CN111144438A - Method and device for detecting commodities in advertisement bill - Google Patents
Method and device for detecting commodities in advertisement bill Download PDFInfo
- Publication number
- CN111144438A CN111144438A CN201911171153.1A CN201911171153A CN111144438A CN 111144438 A CN111144438 A CN 111144438A CN 201911171153 A CN201911171153 A CN 201911171153A CN 111144438 A CN111144438 A CN 111144438A
- Authority
- CN
- China
- Prior art keywords
- commodity
- advertisement
- model
- trained
- detected
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0241—Advertisements
- G06Q30/0277—Online advertisement
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention provides a method and a device for detecting commodities in an advertisement bill, wherein the method comprises the following steps: inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected; inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity; and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill. According to the method and the device for detecting the commodities in the advertisement leaflet, provided by the embodiment of the invention, the image of the advertisement leaflet is processed by using the deep learning neural network, and the characteristics of the texture, the edge and the like of the image are automatically extracted and combined, so that the position of the commodity in the advertisement leaflet is detected, and the extracted commodity is vectorized, so that the position of the commodity can be rapidly compared with the commodities in a commodity library.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a method and a device for detecting commodities in an advertisement bill.
Background
In recent years, with the rapid development of electronic commerce, along with the continuous expansion of the market and the continuous increase of various commercial industries, more and more articles can be selected, purchased and used by users. In practice, merchants often market goods in the form of advertising slips.
At present, in the prior art, a detection-based technology is generally adopted to detect the commodities in the advertisement bill. However, this method has the following problems: firstly, the method is limited by data and fixed categories in a classification stage, and cannot be well adapted to a rapidly-changing commodity library, secondly, because commodities in an advertisement list are numerous and possibly mutually shielded, if the commodities are classified from a minimum bounding box, partial images of the commodities causing shielding are introduced, and excessive noise exists in input.
Therefore, a new method for detecting merchandise in an advertisement bill is needed to solve the above problems.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a method and an apparatus for detecting a product in an advertisement leaflet, which overcome the above problems or at least partially solve the above problems.
In a first aspect, an embodiment of the present invention provides a method for detecting a commodity in an advertisement leaflet, including:
inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected;
inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity;
and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill.
Before the to-be-detected advertisement leaflet is input into the trained commodity detection model, the method further comprises the following steps:
and establishing the commodity detection model, and training the commodity detection model to obtain the trained commodity detection model.
Before the to-be-detected advertisement leaflet is input into the trained commodity detection model, the method further comprises the following steps:
and establishing the commodity comparison model, and training the commodity comparison model to obtain the trained commodity comparison model.
Wherein, the training the commodity comparison model comprises:
forming a commodity pair by the three commodity pictures, wherein the two commodity pictures are the same commodity;
based on the twin network, vectors are extracted for each commodity pair, and the euclidean distance between the vectors is calculated.
In a second aspect, an embodiment of the present invention further provides a device for detecting a commodity in an advertisement leaflet, including:
the advertisement bill input module is used for inputting the advertisement bill to be detected into the trained commodity detection model and acquiring the commodity information in the advertisement bill to be detected;
the characteristic extraction module is used for inputting the commodity information into a trained commodity comparison model and extracting a characteristic vector of the commodity;
and the detection module is used for comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library and determining the commodity category with the similarity smaller than a preset pre-support so as to finish the detection of the commodity in the to-be-detected bill.
Wherein, commodity detection device still includes in the bill of advertisement:
and the first model training module is used for establishing the commodity detection model and training the commodity detection model to obtain the trained commodity detection model.
Wherein, commodity detection device still includes in the bill of advertisement:
and the second model training module is used for establishing the commodity comparison model and training the commodity comparison model to obtain the trained commodity comparison model.
Wherein the second model training module is specifically configured to:
forming a commodity pair by the three commodity pictures, wherein the two commodity pictures are the same commodity;
based on the twin network, vectors are extracted for each commodity pair, and the euclidean distance between the vectors is calculated.
Third aspect an embodiment of the present invention provides an electronic device, including:
a processor, a memory, a communication interface, and a bus; the processor, the memory and the communication interface complete mutual communication through the bus; the memory stores program instructions executable by the processor, and the processor calls the program instructions to execute the method for detecting the commodity in the advertisement bill.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer-readable storage medium storing computer instructions, which cause the computer to execute the method for detecting a product in an advertisement slip.
According to the method and the device for detecting the commodities in the advertisement leaflet, provided by the embodiment of the invention, the image of the advertisement leaflet is processed by using the deep learning neural network, and the characteristics of the texture, the edge and the like of the image are automatically extracted and combined, so that the position of the commodity in the advertisement leaflet is detected, and the extracted commodity is vectorized, so that the position of the commodity can be rapidly compared with the commodities in a commodity library.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for detecting a commodity in an advertisement bill according to an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a device for detecting merchandise in an advertisement leaflet according to an embodiment of the present invention;
fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some embodiments, but not all embodiments, of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart of a method for detecting a commodity in an advertisement leaflet according to an embodiment of the present invention, as shown in fig. 1, the method includes:
101. inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected;
102. inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity;
103. and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill.
It should be noted that the execution subject of the embodiment of the present invention is a computer software program pre-stored in a computer device, and the implementation scenario is an environment where manual identification is not accurate and cost of manual identification is too high in the process of identifying a commodity by an advertisement leaflet.
Specifically, in step 101, each advertisement slip to be detected, that is, the advertisement slip to be detected in the embodiment of the present invention, is input into a trained product detection model, where the product detection model is obtained by training in advance according to business requirements by using a deep neural network architecture, and it is capable of automatically extracting features such as texture and edge of a picture, so as to accurately determine the position of a product in the advertisement slip. Preferably, in the actual identification process, the embodiment of the present invention outputs an outer surrounding frame of the commodity and whether pixels in the frame belong to a mask of the commodity, and in the embodiment of the present invention, the above features related to the commodity are collectively referred to as commodity information.
Further, in step 102, the embodiment of the present invention inputs the output result of the commodity detection model, that is, the commodity information in the embodiment of the present invention, into the commodity comparison model trained in advance, and performs commodity comparison. Similarly, the commodity comparison model is a neural network model which is trained in advance and used for extracting the characteristics of the commodity in the embodiment of the invention. The model vectorizes the characteristics of the commodity and outputs the characteristic vector of the commodity.
Finally, in step 103, the obtained commodity feature vector is compared with commodities in a preset commodity library, and a target commodity with the similarity smaller than a preset threshold is found in the commodity library, so that the commodity type in the to-be-detected bill is determined, and the detection and classification of the commodity type are completed.
According to the method for detecting the commodities in the advertisement leaflet, provided by the embodiment of the invention, the image of the advertisement leaflet is processed by using the deep learning neural network, and the characteristics of the texture, the edge and the like of the image are automatically extracted and combined, so that the position of the commodities in the advertisement leaflet is detected, and the extracted commodities are vectorized, so that the commodities can be rapidly compared with the commodities in a commodity library.
Meanwhile, the method provided by the embodiment of the invention has the characteristics of simple deployment, less manual intervention, high automation degree and the like. The commodity categories in the advertisement bill can be detected in a short time, the labor intensity and the working time of manual processing are reduced, and the commodity classification cost of the advertisement bill is reduced.
On the basis of the above embodiment, before the to-be-detected advertisement leaflet is input into the trained commodity detection model, the method further includes:
and establishing the commodity detection model, and training the commodity detection model to obtain the trained commodity detection model.
It can be seen from the above description that, in the embodiment of the present invention, a product detection model needs to be trained in advance to automatically extract a product from an advertisement bill.
Specifically, when the commodity detection model is trained, the training data adopted in the embodiment of the present invention are: the method comprises the steps of obtaining an advertisement list image of a commodity and a definite commodity position in the advertisement list, wherein the position is expressed in the form of coordinates of a left upper corner point and a right lower corner point of a minimum enclosing rectangle of the outer contour of the commodity and a mask of the commodity.
In the specific training process, the embodiment of the invention adopts mask-rcnn to detect, inputs the advertisement bill image containing the commodity into the model, detects the characteristics and outputs the outer surrounding frames of all commodities in the image and whether the pixels in the frames belong to the mask of the commodity.
On the basis of the above embodiment, before the to-be-detected advertisement leaflet is input into the trained commodity detection model, the method further includes:
and establishing the commodity comparison model, and training the commodity comparison model to obtain the trained commodity comparison model.
The training of the commodity comparison model comprises:
forming a commodity pair by the three commodity pictures, wherein the two commodity pictures are the same commodity;
based on the twin network, vectors are extracted for each commodity pair, and the euclidean distance between the vectors is calculated.
As can be seen from the above description, in the embodiment of the present invention, a product comparison model needs to be trained to classify the detected product types.
The training data of the commodity comparison model can require three commodities to form a commodity pair, wherein two pictures are the same commodity, and the other picture is the other commodity. Meanwhile, the embodiment of the invention will use the result of pairing three commodities two by two, namely whether they are the same commodity or not as a label.
The commodity comparison model used in the embodiment of the invention uses interception-resnet-v 2 as a backbone network, the characteristics of the commodity are extracted, and then L2 norm normalization is carried out on the characteristics of the commodity, so that a 512-dimensional vector is obtained, namely the commodity characteristics. During specific training, a twin network structure is adopted, vectors are extracted from commodity pairs consisting of three commodity pictures respectively, pairwise comparison is carried out, and the Euclidean distance is calculated. If the Euclidean distance of the characteristic vector of two pictures which belong to one commodity and are recorded in the label is too large, the loss is recorded. Similarly, if the euclidean distance between two pictures not belonging to the same product is too small, a loss will be recorded. Thereby supervising the network learning to a distinctive feature.
It should be noted that, in the embodiment of the present invention, the commodity picture in the commodity library is defined according to the business requirement, and the feature corresponding to the commodity picture is extracted and stored in the commodity comparison library.
Fig. 2 is a schematic structural diagram of a device for detecting a commodity in an advertisement leaflet according to an embodiment of the present invention, as shown in fig. 2, the device includes: an advertisement bill input module 201, a feature extraction module 202 and a detection module 203, wherein:
the advertisement leaflet input module 201 is used for inputting the advertisement leaflet to be detected into the trained commodity detection model to acquire the commodity information in the advertisement leaflet to be detected;
the feature extraction module 202 is configured to input the commodity information into a trained commodity comparison model, and extract a feature vector of a commodity;
the detection module 203 is configured to perform similarity comparison on the feature vector of the commodity and a commodity vector in a preset commodity comparison library, and determine a commodity category of which the similarity is smaller than a preset pre-support, so as to complete detection on the commodity in the to-be-detected bill.
Specifically, how to use the advertisement slip input module 201, the feature extraction module 202, and the detection module 203 to execute the technical solution of the embodiment of the method for detecting a commodity in an advertisement slip shown in fig. 1 is similar, and the implementation principle and the technical effect thereof are similar, and are not described herein again.
According to the commodity detection device in the advertisement leaflet, the deep learning neural network is used for processing the image of the advertisement leaflet, and the characteristics of the texture, the edge and the like of the image are automatically extracted and combined, so that the position of the commodity in the advertisement leaflet is detected, and the extracted commodity is vectorized, so that the position of the commodity can be quickly compared with the commodity in the commodity library.
On the basis of the above embodiment, the device for detecting a commodity in an advertisement leaflet further includes:
and the first model training module is used for establishing the commodity detection model and training the commodity detection model to obtain the trained commodity detection model.
On the basis of the above embodiment, the device for detecting a commodity in an advertisement leaflet further includes:
and the second model training module is used for establishing the commodity comparison model and training the commodity comparison model to obtain the trained commodity comparison model.
On the basis of the foregoing embodiment, the second model training module is specifically configured to:
forming a commodity pair by the three commodity pictures, wherein the two commodity pictures are the same commodity;
based on the twin network, vectors are extracted for each commodity pair, and the euclidean distance between the vectors is calculated.
Fig. 3 is a block diagram of an electronic device according to an embodiment of the present invention, and referring to fig. 3, the electronic device includes: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the bus 304. Processor 301 may call logic instructions in memory 303 to perform the following method: inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected; inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity; and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill.
An embodiment of the present invention discloses a computer program product, which includes a computer program stored on a non-transitory computer readable storage medium, the computer program including program instructions, when the program instructions are executed by a computer, the computer can execute the methods provided by the above method embodiments, for example, the method includes: inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected; inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity; and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill.
Embodiments of the present invention provide a non-transitory computer-readable storage medium, which stores computer instructions, where the computer instructions cause the computer to perform the methods provided by the above method embodiments, for example, the methods include: inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected; inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity; and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method according to each embodiment or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for detecting commodities in an advertisement bill is characterized by comprising the following steps:
inputting the advertisement sheet to be detected into a trained commodity detection model, and acquiring commodity information in the advertisement sheet to be detected;
inputting the commodity information into a trained commodity comparison model, and extracting a characteristic vector of the commodity;
and comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library, and determining the commodity category with the similarity smaller than a preset pre-set value so as to finish the detection of the commodity in the to-be-detected bill.
2. The method for detecting merchandise in advertisement leaflet of claim 1, wherein before inputting the advertisement leaflet to be detected into the trained merchandise detection model, the method further comprises:
and establishing the commodity detection model, and training the commodity detection model to obtain the trained commodity detection model.
3. The method for detecting merchandise in advertisement leaflet of claim 2, wherein before inputting the advertisement leaflet to be detected into the trained merchandise detection model, the method further comprises:
and establishing the commodity comparison model, and training the commodity comparison model to obtain the trained commodity comparison model.
4. The method of claim 3, wherein the training of the product comparison model comprises:
forming a commodity pair by the three commodity pictures, wherein the two commodity pictures are the same commodity;
based on the twin network, vectors are extracted for each commodity pair, and the euclidean distance between the vectors is calculated.
5. An apparatus for detecting a commodity in an advertisement leaflet, comprising:
the advertisement bill input module is used for inputting the advertisement bill to be detected into the trained commodity detection model and acquiring the commodity information in the advertisement bill to be detected;
the characteristic extraction module is used for inputting the commodity information into a trained commodity comparison model and extracting a characteristic vector of the commodity;
and the detection module is used for comparing the similarity of the characteristic vector of the commodity with the commodity vector in a preset commodity comparison library and determining the commodity category with the similarity smaller than a preset pre-support so as to finish the detection of the commodity in the to-be-detected bill.
6. The apparatus for detecting merchandise in advertisement leaflet of claim 5, characterized in that said apparatus for detecting merchandise in advertisement leaflet further comprises:
and the first model training module is used for establishing the commodity detection model and training the commodity detection model to obtain the trained commodity detection model.
7. The apparatus for detecting merchandise in an advertisement leaflet of claim 6, wherein the apparatus for detecting merchandise in an advertisement leaflet further comprises:
and the second model training module is used for establishing the commodity comparison model and training the commodity comparison model to obtain the trained commodity comparison model.
8. The device for detecting the commodities in the advertisement leaflet as claimed in claim 7, wherein the second model training module is specifically configured to:
forming a commodity pair by the three commodity pictures, wherein the two commodity pictures are the same commodity;
based on the twin network, vectors are extracted for each commodity pair, and the euclidean distance between the vectors is calculated.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for detecting an item in an advertisement leaflet as claimed in any one of claims 1 to 4.
10. A non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program, when executed by a processor, implements the steps of the method for detecting an item in an advertisement leaflet as claimed in any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911171153.1A CN111144438A (en) | 2019-11-26 | 2019-11-26 | Method and device for detecting commodities in advertisement bill |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911171153.1A CN111144438A (en) | 2019-11-26 | 2019-11-26 | Method and device for detecting commodities in advertisement bill |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144438A true CN111144438A (en) | 2020-05-12 |
Family
ID=70516702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911171153.1A Pending CN111144438A (en) | 2019-11-26 | 2019-11-26 | Method and device for detecting commodities in advertisement bill |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144438A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065447A (en) * | 2021-03-29 | 2021-07-02 | 南京掌控网络科技有限公司 | Method and equipment for automatically identifying commodities in image set |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
| CN106097072A (en) * | 2016-06-17 | 2016-11-09 | 北京京东尚科信息技术有限公司 | The control methods of a kind of merchandise news, device and terminal unit |
| CN108230308A (en) * | 2017-12-29 | 2018-06-29 | 武汉璞华大数据技术有限公司 | A kind of handbill proofreading method, device and equipment |
| CN109978072A (en) * | 2019-04-03 | 2019-07-05 | 青岛伴星智能科技有限公司 | A kind of character comparison method and Compare System based on deep learning |
| US20190279144A1 (en) * | 2018-03-08 | 2019-09-12 | Shanghai Clobotics Technology Co., Ltd. | Method, system and device for association of commodities and price tags |
| CN110263697A (en) * | 2019-06-17 | 2019-09-20 | 哈尔滨工业大学（深圳） | Pedestrian based on unsupervised learning recognition methods, device and medium again |
-
2019
- 2019-11-26 CN CN201911171153.1A patent/CN111144438A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105373938A (en) * | 2014-08-27 | 2016-03-02 | 阿里巴巴集团控股有限公司 | Method for identifying commodity in video image and displaying information, device and system |
| CN106097072A (en) * | 2016-06-17 | 2016-11-09 | 北京京东尚科信息技术有限公司 | The control methods of a kind of merchandise news, device and terminal unit |
| CN108230308A (en) * | 2017-12-29 | 2018-06-29 | 武汉璞华大数据技术有限公司 | A kind of handbill proofreading method, device and equipment |
| US20190279144A1 (en) * | 2018-03-08 | 2019-09-12 | Shanghai Clobotics Technology Co., Ltd. | Method, system and device for association of commodities and price tags |
| CN109978072A (en) * | 2019-04-03 | 2019-07-05 | 青岛伴星智能科技有限公司 | A kind of character comparison method and Compare System based on deep learning |
| CN110263697A (en) * | 2019-06-17 | 2019-09-20 | 哈尔滨工业大学（深圳） | Pedestrian based on unsupervised learning recognition methods, device and medium again |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113065447A (en) * | 2021-03-29 | 2021-07-02 | 南京掌控网络科技有限公司 | Method and equipment for automatically identifying commodities in image set |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10817749B2 (en) | Dynamically identifying object attributes via image analysis | |
| US11335092B2 (en) | Item identification method, system and electronic device | |
| US10133921B2 (en) | Methods and apparatus for capturing, processing, training, and detecting patterns using pattern recognition classifiers | |
| JP6719457B2 (en) | Method and system for extracting main subject of image | |
| CN105426356B (en) | A kind of target information recognition methods and device | |
| CN110956225B (en) | Contraband detection method and system, computing device and storage medium | |
| JP6366024B2 (en) | Method and apparatus for extracting text from an imaged document | |
| KR20190063839A (en) | Method and System for Machine Vision based Quality Inspection using Deep Learning in Manufacturing Process | |
| US8244044B2 (en) | Feature selection and extraction | |
| US9489566B2 (en) | Image recognition apparatus and image recognition method for identifying object | |
| CN110348439B (en) | Method, computer readable medium and system for automatically identifying price tags | |
| CN109711508B (en) | Image processing method and device | |
| CN110807110B (en) | Image searching method and device combining local and global features and electronic equipment | |
| US11354549B2 (en) | Method and system for region proposal based object recognition for estimating planogram compliance | |
| CN113643260A (en) | Method, apparatus, device, medium and product for detecting image quality | |
| Gothai et al. | Design features of grocery product recognition using deep learning | |
| Saqlain et al. | Hybrid Approach for Shelf Monitoring and Planogram Compliance (Hyb‐SMPC) in Retails Using Deep Learning and Computer Vision | |
| US20240193995A1 (en) | Non-transitory computer-readable recording medium, information processing method, and information processing apparatus | |
| CN111144438A (en) | Method and device for detecting commodities in advertisement bill | |
| Feng et al. | Image shadow detection and removal based on region matching of intelligent computing | |
| CN117275011A (en) | Commodity identification and commodity price tag matching method, system, terminal and medium | |
| US20210166028A1 (en) | Automated product recognition, analysis and management | |
| JP2023156991A (en) | information processing system | |
| US20220414379A1 (en) | Hand detection trigger for item identification | |
| US20220414900A1 (en) | Item identification using multiple cameras |
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 |