CN111008655A - Method and device for assisting in identifying authenticity of physical commodity brand and electronic equipment - Google Patents
Method and device for assisting in identifying authenticity of physical commodity brand and electronic equipment Download PDFInfo
- Publication number
- CN111008655A CN111008655A CN201911192888.2A CN201911192888A CN111008655A CN 111008655 A CN111008655 A CN 111008655A CN 201911192888 A CN201911192888 A CN 201911192888A CN 111008655 A CN111008655 A CN 111008655A
- Authority
- CN
- China
- Prior art keywords
- picture
- commodity
- target
- target picture
- deflection angle
- 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
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000012634 fragment Substances 0.000 claims abstract description 87
- 238000012937 correction Methods 0.000 claims abstract description 46
- 230000011218 segmentation Effects 0.000 claims abstract description 28
- 238000013145 classification model Methods 0.000 claims abstract description 25
- 206010061274 Malocclusion Diseases 0.000 claims abstract description 22
- 238000012549 training Methods 0.000 claims description 19
- 238000000926 separation method Methods 0.000 claims description 17
- 238000003062 neural network model Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 235000021167 banquet Nutrition 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
- G06Q30/0185—Product, service or business identity fraud
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
- G06V10/242—Aligning, centring, orientation detection or correction of the image by image rotation, e.g. by 90 degrees
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method for assisting in identifying the authenticity of a brand of a physical commodity, which comprises the steps of obtaining a commodity picture of the physical commodity to be identified, carrying out picture feature identification on the brand of the commodity picture by utilizing a constructed target segmentation model, identifying a target picture fragment in the commodity picture, predicting the deflection angle of the target picture fragment by utilizing the constructed deflection angle classification model, carrying out angle correction and size correction on the target picture fragment based on the deflection angle, and assisting in identifying the authenticity of the brand of the physical commodity by utilizing the corrected target picture fragment. The method comprises the steps of carrying out feature recognition on a commodity picture of a to-be-identified physical commodity to obtain a fragment reflecting the authenticity feature of a commodity brand, predicting the deflection angle of the fragment by using a model, carrying out angle correction and size correction on the fragment to obtain a picture with a better size and an identification angle, carrying out identification of the brand authenticity by using the corrected picture, and improving identification accuracy on the premise of keeping identification speed.
Description
Technical Field
The application relates to the field, in particular to a method and a device for assisting in identifying authenticity of a physical commodity brand and electronic equipment.
Background
The brand of the physical commodity is used as information for distinguishing product sources for users to select commodities, the commodity of the famous brand is often relatively high in price, and many bad merchants are promoted to earn violence by manufacturing fake shoes. Therefore, brand authentication services for providing goods are urged, and a large number of authenticators authenticate users by their own professional skills. The current appraisal mode mainly shoots the commodity picture through the user, passes to appraiser's online appraisal, and appraiser judges according to the picture.
Disclosure of Invention
The embodiment of the specification provides a method, a device and electronic equipment for assisting in identifying authenticity of a physical commodity brand, and aims to solve the problem of low identification accuracy rate in the prior art.
The application provides a method for assisting in identifying authenticity of a physical commodity brand, which comprises the following steps:
acquiring a commodity picture of a physical commodity to be identified;
carrying out picture feature recognition of a brand on the commodity picture by using the constructed target segmentation model, and recognizing a target picture fragment in the commodity picture;
predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model;
and performing angle correction and size correction on the target picture fragment based on the deflection angle, and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
Optionally, the physical goods are shoes.
Optionally, the picture feature of the brand comprises a brand security picture feature.
Optionally, the method further comprises:
acquiring training samples, wherein the training samples comprise commodity pictures containing target picture fragments and commodity pictures not containing the target picture fragments;
marking the area where the target picture fragment is located in the commodity picture containing the target picture fragment;
and constructing a target separation model by using the training samples in a supervised learning mode.
Optionally, the predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model includes:
calculating a circumscribed rectangle of the target picture segment;
and predicting the deflection angle of the target picture segment based on the circumscribed rectangle by using the constructed deflection angle classification model.
Optionally, the angle correction and the size correction of the target picture segment based on the deflection angle include:
rotating the circumscribed rectangle including the target picture segment based on the deflection angle.
Optionally, the angle and size correction of the target picture segment based on the deflection angle further includes:
and amplifying the rotated circumscribed rectangle.
Optionally, before the picture feature recognition of the brand is performed on the commodity picture by using the constructed target segmentation model, the method further includes:
detecting whether a target picture fragment exists in the commodity picture;
and if the commodity picture has the target picture fragment, carrying out picture feature identification on the brand of the commodity picture by utilizing the constructed target segmentation model.
Optionally, the detecting whether the commodity picture has the target picture fragment includes:
and judging whether the commodity picture has the target picture fragment or not by using the constructed target judgment model.
Optionally, the target segmentation model is a deep neural network model.
The application still provides a supplementary device of appraising in kind commodity brand true and false, includes:
the picture acquisition module is used for acquiring a commodity picture of a physical commodity to be identified;
the separation module is used for carrying out picture feature recognition of brands on the commodity pictures by utilizing the constructed target segmentation model, and identifying target picture fragments in the commodity pictures;
the classification module predicts the deflection angle of the target picture segment by using the constructed deflection angle classification model;
and the correction module is used for carrying out angle correction and size correction on the target picture fragment based on the deflection angle and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
Optionally, the physical goods are shoes.
Optionally, the picture feature of the brand comprises a brand security picture feature.
Optionally, the separation module is further configured to:
acquiring training samples, wherein the training samples comprise commodity pictures containing target picture fragments and commodity pictures not containing the target picture fragments;
marking the area where the target picture fragment is located in the commodity picture containing the target picture fragment;
and constructing a target separation model by using the training samples in a supervised learning mode.
Optionally, the predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model includes:
calculating a circumscribed rectangle of the target picture segment;
and predicting the deflection angle of the target picture segment based on the circumscribed rectangle by using the constructed deflection angle classification model.
Optionally, the angle correction and the size correction of the target picture segment based on the deflection angle include:
rotating the circumscribed rectangle including the target picture segment based on the deflection angle.
Optionally, the angle and size correction of the target picture segment based on the deflection angle further includes:
and amplifying the rotated circumscribed rectangle.
Optionally, the system further comprises a judging module, configured to judge whether the commodity picture has a target picture segment before the picture feature recognition of the brand is performed on the commodity picture by using the constructed target segmentation model;
and the separation module is used for carrying out picture feature recognition on the brand of the commodity picture by utilizing the constructed target segmentation model if the commodity picture has the target picture fragment.
Optionally, the detecting whether the commodity picture has the target picture fragment includes:
and judging whether the commodity picture has the target picture fragment or not by using the constructed target judgment model.
Optionally, the target segmentation model is a deep neural network model.
The present application further provides an electronic device, wherein the electronic device includes:
a processor; and the number of the first and second groups,
a memory storing computer-executable instructions that, when executed, cause the processor to perform any of the methods described above.
The present application also provides a computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement any of the methods described above.
In various embodiments described in this specification, a segment reflecting the authenticity characteristics of a brand of a commodity can be obtained by performing feature recognition on a commodity picture of a physical commodity to be authenticated, a deflection angle of the segment is predicted by using a model, and then angle correction and size correction are performed on the segment, so that a picture with a better size and authentication angle can be obtained, and the authenticity of the brand can be authenticated by using the corrected picture, so that the authentication accuracy can be improved on the premise of maintaining the authentication rate.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
fig. 1 is a schematic diagram illustrating a method for assisting in authenticating a brand of a physical commodity according to an embodiment of the present disclosure;
fig. 2 is a schematic structural diagram of an apparatus for assisting in authenticating a brand of a physical commodity according to an embodiment of the present disclosure;
fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure.
Detailed Description
However, as the market volume is increasing, the number of identifications is increasing, so that it is difficult for an authenticator to simultaneously ensure high identification accuracy and identification speed.
By analyzing the prior art, it is found that the identification of the authenticity of the brand of the physical commodity needs to identify the details in the picture, and because the details are not known to the clients with identification requirements, the clients need to rely on an identification engineer for identification, which results in that the clients with identification requirements cannot accurately know which part of the physical commodity can embody the details for identifying the authenticity of the brand, and it is difficult to position the lens on the details required by the identification engineer, therefore, the clients often directly shoot the whole picture of the physical commodity, so that the part capable of identifying the authenticity of the brand of the shoe does not reach a larger size, the identification engineer is difficult to directly identify, on the other hand, the angles of shooting the picture by the clients are various, and the feeling brought by observing the same pattern from different angles is different, this results in a decrease in accuracy when the authentication is performed directly on the basis of the picture taken by the client, a decrease in authentication rate when the picture is manually rotated during the authentication, and the rotation angle is limited by manual operation and is difficult to adjust to the optimum angle.
Therefore, the embodiment of the present specification provides a method for assisting in authenticating a real commodity brand, including:
acquiring a commodity picture of a physical commodity to be identified;
carrying out picture feature recognition of a brand on the commodity picture by using the constructed target segmentation model, and recognizing a target picture fragment in the commodity picture;
predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model;
and performing angle correction and size correction on the target picture fragment based on the deflection angle, and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
The method has the advantages that the commodity picture of the real commodity to be identified is subjected to feature recognition, a fragment reflecting the authenticity feature of a commodity brand can be obtained, the deflection angle of the fragment is predicted by using a model, then angle correction and size correction are carried out on the fragment, the picture with the better size and identification angle can be obtained, the picture subjected to correction is used for identifying the authenticity of the brand, the identification accuracy can be improved on the premise of keeping the identification rate, and the identification efficiency is improved.
Exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. The exemplary embodiments, however, may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art. The same reference numerals denote the same or similar elements, components, or parts in the drawings, and thus their repetitive description will be omitted.
Features, structures, characteristics or other details described in a particular embodiment do not preclude the fact that the features, structures, characteristics or other details may be combined in a suitable manner in one or more other embodiments in accordance with the technical idea of the invention.
In describing particular embodiments, the present invention has been described with reference to features, structures, characteristics or other details that are within the purview of one skilled in the art to provide a thorough understanding of the embodiments. One skilled in the relevant art will recognize, however, that the invention may be practiced without one or more of the specific features, structures, characteristics, or other details.
The flow charts shown in the drawings are merely illustrative and do not necessarily include all of the contents and operations/steps, nor do they necessarily have to be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the actual execution sequence may be changed according to the actual situation.
The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. I.e. these functional entities may be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor means and/or microcontroller means.
The term "and/or" and/or "includes all combinations of any one or more of the associated listed items.
Fig. 1 is a schematic diagram of a method for assisting in authenticating a brand of a physical commodity according to an embodiment of the present disclosure, where the method may include:
s101: and acquiring a commodity picture of the physical commodity to be identified.
In embodiments of the present description, the physical article is an article of footwear, such as a known brand of sneaker.
As the sneaker culture (shoes) rolled up around the globe in the united states, more and more people, particularly young people, began to join the ball banquet. Thus, there is a need for identification of physical goods such as footwear, among others. Since the material of the shoe product is mostly non-rigid material, it is easy to be squeezed and concaved during shooting, so that the details reflecting the brand of the shoe product are easy to be angularly shifted, and therefore, it is more necessary to perform auxiliary identification of the shoe product.
S102: and carrying out picture feature recognition of the brand on the commodity picture by utilizing the constructed target segmentation model, and recognizing a target picture fragment in the commodity picture.
In the embodiment of the present specification, the picture features of the brand include a brand anti-counterfeit picture feature, such as a brand trademark, a serial number, a side mark, and the like, details of the genuine products and the fake-brand products are different, and features of the picture of the genuine products can be used as the brand anti-counterfeit picture feature.
In an embodiment of the present specification, the method may further include:
acquiring training samples, wherein the training samples comprise commodity pictures containing target picture fragments and commodity pictures not containing the target picture fragments;
marking the area where the target picture fragment is located in the commodity picture containing the target picture fragment;
and constructing a target separation model by using the training samples in a supervised learning mode.
After the region where the target picture segment is located is marked, a mask with the outline of the region is generated for the corresponding commodity picture.
Because the region where the target picture fragment is located is marked in the commodity picture containing the target picture fragment, and the region where the target picture fragment is not marked in the commodity picture containing the target picture fragment is not marked, the region is used as a white sample and a black sample, and a target separation model is trained, so that the model can learn how to obtain the region where the target picture fragment is located from the picture to be identified.
For the object separation model, a deep neural network model, a convolutional neural network model, a mask-RCNN (area mask convolutional neural network model), a fast-R-CNN (fast area convolutional neural network model) may be used.
The Mask RCNN is a very advanced target segmentation network at present, the idea of fast RCNN is used, the ResNet-FPN architecture is adopted for feature extraction, a Mask prediction branch is additionally arranged, image identification and pixel level segmentation can be well achieved, and detailed description is not provided.
In view of practical application scenarios, a network may be used as a classifier to determine whether there is a target that we need in an input image, and therefore, in this embodiment of the present specification, before performing picture feature recognition of a brand on the commodity picture by using the constructed target segmentation model, the method may further include:
detecting whether a target picture fragment exists in the commodity picture;
and if the commodity picture has the target picture fragment, carrying out picture feature identification on the brand of the commodity picture by utilizing the constructed target segmentation model.
This may be identification and discrimination by using the constructed model, and therefore, optionally, the detecting whether the commodity picture has the target picture segment may include:
and judging whether the commodity picture has the target picture fragment or not by using the constructed target judgment model.
For the target discrimination model, the commodity image with the target picture segment may be used as a white sample, the image without the target picture segment may be used as a black sample, and a sample label is set for training, which is not specifically described herein.
The layer structure of the target discrimination model can be a Resnet (depth residual error network model), and the pioneering residual error structure provides a good way for solving gradient dispersion and explosion.
S103: and predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model.
In the embodiment of the specification, the deflection angle classification model is a classification model, and the difficulty of determining the deflection angle by using a regression sample picture is higher than the difficulty of determining the deflection angle by using classification, so that a target picture fragment is identified first, and then the deflection angle is determined by using the classification model, so that the method is easy to implement, and the complexity of auxiliary identification is reduced.
In an embodiment of the present specification, the predicting a deflection angle of the target picture segment by using the constructed deflection angle classification model may include:
calculating a circumscribed rectangle of the target picture segment;
and predicting the deflection angle of the target picture segment based on the circumscribed rectangle by using the constructed deflection angle classification model.
In one embodiment, a lightweight yaw angle classification model can be constructed, such as: squeeze-Net. Alternatively, if 5 categories are predicted, the labels may be set to 0 (not target), 1(0 degrees), 2(90 degrees), 3(180 degrees), 4(270 degrees).
The included angle of the four sides of the rectangle on the X axis is calculated by determining the deflection angle, so that the image can be corrected by rotating and correcting the image in the direction opposite to the minimum included angle. The X-axis may be a reference set according to a commodity placement angle required by an authenticator.
The 4 categories are used to determine the direction of the target from which the split network is to be split, and the "not target" category is added because the split network may be split with erroneous results. A part of erroneous results can be filtered out by the category 0, and the robustness of the system is increased.
S104: and performing angle correction and size correction on the target picture fragment based on the deflection angle, and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
The method comprises the steps of carrying out feature recognition on a commodity picture of a to-be-identified physical commodity to obtain a fragment reflecting the authenticity feature of a commodity brand, predicting the deflection angle of the fragment by using a model, carrying out angle correction and size correction on the fragment to obtain a picture with a better size and an identification angle, carrying out identification of the brand authenticity by using the corrected picture, and improving identification accuracy on the premise of keeping identification speed.
In an embodiment of the present specification, the performing angle correction and size correction on the target picture segment based on the deflection angle may include:
rotating the circumscribed rectangle including the target picture segment based on the deflection angle.
Before rotating the circumscribed rectangle containing the target picture segment, initial alignment may be performed first, and then rotation may be performed.
Optionally, the performing angle correction and size correction on the target picture segment based on the deflection angle may further include:
and amplifying the rotated circumscribed rectangle.
After performing angle correction and size correction on the target picture segment based on the deflection angle, the method may further include: and replacing the commodity picture to be authenticated with the corrected target picture fragment.
In addition, the key parts (target picture fragments) of the shoe products are separated by utilizing the target segmentation model obtained by deep learning, and the key parts of the shoe products are judged by utilizing the classification model obtained by deep learning, so that the method is suitable for identifying the shoe products of various brands, the model for assisting identification is not required to be adjusted according to the shoe products of different brands manually, and only the samples of various brands are required to be collected when the model is constructed.
Fig. 2 is a schematic structural diagram of an apparatus for assisting in authenticating a real brand of a physical commodity according to an embodiment of the present disclosure, where the apparatus may include:
the picture acquisition module 201 is used for acquiring a commodity picture of a physical commodity to be identified;
the separation module 202 is used for performing brand image feature identification on the commodity image by using the constructed target segmentation model, and identifying a target image fragment in the commodity image;
the classification module 203 predicts the deflection angle of the target picture segment by using the constructed deflection angle classification model;
and the correction module 204 is used for performing angle correction and size correction on the target picture fragment based on the deflection angle, and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
Optionally, the physical goods are shoes, and the picture features of the brand include brand anti-counterfeiting picture features.
Optionally, the separation module 202 is further configured to:
acquiring training samples, wherein the training samples comprise commodity pictures containing target picture fragments and commodity pictures not containing the target picture fragments;
marking the area where the target picture fragment is located in the commodity picture containing the target picture fragment;
and constructing a target separation model by using the training samples in a supervised learning mode.
Optionally, the predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model includes:
calculating a circumscribed rectangle of the target picture segment;
and predicting the deflection angle of the target picture segment based on the circumscribed rectangle by using the constructed deflection angle classification model.
Optionally, the angle correction and the size correction of the target picture segment based on the deflection angle include:
rotating the circumscribed rectangle including the target picture segment based on the deflection angle.
Optionally, the angle and size correction of the target picture segment based on the deflection angle further includes:
and amplifying the rotated circumscribed rectangle.
Optionally, the system further comprises a judging module, configured to judge whether the commodity picture has a target picture segment before the picture feature recognition of the brand is performed on the commodity picture by using the constructed target segmentation model;
the separation module 202 is configured to, if the commodity picture has a target picture fragment, perform picture feature identification of a brand on the commodity picture by using the constructed target segmentation model.
Optionally, the detecting whether the commodity picture has the target picture fragment includes:
and judging whether the commodity picture has the target picture fragment or not by using the constructed target judgment model.
Optionally, the target segmentation model is a deep neural network model.
The device carries out feature recognition through the commodity picture of treating the real object commodity of appraising, can obtain the fragment that reflects commodity brand true and false characteristic, utilizes the deflection angle of this fragment of model prediction, and then carries out angle correction and size correction to this fragment, alright in order to obtain the picture of preferred size and appraisal angle, utilizes the picture of this kind of correction to carry out the appraisal of brand true and false, can improve the appraisal rate of accuracy under the prerequisite that keeps appraisal speed.
Based on the same inventive concept, the embodiment of the specification further provides the electronic equipment.
In the following, embodiments of the electronic device of the present invention are described, which may be regarded as specific physical implementations for the above-described embodiments of the method and apparatus of the present invention. Details described in the embodiments of the electronic device of the invention should be considered supplementary to the embodiments of the method or apparatus described above; for details which are not disclosed in embodiments of the electronic device of the invention, reference may be made to the above-described embodiments of the method or the apparatus.
Fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present disclosure. An electronic device 300 according to this embodiment of the invention is described below with reference to fig. 3. The electronic device 300 shown in fig. 3 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present invention.
As shown in fig. 3, electronic device 300 is embodied in the form of a general purpose computing device. The components of electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one memory unit 320, a bus 330 connecting the various system components (including the memory unit 320 and the processing unit 310), a display unit 340, and the like.
Wherein the storage unit stores program code executable by the processing unit 310 to cause the processing unit 310 to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned processing method section of the present specification. For example, the processing unit 310 may perform the steps as shown in fig. 1.
The storage unit 320 may include readable media in the form of volatile storage units, such as a random access memory unit (RAM)3201 and/or a cache storage unit 3202, and may further include a read only memory unit (ROM) 3203.
The storage unit 320 may also include a program/utility 3204 having a set (at least one) of program modules 3205, such program modules 3205 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which, or some combination thereof, may comprise an implementation of a network environment.
The electronic device 300 may also communicate with one or more external devices 400 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 300, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 300 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 350. Also, the electronic device 300 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the internet) via the network adapter 360. Network adapter 360 may communicate with other modules of electronic device 300 via bus 330. It should be appreciated that although not shown in FIG. 3, other hardware and/or software modules may be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
Through the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments of the present invention described herein may be implemented by software, or by software in combination with necessary hardware. Therefore, the technical solution according to the embodiment of the present invention can be embodied in the form of a software product, which can be stored in a computer-readable storage medium (which can be a CD-ROM, a usb disk, a removable hard disk, etc.) or on a network, and includes several instructions to make a computing device (which can be a personal computer, a server, or a network device, etc.) execute the above-mentioned method according to the present invention. The computer program, when executed by a data processing apparatus, enables the computer readable medium to implement the above-described method of the invention, namely: such as the method shown in fig. 1.
The computer program may be stored on one or more computer readable media. The computer readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The computer readable storage medium may include a propagated data signal with readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A readable storage medium may also be any readable medium that is not a readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., through the internet using an internet service provider).
In summary, the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. Those skilled in the art will appreciate that some or all of the functionality of some or all of the components in embodiments in accordance with the invention may be implemented in practice using a general purpose data processing device such as a microprocessor or a Digital Signal Processor (DSP). The present invention may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
While the foregoing embodiments have described the objects, aspects and advantages of the present invention in further detail, it should be understood that the present invention is not inherently related to any particular computer, virtual machine or electronic device, and various general-purpose machines may be used to implement the present invention. The invention is not to be considered as limited to the specific embodiments thereof, but is to be understood as being modified in all respects, all changes and equivalents that come within the spirit and scope of the invention.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (20)
1. A method for assisting in identifying authenticity of a physical commodity brand comprises the following steps:
acquiring a commodity picture of a physical commodity to be identified;
carrying out picture feature recognition of a brand on the commodity picture by using the constructed target segmentation model, and recognizing a target picture fragment in the commodity picture;
predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model;
and performing angle correction and size correction on the target picture fragment based on the deflection angle, and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
2. The method of claim 1, wherein the physical good is an article of footwear.
3. The method of claim 1, further comprising:
acquiring training samples, wherein the training samples comprise commodity pictures containing target picture fragments and commodity pictures not containing the target picture fragments;
marking the area where the target picture fragment is located in the commodity picture containing the target picture fragment;
and constructing a target separation model by using the training samples in a supervised learning mode.
4. The method according to claim 3, wherein the predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model comprises:
calculating a circumscribed rectangle of the target picture segment;
and predicting the deflection angle of the target picture segment based on the circumscribed rectangle by using the constructed deflection angle classification model.
5. The method of claim 4, the angle correcting and size correcting the target picture segment based on the deflection angle, comprising:
rotating the circumscribed rectangle including the target picture segment based on the deflection angle.
6. The method of claim 5, the angle correcting and size correcting the target picture segment based on the deflection angle, further comprising:
and amplifying the rotated circumscribed rectangle.
7. The method of claim 1, further comprising, before the picture feature recognition of the brand of the commodity picture by using the constructed target segmentation model, the following steps:
detecting whether a target picture fragment exists in the commodity picture;
and if the commodity picture has the target picture fragment, carrying out picture feature identification on the brand of the commodity picture by utilizing the constructed target segmentation model.
8. The method of claim 7, the detecting whether the commodity picture has a target picture segment therein, comprising:
and judging whether the commodity picture has the target picture fragment or not by using the constructed target judgment model.
9. The method of claim 1, the target segmentation model being a deep neural network model.
10. An apparatus for assisting in identifying the authenticity of a physical good brand, comprising:
the picture acquisition module is used for acquiring a commodity picture of a physical commodity to be identified;
the separation module is used for carrying out picture feature recognition of brands on the commodity pictures by utilizing the constructed target segmentation model, and identifying target picture fragments in the commodity pictures;
the classification module predicts the deflection angle of the target picture segment by using the constructed deflection angle classification model;
and the correction module is used for carrying out angle correction and size correction on the target picture fragment based on the deflection angle and assisting the identification of the brand authenticity of the physical commodity by using the corrected target picture fragment.
11. The apparatus of claim 10, wherein the physical good is an article of footwear.
12. The apparatus of claim 10, the separation module further to:
acquiring training samples, wherein the training samples comprise commodity pictures containing target picture fragments and commodity pictures not containing the target picture fragments;
marking the area where the target picture fragment is located in the commodity picture containing the target picture fragment;
and constructing a target separation model by using the training samples in a supervised learning mode.
13. The apparatus according to claim 12, wherein the predicting the deflection angle of the target picture segment by using the constructed deflection angle classification model comprises:
calculating a circumscribed rectangle of the target picture segment;
and predicting the deflection angle of the target picture segment based on the circumscribed rectangle by using the constructed deflection angle classification model.
14. The apparatus of claim 13, the angle and size correcting the target picture segment based on the yaw angle, comprising:
rotating the circumscribed rectangle including the target picture segment based on the deflection angle.
15. The apparatus of claim 14, the angle and size correcting the target picture segment based on the yaw angle, further comprising:
and amplifying the rotated circumscribed rectangle.
16. The device of claim 10, further comprising a determining module, configured to determine whether there is a target picture segment in the commodity picture before the picture feature recognition of the brand is performed on the commodity picture by using the constructed target segmentation model;
and the separation module is used for carrying out picture feature recognition on the brand of the commodity picture by utilizing the constructed target segmentation model if the commodity picture has the target picture fragment.
17. The apparatus of claim 16, the detecting whether the picture of the good has a target picture segment therein, comprising:
and judging whether the commodity picture has the target picture fragment or not by using the constructed target judgment model.
18. The apparatus of claim 10, the target segmentation model being a deep neural network model.
19. An electronic device, wherein the electronic device comprises:
a processor; and the number of the first and second groups,
a memory storing computer-executable instructions that, when executed, cause the processor to perform the method of any of claims 1-9.
20. A computer readable storage medium, wherein the computer readable storage medium stores one or more programs which, when executed by a processor, implement the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911192888.2A CN111008655A (en) | 2019-11-28 | 2019-11-28 | Method and device for assisting in identifying authenticity of physical commodity brand and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911192888.2A CN111008655A (en) | 2019-11-28 | 2019-11-28 | Method and device for assisting in identifying authenticity of physical commodity brand and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111008655A true CN111008655A (en) | 2020-04-14 |
Family
ID=70112263
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911192888.2A Pending CN111008655A (en) | 2019-11-28 | 2019-11-28 | Method and device for assisting in identifying authenticity of physical commodity brand and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111008655A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508072A (en) * | 2020-11-30 | 2021-03-16 | 云南省烟草质量监督检测站 | Cigarette true and false identification method, device and equipment based on residual convolutional neural network |
| CN112633383A (en) * | 2020-12-25 | 2021-04-09 | 百度在线网络技术（北京）有限公司 | Antique identification method and device, electronic equipment and readable medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329735A (en) * | 2008-06-27 | 2008-12-24 | 北京中星微电子有限公司 | Device and method for identifying hand-written signature |
| CN102982332A (en) * | 2012-09-29 | 2013-03-20 | 顾坚敏 | Retail terminal goods shelf image intelligent analyzing system based on cloud processing method |
| CN107358242A (en) * | 2017-07-11 | 2017-11-17 | 浙江宇视科技有限公司 | Target area color identification method, device and monitor terminal |
| CN108388935A (en) * | 2017-07-03 | 2018-08-10 | 林力东 | A kind of method for anti-counterfeit and system |
| CN108764306A (en) * | 2018-05-15 | 2018-11-06 | 深圳大学 | Image classification method, device, computer equipment and storage medium |
| US10140726B2 (en) * | 2015-02-25 | 2018-11-27 | Canon Kabushiki Kaisha | Apparatus and method for estimating gazed position of person |
| CN109241968A (en) * | 2018-09-25 | 2019-01-18 | 广东工业大学 | Picture material tilt angle predicts network training method and modification method, system |
| US10192301B1 (en) * | 2017-08-16 | 2019-01-29 | Siemens Energy, Inc. | Method and system for detecting line defects on surface of object |
| CN110148121A (en) * | 2019-05-09 | 2019-08-20 | 腾讯科技（深圳）有限公司 | A kind of skin image processing method, device, electronic equipment and medium |
| CN110458830A (en) * | 2019-03-08 | 2019-11-15 | 腾讯科技（深圳）有限公司 | Image processing method, device, server and storage medium |
-
2019
- 2019-11-28 CN CN201911192888.2A patent/CN111008655A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101329735A (en) * | 2008-06-27 | 2008-12-24 | 北京中星微电子有限公司 | Device and method for identifying hand-written signature |
| CN102982332A (en) * | 2012-09-29 | 2013-03-20 | 顾坚敏 | Retail terminal goods shelf image intelligent analyzing system based on cloud processing method |
| US10140726B2 (en) * | 2015-02-25 | 2018-11-27 | Canon Kabushiki Kaisha | Apparatus and method for estimating gazed position of person |
| CN108388935A (en) * | 2017-07-03 | 2018-08-10 | 林力东 | A kind of method for anti-counterfeit and system |
| CN107358242A (en) * | 2017-07-11 | 2017-11-17 | 浙江宇视科技有限公司 | Target area color identification method, device and monitor terminal |
| US10192301B1 (en) * | 2017-08-16 | 2019-01-29 | Siemens Energy, Inc. | Method and system for detecting line defects on surface of object |
| CN108764306A (en) * | 2018-05-15 | 2018-11-06 | 深圳大学 | Image classification method, device, computer equipment and storage medium |
| CN109241968A (en) * | 2018-09-25 | 2019-01-18 | 广东工业大学 | Picture material tilt angle predicts network training method and modification method, system |
| CN110458830A (en) * | 2019-03-08 | 2019-11-15 | 腾讯科技（深圳）有限公司 | Image processing method, device, server and storage medium |
| CN110148121A (en) * | 2019-05-09 | 2019-08-20 | 腾讯科技（深圳）有限公司 | A kind of skin image processing method, device, electronic equipment and medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112508072A (en) * | 2020-11-30 | 2021-03-16 | 云南省烟草质量监督检测站 | Cigarette true and false identification method, device and equipment based on residual convolutional neural network |
| CN112508072B (en) * | 2020-11-30 | 2024-04-26 | 云南省烟草质量监督检测站 | Cigarette true and false identification method, device and equipment based on residual convolution neural network |
| CN112633383A (en) * | 2020-12-25 | 2021-04-09 | 百度在线网络技术（北京）有限公司 | Antique identification method and device, electronic equipment and readable medium |
| CN112633383B (en) * | 2020-12-25 | 2023-08-18 | 百度在线网络技术（北京）有限公司 | Ancient game authentication method and device, electronic equipment and readable medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Neubert et al. | Extended StirTrace benchmarking of biometric and forensic qualities of morphed face images | |
| CN109409204B (en) | Anti-counterfeiting detection method and device, electronic equipment and storage medium | |
| CN110363220B (en) | Behavior class detection method and device, electronic equipment and computer readable medium | |
| CN110812845B (en) | Plug-in detection method, plug-in recognition model training method and related device | |
| CN113627395B (en) | Text recognition method, device, medium and electronic equipment | |
| US10769247B2 (en) | System and method for interacting with information posted in the media | |
| CN113887438B (en) | Watermark detection method, device, equipment and medium for face image | |
| CN112214984A (en) | Content plagiarism identification method, device, equipment and storage medium | |
| CN112712005B (en) | Training method of recognition model, target recognition method and terminal equipment | |
| CN111008655A (en) | Method and device for assisting in identifying authenticity of physical commodity brand and electronic equipment | |
| CN107729928A (en) | Information acquisition method and device | |
| Gong et al. | A novel unified deep neural networks methodology for use by date recognition in retail food package image | |
| CN111415336A (en) | Image tampering identification method and device, server and storage medium | |
| CN112115921A (en) | True and false identification method and device and electronic equipment | |
| US20130191641A1 (en) | Captcha (completely automated public test to tell computers and humans apart) data generation methods and related data management systems and computer program products thereof | |
| CN113361643A (en) | Deep learning-based universal mark identification method, system, equipment and storage medium | |
| Warif et al. | A comprehensive evaluation procedure for copy-move forgery detection methods: results from a systematic review | |
| Naeem et al. | Digital forensics for malware classification: An approach for binary code to pixel vector transition | |
| CN113705468B (en) | Digital image recognition method based on artificial intelligence and related equipment | |
| CN113627576B (en) | Code scanning information detection method, device, equipment and storage medium | |
| Xia et al. | DMFF-Net: Double-stream multilevel feature fusion network for image forgery localization | |
| CN111476090B (en) | Watermark identification method and device | |
| CN117523586A (en) | Check seal verification method and device, electronic equipment and medium | |
| Hu et al. | Fast sign recognition with weighted hybrid K-nearest neighbors based on holistic features from local feature descriptors | |
| CN112801960B (en) | Image processing method and device, storage medium and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: Room 6416, Building 13, No. 723 Tongxin Road, Hongkou District, Shanghai 200080 Applicant after: Shanghai Dewu Information Group Co.,Ltd. Address before: Room B6-2005, No. 121 Zhongshan North 1st Road, Hongkou District, Shanghai Applicant before: SHANGHAI SHIZHUANG INFORMATION TECHNOLOGY Co.,Ltd. Country or region before: China |