiry commodity storehouse:
All commodity storehouses of inquiry, merchandise query unit; Perhaps,
The zone acquiring unit also obtains the personalization option content that the user selects, the commodity storehouse that the personalization option content that merchandise query unit inquiring user is selected is corresponding.
When wherein obtaining the merchandise news of recognition result correspondence, can adopt following embodiment in inquiry commodity storehouse:
First kind of embodiment: according to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; The characters matching weight is come preceding n1 merchandise news be included in the merchandise query tabulation, n1 is preset positive integer.
Second kind of embodiment: according to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news; The inquiry weight is come preceding n2 merchandise news be included in the merchandise query tabulation, n2 is preset positive integer.
The third embodiment: according to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news; The selection weight of being calculated merchandise news by the inquiry situation based on merchandise news; In conjunction with total weight of said inquiry weight and right to choose re-computation merchandise news, total weighted value is come preceding n3 merchandise news generate the merchandise query tabulation, the positive integer of n3 for presetting.
Particularly, merchandise query unit 303 can specifically adopt following mode when calculating the selection weight of merchandise news:
Mode one, the total degree that is arrived by all user inquirings according to merchandise news calculate the selection weight of merchandise news, and total degree choice weighted value more is big more.
Mode two, the total degree that utilizes merchandise news to be queried to are confirmed the commodity weight of merchandise news; The big more commodity weighted value of total degree is big more; Utilize the total degree that all merchandise newss of classification are checked by the active user under the merchandise news to confirm the user individual weight again, utilize the product of commodity weight and the user individual weight of merchandise news to confirm the selection weight of this merchandise news.
At last, push unit 304 pushes the merchandise query tabulation that comprises merchandise news as a result.Also can recognition result be returned to portable terminal simultaneously.
After merchandise query tabulation returned to portable terminal, the user just can obtain merchandise news from the demonstration of portable terminal.And; Merchandise news wherein possibly be more than one classifications; If the user has checked wherein some or several classifications; Then can report, upgrade each merchandise news by the total degree of all user inquirings, upgrade the corresponding selection of the affiliated merchandise classification of merchandise news simultaneously by merchandise query unit 303 to server.
Through said method of the present invention and device, the user can obtain corresponding merchandise news through the mode of uploading pictures, from a large amount of Search Results, obtains merchandise news and need not manual mode through search engine, and is obviously convenient and laborsaving.
For example; The user photographs the image that comprises literal " thousand sigh " through portable terminal, send it to server after, after server carries out pictograph identification and inquiry commodity storehouse through said process; Return the tabulation of recognition result and merchandise query; Wherein the exhibition method of merchandise query tabulation does not limit in the present invention, can adopt any-mode, for example the mode of quoting frame shown in Fig. 4.
Again for example; The user photographs the image that comprises literal " darkness please be closed one's eyes " through portable terminal; After sending it to server, after server carries out pictograph identification and inquiry commodity storehouse through said process, comprise the commodity of plurality of classes in the merchandise query tabulation of returning; Wherein the exhibition method of commodity of all categories does not limit in the present invention yet, for example the mode of the employing label shown in Fig. 5.
The above is merely preferred embodiment of the present invention, and is in order to restriction the present invention, not all within spirit of the present invention and principle, any modification of being made, is equal to replacement, improvement etc., all should be included within the scope that the present invention protects.
Claims (12)
1. commodity method for pushing based on pictograph identification is characterized in that this method comprises:
S1, obtain the character area in the image to be identified;
S2, said character area is carried out literal identification;
S3, utilize recognition result inquiry commodity storehouse to obtain the corresponding merchandise news of recognition result;
S4, propelling movement comprise the merchandise query tabulation of said merchandise news.
2. method according to claim 1 is characterized in that, said step S1 specifically comprises:
The image to be identified that the server mobile terminal receive sends extracts character area from said image to be identified; Perhaps,
The character area that the server mobile terminal receive extracts and sends from image to be identified.
3. method according to claim 1 is characterized in that, said step S2 specifically comprises:
Character area is carried out binaryzation;
Character area after the binaryzation is divided into each block;
Extract the characteristic information of each block and mate, with the recognition result of matching result as each block with property data base;
Recognition result with each block makes up the recognition result that obtains said character area in order.
4. method according to claim 1 is characterized in that, said commodity storehouse comprises the commodity storehouse of an above classification;
All commodity storehouses of inquiry in said step S3; Perhaps,
In said step S1, also obtain the personalization option content that the user selects, the corresponding commodity storehouse of personalization option content that the said user of inquiry selects in said step S3.
5. method according to claim 4 is characterized in that, said inquiry commodity storehouse obtains the corresponding merchandise news of recognition result and specifically comprises:
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result, calculate the characters matching weight of merchandise news, n1 merchandise news was included in the merchandise query tabulation before the characters matching weight was come, and n1 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, the inquiry weight is come preceding n2 merchandise news be included in the merchandise query tabulation, n2 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, based on the selection weight of being calculated merchandise news by the inquiry situation of merchandise news, in conjunction with total weight of said inquiry weight and right to choose re-computation merchandise news; Total weighted value is come preceding n3 merchandise news generate the merchandise query tabulation, the positive integer of n3 for presetting.
6. method according to claim 5 is characterized in that, the selection weight of said calculating merchandise news comprises:
The total degree that is queried to according to merchandise news calculates the selection weight of merchandise news, and total degree choice weighted value more is big more; Perhaps,
The total degree that utilizes merchandise news to be queried to is confirmed the commodity weight of merchandise news; The big more commodity weighted value of total degree is big more; Utilize the total degree that all merchandise newss of classification are checked by the active user under the merchandise news to confirm the user individual weight again, utilize the product of commodity weight and the user individual weight of merchandise news to confirm the selection weight of this merchandise news.
7. commodity pusher based on pictograph identification is characterized in that this device comprises:
The zone acquiring unit is used for obtaining the character area of image to be identified;
Word recognition unit is used for said character area is carried out literal identification;
The merchandise query unit, the recognition result inquiry commodity storehouse that is used for said word recognition unit obtains the corresponding merchandise news of recognition result;
Push unit is used to push the merchandise query tabulation that comprises said merchandise news as a result.
8. device according to claim 7 is characterized in that, the image to be identified that said regional acquiring unit mobile terminal receive sends extracts character area from said image to be identified; Perhaps, the mobile terminal receive character area that from image to be identified, extracts and send.
9. device according to claim 7; It is characterized in that; Said word recognition unit is specifically carried out: character area is carried out binaryzation, the character area after the binaryzation is divided into each block, extract the characteristic information of each block and mate with property data base; With the recognition result of matching result as each block, the recognition result with each block makes up the recognition result that obtains said character area in order.
10. device according to claim 7 is characterized in that, said commodity storehouse comprises the commodity storehouse of an above classification;
All commodity storehouses of inquiry, said merchandise query unit; Perhaps,
Said regional acquiring unit also obtains the personalization option content that the user selects, and the corresponding commodity storehouse of personalization option content that said user selects is inquired about in said merchandise query unit.
11. device according to claim 10 is characterized in that, and is when said merchandise query unit obtains the merchandise news of recognition result correspondence in inquiry commodity storehouse, concrete:
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result, calculate the characters matching weight of merchandise news, n1 merchandise news was included in the merchandise query tabulation before the characters matching weight was come, and n1 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, the inquiry weight is come preceding n2 merchandise news be included in the merchandise query tabulation, n2 is preset positive integer; Perhaps,
According to the merchandise news Chinese words content in commodity storehouse and the semantic similarity between the recognition result; Calculate the characters matching weight of merchandise news; And according to the images match weight of the calculating of the similarity between image merchandise news in the merchandise news in said image to be identified and commodity storehouse; In conjunction with characters matching weight and the corresponding inquiry weight of images match weight calculation merchandise news, based on the selection weight of being calculated merchandise news by the inquiry situation of merchandise news, in conjunction with total weight of said inquiry weight and right to choose re-computation merchandise news; Total weighted value is come preceding n3 merchandise news generate the merchandise query tabulation, the positive integer of n3 for presetting.
12. device according to claim 11 is characterized in that, said merchandise query unit is when calculating the selection weight of merchandise news, and is concrete:
The total degree that is queried to according to merchandise news calculates the selection weight of merchandise news, and total degree choice weighted value more is big more; Perhaps,
The total degree that utilizes merchandise news to be queried to is confirmed the commodity weight of merchandise news; The big more commodity weighted value of total degree is big more; Utilize the total degree that all merchandise newss of classification are checked by the active user under the merchandise news to confirm the user individual weight again, utilize the product of commodity weight and the user individual weight of merchandise news to confirm the selection weight of this merchandise news.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102793672A CN102831200A (en) | 2012-08-07 | 2012-08-07 | Commodity propelling method and device based on image character recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102793672A CN102831200A (en) | 2012-08-07 | 2012-08-07 | Commodity propelling method and device based on image character recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102831200A true CN102831200A (en) | 2012-12-19 |
Family
ID=47334337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012102793672A Pending CN102831200A (en) | 2012-08-07 | 2012-08-07 | Commodity propelling method and device based on image character recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102831200A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064936A (en) * | 2012-12-24 | 2013-04-24 | 北京百度网讯科技有限公司 | Voice-input-based image information extraction analysis method and device |
| CN103294779A (en) * | 2013-05-13 | 2013-09-11 | 北京百度网讯科技有限公司 | Method and device for acquiring object information |
| CN103412938A (en) * | 2013-08-22 | 2013-11-27 | 成都数之联科技有限公司 | Commodity price comparing method based on picture interactive type multiple-target extraction |
| CN104008388A (en) * | 2014-06-06 | 2014-08-27 | 杨军辉 | Method and system for obtaining merchant business data by recognizing product identification |
| CN104240096A (en) * | 2014-08-27 | 2014-12-24 | 小米科技有限责任公司 | Information display method and device and electronic equipment |
| CN104268168A (en) * | 2014-09-10 | 2015-01-07 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information to user |
| CN105095446A (en) * | 2015-07-24 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Medicine search processing method, server and terminal device |
| CN105321146A (en) * | 2015-09-25 | 2016-02-10 | 广东小天才科技有限公司 | Method and apparatus for processing subject picture taken by mobile terminal |
| CN105426462A (en) * | 2015-11-13 | 2016-03-23 | 深圳码隆科技有限公司 | Image searching method and device based on image element |
| CN105447708A (en) * | 2014-08-28 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Information offering method and information offering device |
| CN105653733A (en) * | 2016-02-26 | 2016-06-08 | 百度在线网络技术（北京）有限公司 | Searching method and device |
| CN105912642A (en) * | 2016-04-08 | 2016-08-31 | 世纪禾光科技发展（北京）有限公司 | Product price data acquisition method and system |
| CN106126755A (en) * | 2016-08-24 | 2016-11-16 | 广东华邦云计算股份有限公司 | A kind of purchase method based on image recognition |
| CN106294527A (en) * | 2015-06-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of information recommendation method and equipment |
| CN106708823A (en) * | 2015-07-20 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Search processing method, apparatus and system |
| CN107291352A (en) * | 2017-06-20 | 2017-10-24 | 广州阿里巴巴文学信息技术有限公司 | Application program is redirected in a kind of word read method and its device |
| CN107292642A (en) * | 2016-03-31 | 2017-10-24 | 苏宁云商集团股份有限公司 | A kind of Method of Commodity Recommendation and system based on image |
| CN107330391A (en) * | 2017-06-26 | 2017-11-07 | 北京小米移动软件有限公司 | Product information reminding method and device |
| CN107580047A (en) * | 2017-08-31 | 2018-01-12 | 广东美的制冷设备有限公司 | Equipment method for pushing, electronic equipment and computer-readable recording medium |
| CN107798070A (en) * | 2017-09-26 | 2018-03-13 | 平安普惠企业管理有限公司 | A kind of web data acquisition methods and terminal device |
| CN108804978A (en) * | 2017-04-28 | 2018-11-13 | 腾讯科技（深圳）有限公司 | A kind of printed page analysis method and device |
| CN109429077A (en) * | 2017-08-24 | 2019-03-05 | 北京搜狗科技发展有限公司 | Method for processing video frequency and device, for the device of video processing |
| CN110858233A (en) * | 2018-08-17 | 2020-03-03 | 珠海格力电器股份有限公司 | Mobile terminal information recommendation system and method based on image understanding |
| CN111258409A (en) * | 2020-05-06 | 2020-06-09 | 北京深光科技有限公司 | Feature point identification method and device for man-machine interaction |
| CN113724030A (en) * | 2020-07-23 | 2021-11-30 | 景德镇陶瓷大学 | Method and system for customizing articles on line |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101000623A (en) * | 2007-01-08 | 2007-07-18 | 深圳市宜搜科技发展有限公司 | Method for image identification search by mobile phone photographing and device using the method |
| CN101044494A (en) * | 2004-10-20 | 2007-09-26 | 摩托罗拉公司 | An electronic device and method for visual text interpretation |
| CN101136096A (en) * | 2006-08-31 | 2008-03-05 | 林�智 | Dress ornament evaluating and matching system and method on internet |
| US20080059526A1 (en) * | 2006-09-01 | 2008-03-06 | Sony Corporation | Playback apparatus, searching method, and program |
| CN101414307A (en) * | 2008-11-26 | 2009-04-22 | 阿里巴巴集团控股有限公司 | Method and server for providing picture searching |
| CN101751566A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | Method and device for identifying and annotating menu based on handheld device |
-
2012
- 2012-08-07 CN CN2012102793672A patent/CN102831200A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101044494A (en) * | 2004-10-20 | 2007-09-26 | 摩托罗拉公司 | An electronic device and method for visual text interpretation |
| CN101136096A (en) * | 2006-08-31 | 2008-03-05 | 林�智 | Dress ornament evaluating and matching system and method on internet |
| US20080059526A1 (en) * | 2006-09-01 | 2008-03-06 | Sony Corporation | Playback apparatus, searching method, and program |
| CN101000623A (en) * | 2007-01-08 | 2007-07-18 | 深圳市宜搜科技发展有限公司 | Method for image identification search by mobile phone photographing and device using the method |
| CN101414307A (en) * | 2008-11-26 | 2009-04-22 | 阿里巴巴集团控股有限公司 | Method and server for providing picture searching |
| CN101751566A (en) * | 2008-12-12 | 2010-06-23 | 汉王科技股份有限公司 | Method and device for identifying and annotating menu based on handheld device |
Non-Patent Citations (1)
| Title |
|---|
| 唐一之: "《无形的市场——知识本体与网络消费研究（2009年1月第1版）》", 31 January 2009, 湖南师范大学出版社 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103064936B (en) * | 2012-12-24 | 2018-03-30 | 北京百度网讯科技有限公司 | A kind of image information extraction and analytical method and device based on phonetic entry |
| CN103064936A (en) * | 2012-12-24 | 2013-04-24 | 北京百度网讯科技有限公司 | Voice-input-based image information extraction analysis method and device |
| CN103294779A (en) * | 2013-05-13 | 2013-09-11 | 北京百度网讯科技有限公司 | Method and device for acquiring object information |
| CN103412938A (en) * | 2013-08-22 | 2013-11-27 | 成都数之联科技有限公司 | Commodity price comparing method based on picture interactive type multiple-target extraction |
| CN103412938B (en) * | 2013-08-22 | 2016-06-29 | 成都数之联科技有限公司 | A kind of commodity price-comparing method extracted based on picture interactive multiobjective |
| CN104008388A (en) * | 2014-06-06 | 2014-08-27 | 杨军辉 | Method and system for obtaining merchant business data by recognizing product identification |
| CN104240096A (en) * | 2014-08-27 | 2014-12-24 | 小米科技有限责任公司 | Information display method and device and electronic equipment |
| CN105447708A (en) * | 2014-08-28 | 2016-03-30 | 阿里巴巴集团控股有限公司 | Information offering method and information offering device |
| CN104268168A (en) * | 2014-09-10 | 2015-01-07 | 百度在线网络技术（北京）有限公司 | Method and device for pushing information to user |
| CN106294527A (en) * | 2015-06-26 | 2017-01-04 | 阿里巴巴集团控股有限公司 | A kind of information recommendation method and equipment |
| CN106708823A (en) * | 2015-07-20 | 2017-05-24 | 阿里巴巴集团控股有限公司 | Search processing method, apparatus and system |
| CN105095446A (en) * | 2015-07-24 | 2015-11-25 | 百度在线网络技术（北京）有限公司 | Medicine search processing method, server and terminal device |
| CN105321146A (en) * | 2015-09-25 | 2016-02-10 | 广东小天才科技有限公司 | Method and apparatus for processing subject picture taken by mobile terminal |
| CN105426462A (en) * | 2015-11-13 | 2016-03-23 | 深圳码隆科技有限公司 | Image searching method and device based on image element |
| CN105653733A (en) * | 2016-02-26 | 2016-06-08 | 百度在线网络技术（北京）有限公司 | Searching method and device |
| CN107292642A (en) * | 2016-03-31 | 2017-10-24 | 苏宁云商集团股份有限公司 | A kind of Method of Commodity Recommendation and system based on image |
| CN105912642A (en) * | 2016-04-08 | 2016-08-31 | 世纪禾光科技发展（北京）有限公司 | Product price data acquisition method and system |
| CN106126755A (en) * | 2016-08-24 | 2016-11-16 | 广东华邦云计算股份有限公司 | A kind of purchase method based on image recognition |
| CN108804978A (en) * | 2017-04-28 | 2018-11-13 | 腾讯科技（深圳）有限公司 | A kind of printed page analysis method and device |
| CN108804978B (en) * | 2017-04-28 | 2022-04-12 | 腾讯科技（深圳）有限公司 | Layout analysis method and device |
| CN107291352A (en) * | 2017-06-20 | 2017-10-24 | 广州阿里巴巴文学信息技术有限公司 | Application program is redirected in a kind of word read method and its device |
| CN107330391A (en) * | 2017-06-26 | 2017-11-07 | 北京小米移动软件有限公司 | Product information reminding method and device |
| CN109429077A (en) * | 2017-08-24 | 2019-03-05 | 北京搜狗科技发展有限公司 | Method for processing video frequency and device, for the device of video processing |
| CN107580047A (en) * | 2017-08-31 | 2018-01-12 | 广东美的制冷设备有限公司 | Equipment method for pushing, electronic equipment and computer-readable recording medium |
| WO2019041595A1 (en) * | 2017-08-31 | 2019-03-07 | 广东美的制冷设备有限公司 | Device pushing method, electronic device, and computer readable storage medium |
| CN107798070A (en) * | 2017-09-26 | 2018-03-13 | 平安普惠企业管理有限公司 | A kind of web data acquisition methods and terminal device |
| CN110858233A (en) * | 2018-08-17 | 2020-03-03 | 珠海格力电器股份有限公司 | Mobile terminal information recommendation system and method based on image understanding |
| CN111258409A (en) * | 2020-05-06 | 2020-06-09 | 北京深光科技有限公司 | Feature point identification method and device for man-machine interaction |
| CN113724030A (en) * | 2020-07-23 | 2021-11-30 | 景德镇陶瓷大学 | Method and system for customizing articles on line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102831200A (en) | Commodity propelling method and device based on image character recognition | |
| US9042659B2 (en) | Method and system for fast and robust identification of specific product images | |
| US10007928B2 (en) | Dynamic presentation of targeted information in a mixed media reality recognition system | |
| CN102855480A (en) | Method and device for recognizing characters in image | |
| KR102124568B1 (en) | System for payment solution service based on object recognition in image with machine learning using artificial intelligent | |
| US20150161485A1 (en) | Learning Semantic Image Similarity | |
| EP2164009A2 (en) | Architecture for mixed media reality retrieval of locations and registration of images | |
| EP2639745A1 (en) | Object identification in images or image sequences | |
| CN101288077A (en) | Use of image-derived information as search criteria for internet and other search engines | |
| RU2637876C2 (en) | Method, server device and terminal device for image delivery | |
| CN110209862B (en) | Text matching method, electronic device and computer readable storage medium | |
| CN111382620B (en) | Video tag adding method, computer storage medium and electronic device | |
| CN103678460B (en) | For identifying the method and system for the non-text elements for being suitable to be communicated in multi-language environment | |
| US9910864B2 (en) | Method for object recognition, corresponding system, apparatus and computer program product | |
| US20230169555A1 (en) | System and method for textual analysis of images | |
| CN111177450B (en) | Image retrieval cloud identification method and system and computer readable storage medium | |
| CN110674388A (en) | Mapping method and device for push item, storage medium and terminal equipment | |
| KR102043693B1 (en) | Machine learning based document management system | |
| CN110705572B (en) | Image recognition method | |
| CN114821234A (en) | Network training and target detection method, device, equipment and storage medium | |
| EP3115927A1 (en) | Method and apparatus for processing a scene | |
| KR101910825B1 (en) | Method, apparatus, system and computer program for providing aimage retrieval model | |
| CA3140679A1 (en) | Method and apparatus for cosmetic product recommendation | |
| EP2665018A1 (en) | Object identification in images or image sequences | |
| Guimarães et al. | A Review of Recent Advances and Challenges in Grocery Label Detection and Recognition |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20121219 |