CN109034067B - Method, system, equipment and storage medium for commodity image reproduction detection - Google Patents
Method, system, equipment and storage medium for commodity image reproduction detection Download PDFInfo
- Publication number
- CN109034067B CN109034067B CN201810844896.XA CN201810844896A CN109034067B CN 109034067 B CN109034067 B CN 109034067B CN 201810844896 A CN201810844896 A CN 201810844896A CN 109034067 B CN109034067 B CN 109034067B
- Authority
- CN
- China
- Prior art keywords
- image
- commodity
- target
- detected
- region
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
Abstract
The invention provides a method, a system, equipment and a storage medium for detecting reproduction of commodity images, which comprises the following steps: collecting a plurality of images, and detecting each image to identify a plurality of commodity areas on each image and a commodity category number corresponding to each commodity area; generating at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity area on each image; generating a feature database according to the distinguishing features corresponding to each image; detecting an image to be detected, identifying a plurality of target commodity areas and commodity category numbers corresponding to each target commodity area on the image to be detected, and generating target characteristics of the image to be detected according to the commodity category numbers corresponding to the target commodity areas; and comparing the target distinguishing features with the distinguishing features in the feature database to judge whether the image to be detected is a reproduction image. The invention can realize effective detection of the image to be detected.
Description
Technical Field
The invention relates to a commodity image reproduction detection method, a commodity image reproduction detection system, commodity image reproduction detection equipment and a storage medium.
Background
With the rapid development of commercial economy, the improvement of the living standard of people, the establishment of urban brand images and the existence of department stores and convenience stores in gathering areas of people's life.
As suppliers of department stores and convenience stores, for example, coca-cola company, pepa-cola company, proclaim company, etc. have a need to know the placement of the products of the company in department stores and convenience stores. Because the placement positions and the placement quantities of the commodities in department stores and convenience stores directly influence the sales volume of the commodities in the department stores and the convenience stores. At this time, the supplier company generally sends staff to patrol department stores and convenience stores regularly, investigates the commodity placement condition, and photographs the commodity photographing condition to record the placement condition.
However, since different department stores and convenience stores use the same shelf, even the layout of the shelves is the same, so that the arrangement of the goods of the same supplier in different department stores and convenience stores is similar, for example, the arrangement of the cola products of the coca-cola company in different department stores and convenience stores is similar. Under the condition that some employees have inertia, pictures taken by patrolling stores can be copied as pictures of non-patrolling stores, so that great errors exist in records of commodity arrangement conditions in department stores and convenience stores, and the prediction of sales conditions is influenced.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to provide a commodity image copying detection method, a commodity image copying detection system, a commodity image copying detection device and a storage medium.
The commodity image copying detection method provided by the invention comprises the following steps:
step S1: collecting a plurality of images, and detecting each image to identify a plurality of commodity areas on each image and a commodity type number corresponding to each commodity area;
step S2: generating at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity area on each image;
step S3: generating a feature database according to the distinguishing features corresponding to each image;
step S4: detecting an image to be detected, identifying a plurality of target commodity areas and commodity category numbers corresponding to each target commodity area on the image to be detected, and generating target distinguishing characteristics of the image to be detected according to the commodity category numbers corresponding to the target commodity areas;
step S5: and comparing the target distinguishing features with the distinguishing features in the feature database to judge whether the image to be detected is a reproduction image.
Preferably, the method further comprises the following steps:
-when it is determined that the image to be detected is not a reproduction image, supplementing the image to be detected and the corresponding target discriminating characteristic to the characteristic database;
and sending a reproduction reminding message when the image to be detected is judged to be a reproduction image.
Preferably, the step S2 includes the steps of:
step S201: a preset commodity category numbering sequence;
step S202: counting the number of commodity areas corresponding to each commodity category number on each image according to the commodity category number sequence to form a one-dimensional matrix corresponding to each image, wherein the one-dimensional matrix is used as a distinguishing feature corresponding to each image;
the step S4 includes the following steps:
step S401: detecting an image to be detected, and identifying a plurality of target commodity areas on the image to be detected and commodity category numbers corresponding to each target commodity area;
step S402: and counting the number of the commodity areas corresponding to each commodity category number on each image to be detected according to the commodity category number sequence to form a one-dimensional matrix corresponding to each image to be detected as a target distinguishing characteristic corresponding to each image to be detected.
Preferably, the step S5 includes the steps of:
step S501: subtracting each element in the target distinguishing feature from a corresponding element in a distinguishing feature, and then squaring to generate a plurality of first element difference cardinalities;
step S502: adding a plurality of first element difference bases and then squaring to generate a first feature difference base between the target distinguishing feature and a distinguishing feature;
step S503: judging whether the first feature difference cardinality is smaller than a preset first feature difference cardinality threshold, when the feature difference cardinality is smaller than the first feature difference cardinality threshold, judging that the image to be detected corresponding to the target distinguishing feature is a copied image, and when the feature difference cardinality is larger than or equal to the first feature difference cardinality threshold, triggering step S504;
step S504: and repeatedly executing the steps S501 to S503, and when the feature difference base number between the target distinguishing feature and each distinguishing feature in the feature database is greater than or equal to the first feature difference base number threshold, judging that the image to be detected corresponding to the target distinguishing feature is not a copied image.
Preferably, the step S2 includes the steps of:
step S201: expanding the periphery of each commodity area in each image by a preset area to form a first nine-check image, wherein the commodity area is positioned in the center of the first nine-check image;
step S202: judging whether each preset area region in the first nine-grid image has a commodity region or not;
step S203: when a commodity region exists in a preset area region in the first nine-grid image, acquiring a commodity type number of the commodity region, and when a commodity region does not exist in the preset area region, setting the commodity type number corresponding to the preset area region as a constant;
step S204: sequentially counting the commodity category numbers corresponding to each preset area region in the first nine-grid image according to a preset counting sequence to form a one-dimensional matrix corresponding to each commodity region, wherein the one-dimensional matrix is used as a distinguishing feature corresponding to each commodity region;
step S205: the steps S201 to S204 are repeated in sequence to generate a plurality of distinguishing features for each image.
Preferably, the step S4 includes the steps of:
step S401: expanding the periphery of each target commodity area in each image to be detected by a preset area to form a second nine-check image, wherein the target commodity area is positioned in the center of the second nine-check image;
step S402: judging whether a target commodity region exists in each preset area region corresponding to each target commodity region in the second nine-grid image;
step S403: when a target commodity region exists in a preset area region in the second nine-check image, acquiring a commodity category number of the target commodity region, and when a target commodity region does not exist in a preset area region in the second nine-check image, setting the commodity category number corresponding to the preset area region as a constant;
step S404: according to the statistical sequence, sequentially counting the commodity category numbers corresponding to each preset area region in the second nine-grid image to form a one-dimensional matrix corresponding to each target commodity region, and taking the one-dimensional matrix as a target distinguishing feature corresponding to each target commodity region;
step S405: and repeating the steps S401 to S404 to generate a plurality of target distinguishing characteristics of each image to be detected.
Preferably, the step S5 includes the steps of:
step S501: comparing the to-be-detected commodity image with each image in the characteristic database, judging whether the to-be-detected commodity image is a reproduction image or not when the commodity category number corresponding to a target commodity area in the to-be-detected commodity image cannot be inquired in the commodity category number corresponding to each image in the characteristic database, and otherwise triggering the step S502;
step S502: judging whether each element in the target distinguishing feature corresponding to a target commodity region in the commodity image to be detected is the same as each corresponding element in the distinguishing feature corresponding to the commodity region with the same commodity category number in the image;
step S503: when each element in the target distinguishing feature is the same as each corresponding element in the distinguishing feature corresponding to the commodity region with the same commodity category number in an image, judging that the target commodity region is the same as the commodity region with the same commodity category number in the image, and otherwise, judging that the target commodity region is different from the commodity region with the same commodity category number in the image;
step S504: and repeating the step S502 to the step S503, when the ratio of the number of the target commodity areas in the to-be-detected commodity image, which are the same as the commodity area of one image, to the total number of the target commodity areas in the to-be-detected commodity image is greater than a preset proportional threshold, judging that the to-be-detected commodity image is a copied image, and otherwise, judging that the to-be-detected commodity image is not the copied image.
The commodity image copying detection system provided by the invention is used for realizing the commodity image copying detection method, and comprises the following steps:
the commodity area identification module is used for acquiring a plurality of images and detecting each image so as to identify a plurality of commodity areas on each image and a commodity category number corresponding to each commodity area;
the distinguishing feature generation module is used for generating at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity area on each image;
the characteristic database generating module is used for generating a characteristic database according to the distinguishing characteristic corresponding to each image;
the target distinguishing feature generation module is used for detecting an image to be detected, identifying a plurality of target commodity areas and commodity category numbers corresponding to each target commodity area on the image to be detected, and generating the target distinguishing features of the image to be detected according to the commodity category numbers corresponding to the target commodity areas;
and the characteristic comparison module is used for comparing the target distinguishing characteristics with the distinguishing characteristics in the characteristic database and judging whether the image to be detected is a reproduced image.
The invention provides a commodity image reproduction detection device, which comprises:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to perform the steps of the merchandise image duplication detection method via execution of the executable instructions.
According to the present invention, there is provided a computer-readable storage medium storing a program which, when executed, implements the steps of the article image duplication detection method.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, a plurality of images are collected, the commodity area on each image is numbered according to the preset commodity category to generate the distinguishing characteristics, the distinguishing characteristics corresponding to each image are summarized to generate a characteristic database, and the target distinguishing characteristics generated according to the image to be detected are input into the characteristic database to be inquired and compared to judge whether the image is a copied image, so that the image to be detected is effectively detected, and the shot picture of a shop traveler is effectively supervised;
according to the method and the device, when the image to be detected is judged not to be the reproduction image, the target distinguishing characteristics of the image to be detected are supplemented into the characteristic database, so that the characteristic database is effectively updated in real time, and the accuracy of detection on the image to be detected is improved.
Drawings
Other features, objects and advantages of the invention will become more apparent upon reading of the detailed description of non-limiting embodiments with reference to the following drawings:
FIG. 1 is a flowchart illustrating steps of a method for detecting reproduction of a commodity image according to the present invention;
FIG. 2 is a flow chart of the steps of discriminating characteristic generation in the present invention;
FIG. 3 is a flowchart of the steps of target discriminating characteristic generation in the present invention;
FIG. 4 is a flowchart illustrating the steps of determining reproduction of an image to be detected according to the present invention;
FIG. 5 is a flowchart of the steps for distinguishing feature generation in accordance with a variation of the present invention;
FIG. 6 is a flowchart of the steps of target discriminating characteristic generation in the variation of the present invention;
FIG. 7 is a flowchart illustrating the steps of determining the reproduction of an image to be detected according to the variation of the present invention;
FIG. 8 is a diagram of a first nine-grid image according to a variation of the present invention;
FIG. 9 is a schematic diagram of a commercial product image duplication detection system according to the present invention;
FIG. 10 is a schematic structural diagram of a merchandise image duplication detection device according to the present invention; and
fig. 11 is a schematic structural diagram of a computer-readable storage medium according to the present invention.
Detailed Description
The present invention will be described in detail with reference to specific examples. The following examples will assist those skilled in the art in further understanding the invention, but are not intended to limit the invention in any way. It should be noted that variations and modifications can be made by persons skilled in the art without departing from the spirit of the invention. All falling within the scope of the present invention.
Fig. 1 is a flowchart of steps of a method for detecting reproduction of a commodity image according to the present invention, and as shown in fig. 1, the method for detecting reproduction of a commodity image according to the present invention includes the following steps:
step S1: collecting a plurality of images, and detecting each image to identify a plurality of commodity areas on each image and a commodity type number corresponding to each commodity area;
step S2: generating at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity area on each image;
step S3: generating a feature database according to the distinguishing features corresponding to each image in the plurality of images;
step S4: detecting an image to be detected, identifying a plurality of target commodity areas and commodity category numbers corresponding to each target commodity area on the image to be detected, and generating target distinguishing characteristics of the image to be detected according to the commodity category numbers corresponding to the target commodity areas;
step S5: and comparing the target distinguishing features with the distinguishing features in the feature database to judge whether the image to be detected is a reproduction image.
In this embodiment, the distinguishing features corresponding to each image may be selected to be collected to generate a feature database, or one distinguishing feature or a plurality of distinguishing features corresponding to each image may be associated to form the feature database.
In this embodiment, the image may be a shelf image shot in a shopping mall or a refrigerator image shot. The commodity area is an area corresponding to a certain commodity on the image, and can be an area of a cola bottle on the image or an area of food package.
In this embodiment, the item category number is a number set according to a SKU (Stock Keeping Unit) of the item.
In this embodiment, each commodity area on the image and the SKU corresponding to the commodity area are identified by a pre-trained neural network model, and the commodity category number corresponding to the commodity area is determined according to the relationship between the SKU and the commodity category number.
According to the invention, a plurality of images are collected, the commodity area on each image is generated with the distinguishing characteristics according to the commodity category number, the distinguishing characteristics corresponding to each image are summarized to generate a characteristic database, and the target distinguishing characteristics generated according to the image to be detected are input into the characteristic database to be inquired and compared to judge whether the image is a copied image, so that the effective detection of the image to be detected is realized, and the effective supervision of the shot photo of the shop patrol officer is realized.
The invention provides a commodity image reproduction detection method, which further comprises the following steps:
-when it is determined that the image to be detected is not a reproduction image, supplementing the image to be detected and the corresponding target discriminating characteristic to the characteristic database;
and sending a reproduction reminding message when the image to be detected is judged to be a reproduction image.
Fig. 2 is a flowchart of the step of generating the distinctive feature in the present invention, as shown in fig. 2, in the present invention, the step S2 includes the following steps:
step S201: a preset commodity category numbering sequence;
step S202: counting the number of commodity areas corresponding to each commodity category number on each image according to the commodity category number sequence to form a one-dimensional matrix corresponding to each image, wherein the one-dimensional matrix is used as a distinguishing feature corresponding to each image;
in this embodiment, the order of the product category numbers may be arranged in an ascending order according to the product category numbers, where the number of the product category numbers forms a dimension of the one-dimensional matrix, for example, when the number of the product category numbers is 100, the one-dimensional matrix is 100, and when a product area corresponding to a certain product category number is not intended on the product image, an element corresponding to the product category number in the one-dimensional matrix is 0.
Fig. 3 is a flowchart of the steps of generating the target distinguishing characteristics in the present invention, and as shown in fig. 3, the step S4 in the present invention includes the following steps:
step S401: detecting an image to be detected, and identifying a plurality of target commodity areas on the image to be detected and commodity category numbers corresponding to each target commodity area;
step S402: and counting the number of the commodity areas corresponding to each commodity category number on each image to be detected according to the commodity category number sequence to form a one-dimensional matrix corresponding to each image to be detected as a target distinguishing characteristic corresponding to each image to be detected.
Fig. 4 is a flowchart of the steps of determining the reproduction of the image to be detected in the present invention, and as shown in fig. 4, the step S5 includes the following steps:
step S501: subtracting each element in the target distinguishing features from a corresponding element in one distinguishing feature in the feature database, and then squaring to generate a plurality of first element difference cardinalities;
step S502: adding a plurality of first element difference bases and then squaring to generate a first feature difference base between the target distinguishing feature and a distinguishing feature in the feature database;
step S503: judging whether the first feature difference cardinality is smaller than a preset first feature difference cardinality threshold, when the feature difference cardinality is smaller than the first feature difference cardinality threshold, judging that the image to be detected corresponding to the target distinguishing feature is a copied image, and when the feature difference cardinality is larger than or equal to the first feature difference cardinality threshold, triggering step S504;
step S504: and repeatedly executing the steps S501 to S503, and when the feature difference base number between the target distinguishing feature and each distinguishing feature in the feature database is greater than or equal to the first feature difference base number threshold, judging that the image to be detected corresponding to the target distinguishing feature is not a copied image.
In the present embodiment, let the distinguishing feature be [ M ]1,M2,M3,M4,M5]The target distinguishing characteristic is [ N ]1,N2,N3,N4,N5]Then the feature difference radix F is
In this embodiment, the first feature difference cardinality threshold may be set to 1 or 2.
Fig. 5 is a flowchart of the step of generating the distinguishing feature in the modification of the present invention, and as shown in fig. 5, the step S2 includes the steps of:
step S201: expanding the periphery of each commodity area in each image by a preset area to form a first nine-check image, wherein the commodity area is positioned in the center of the first nine-check image;
step S202: judging whether each preset area region in the first nine-grid image has a commodity region or not;
step S203: when a commodity region exists in a preset area region in the first nine-grid image, acquiring a commodity type number of the commodity region, and when a commodity region does not exist in the preset area region, setting the commodity type number corresponding to the preset area region as a constant;
step S204: sequentially counting the commodity category numbers corresponding to each preset area region in the first nine-grid image according to a preset counting sequence to form a one-dimensional matrix corresponding to each commodity region, wherein the one-dimensional matrix is used as a distinguishing feature corresponding to each commodity region;
step S205: the steps S201 to S204 are repeated in sequence to generate a plurality of distinguishing features for each image.
Fig. 8 is a schematic diagram of a first nine-check image according to a modification of the present invention, and as shown in fig. 8, the preset area is the same as the area of the commodity region, that is, 8 copies of the commodity region are enclosed around the commodity region to form the first nine-check image.
In this modification, it is determined whether the center point of the identified product region falls within a predetermined area region according to the product region identified in step S1, and if the center point of the identified product region falls within the predetermined area region, it is determined that a product region exists in the predetermined area region, and the product type number corresponding to the predetermined area may be extracted.
In this embodiment, the preset statistical order is from left to right, and the identification is performed sequentially from top to bottom. For example, a target discriminating characteristic can be formed as [ A ]1,A2,A3,A4,A5,A6,A7,A8]. In this embodiment, when there is no target commodity region in the predetermined area region, the commodity type number corresponding to the predetermined area region is set to be 0. Such as A6If there is no image area, setting A6＝0。
Fig. 6 is a flowchart of the step of generating the target distinguishing characteristic in the modification of the present invention, and as shown in fig. 6, the step S4 includes the following steps:
step S401: expanding the periphery of each target commodity area in each image to be detected by a preset area to form a second nine-check image, wherein the target commodity area is positioned in the center of the second nine-check image;
step S402: judging whether a target commodity region exists in each preset area region corresponding to each target commodity region in the second nine-grid image;
step S403: when a target commodity region exists in a preset area region in the second nine-check image, acquiring a commodity category number of the target commodity region, and when a target commodity region does not exist in a preset area region in the second nine-check image, setting the commodity category number corresponding to the preset area region as a constant;
step S404: according to the statistical sequence, sequentially counting the commodity category numbers corresponding to each preset area region in the second nine-grid image to form a one-dimensional matrix corresponding to each target commodity region, and taking the one-dimensional matrix as a target distinguishing feature corresponding to each target commodity region;
step S405: and repeating the steps S401 to S404 to generate a plurality of target distinguishing characteristics of each image to be detected.
In this modification, the formed target discriminating characteristic may be represented as [ B ]1,B2,B3,B4,B5,B6,B7,B8]. When the number of the images to be detected is 10, 10 target distinguishing features can be formed. In this embodiment, when there is no target commodity region in the predetermined area region, the commodity type number corresponding to the predetermined area region is set to be 0. Such as B6If there is no image area, setting the command B6＝0。
Fig. 7 is a flowchart of the steps of determining the duplication of the image to be detected in the modification of the present invention, and as shown in fig. 7, the step S5 includes the following steps:
step S501: comparing the to-be-detected commodity image with each image in the characteristic database, judging whether the to-be-detected commodity image is a reproduction image or not when the commodity category number corresponding to a target commodity area in the to-be-detected commodity image cannot be inquired in the commodity category number corresponding to each image in the characteristic database, and otherwise triggering the step S502;
step S502: judging whether each element in the target distinguishing feature corresponding to a target commodity region in the commodity image to be detected is the same as each corresponding element in the distinguishing feature corresponding to the commodity region with the same commodity category number in the image;
step S503: when each element in the target distinguishing feature is the same as each corresponding element in the distinguishing feature corresponding to the commodity region with the same commodity category number in an image, judging that the target commodity region is the same as the commodity region with the same commodity category number in the image, and otherwise, judging that the target commodity region is different from the commodity region with the same commodity category number in the image;
step S504: and repeating the step S502 to the step S503, when the ratio of the number of the target commodity areas in the to-be-detected commodity image, which are the same as the commodity area of one image, to the total number of the target commodity areas in the to-be-detected commodity image is greater than a preset proportional threshold, judging that the to-be-detected commodity image is a copied image, and otherwise, judging that the to-be-detected commodity image is not the copied image.
In this modification, when the image of the to-be-detected commodity has a commodity category number corresponding to a commodity region and cannot be searched in the image in the feature database, it may be directly determined that the image of the to-be-detected commodity is not a reproduction image. The detection from step S502 to step S503 is performed only when the image of the article to be detected has an article category number corresponding to an article area that can be found on an image.
In this modification, each element in the target distinguishing feature is identical to each corresponding element in the corresponding distinguishing feature of the commodity region having the same commodity category number in one image
In this modification, the preset proportional threshold is 90%, and if the total number of the target commodity areas in the commodity image to be detected is 50 and the number of the target commodity areas in the commodity image to be detected, which is the same as the number of the commodity areas in one image, is 48, the image is determined to be a copied image.
Fig. 9 is a schematic block diagram of a product image duplication detection system according to the present invention, configured to implement the product image duplication detection method, as shown in fig. 9, the product image duplication detection system 100 according to the present invention includes:
the commodity area identification module 101 is configured to collect a plurality of images, and detect each image to identify a plurality of commodity areas on each image and a commodity category number corresponding to each commodity area;
a distinguishing feature generation module 102, configured to generate at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity region on each image;
the feature database generation module 103 is configured to generate a feature database according to the distinguishing feature corresponding to each image in the multiple images;
a target distinguishing feature generation module 104, configured to detect an image to be detected, identify a plurality of target commodity areas and a commodity category number corresponding to each target commodity area on the image to be detected, and generate a target distinguishing feature of the image to be detected according to the commodity category number corresponding to the target commodity area;
and the feature comparison module 105 is configured to compare the target distinguishing features with the distinguishing features in the feature database, and determine whether the image to be detected is a copied image.
The embodiment of the invention also provides commodity image copying detection equipment which comprises a processor. A memory having stored therein executable instructions of the processor. Wherein the processor is configured to perform the steps of the article image duplication detection method via execution of the executable instructions.
As described above, in this embodiment, a plurality of images are collected, the distinguishing features are generated for the commodity region on each image according to the commodity category number, the distinguishing features corresponding to each image are summarized to generate a feature database, and the target distinguishing features generated according to the image to be detected are input into the feature database to be queried and compared to determine whether the image is a copied image, so that effective detection of the image to be detected is realized, and effective supervision of a picture taken by a shop clerk is realized.
As will be appreciated by one skilled in the art, aspects of the present invention may be embodied as a system, method or program product. Thus, various aspects of the invention may be embodied in the form of: an entirely hardware embodiment, an entirely software embodiment (including firmware, microcode, etc.) or an embodiment combining hardware and software aspects that may all generally be referred to herein as a "circuit," module "or" platform.
Fig. 10 is a schematic structural diagram of the commodity image duplication detection apparatus of the present invention. An electronic device 600 according to this embodiment of the invention is described below with reference to fig. 10. The electronic device 600 shown in fig. 10 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. 10, the electronic device 600 is embodied in the form of a general purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one memory unit 620, a bus 630 connecting the different platform components (including the memory unit 620 and the processing unit 610), a display unit 640, etc.
Wherein the storage unit stores program code executable by the processing unit 610 to cause the processing unit 610 to perform steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of the present specification. For example, processing unit 610 may perform the steps as shown in fig. 1.
The storage unit 620 may include readable media in the form of volatile memory units, such as a random access memory unit (RAM)6201 and/or a cache memory unit 6202, and may further include a read-only memory unit (ROM) 6203.
The memory unit 620 may also include a program/utility 6204 having a set (at least one) of program modules 6205, such program modules 6205 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 600 may also communicate with one or more external devices 700 (e.g., keyboard, pointing device, bluetooth device, etc.), with one or more devices that enable a user to interact with the electronic device 600, and/or with any devices (e.g., router, modem, etc.) that enable the electronic device 600 to communicate with one or more other computing devices. Such communication may occur via an input/output (I/O) interface 650. Also, the electronic device 600 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 660. The network adapter 660 may communicate with other modules of the electronic device 600 via the bus 630. It should be appreciated that although not shown in FIG. 10, other hardware and/or software modules may be used in conjunction with electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage platforms, to name a few.
The embodiment of the invention also provides a computer readable storage medium for storing a program, and the steps of the commodity image duplication detection method are realized when the program is executed. In some possible embodiments, the aspects of the present invention may also be implemented in the form of a program product comprising program code for causing a terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above-mentioned electronic prescription flow processing method section of this specification, when the program product is run on the terminal device.
As shown above, when the program of the computer-readable storage medium of this embodiment is executed, the multiple images are collected, the distinguishing features are generated for the commodity region on each image according to the commodity category number, the distinguishing features corresponding to each image are summarized to generate a feature database, and the target distinguishing features generated according to the image to be detected are input into the feature database to be queried and compared to determine whether the image is a copied image, so that effective detection of the image to be detected is realized, and effective supervision of a shot photo of a clerk is realized.
Fig. 11 is a schematic structural diagram of a computer-readable storage medium of the present invention. Referring to fig. 11, a program product 800 for implementing the above method according to an embodiment of the present invention is described, which may employ a portable compact disc read only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited in this regard and, in the present document, a readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The program product may employ any combination of one or more readable media. The 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.
A 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).
According to the invention, a plurality of images are collected, the commodity area on each image is generated with distinguishing characteristics according to the commodity category number, the distinguishing characteristics corresponding to each image are summarized to generate a characteristic database, and the target distinguishing characteristics generated according to the image to be detected are input into the characteristic database to be inquired and compared to judge whether the image is a copied image, so that the effective detection of the image to be detected is realized, and the effective supervision of the shot photo of the shop patrol officer is realized;
according to the method and the device, when the image to be detected is judged not to be the reproduction image, the target distinguishing characteristics of the image to be detected are supplemented into the characteristic database, so that the characteristic database is effectively updated in real time, and the accuracy of detection on the image to be detected is improved.
The foregoing description of specific embodiments of the present invention has been presented. It is to be understood that the present invention is not limited to the specific embodiments described above, and that various changes and modifications may be made by one skilled in the art within the scope of the appended claims without departing from the spirit of the invention.
Claims (9)
1. A commodity image reproduction detection method is characterized by comprising the following steps:
step S1: collecting a plurality of images, and detecting each image to identify a plurality of commodity areas on each image and a commodity type number corresponding to each commodity area;
step S2: generating at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity area on each image;
step S3: generating a feature database according to the distinguishing features corresponding to each image;
step S4: detecting an image to be detected, identifying a plurality of target commodity areas and commodity category numbers corresponding to each target commodity area on the image to be detected, and generating target distinguishing characteristics of the image to be detected according to the commodity category numbers corresponding to the target commodity areas;
step S5: comparing the target distinguishing features with the distinguishing features in the feature database, and judging whether the image to be detected is a reproduction image;
the step S2 includes the following steps:
step S201: expanding the periphery of each commodity area in each image by a preset area to form a first nine-check image, wherein the commodity area is positioned in the center of the first nine-check image;
step S202: judging whether each preset area region in the first nine-grid image has a commodity region or not;
step S203: when a commodity region exists in a preset area region in the first nine-grid image, acquiring a commodity type number of the commodity region, and when a commodity region does not exist in the preset area region, setting the commodity type number corresponding to the preset area region as a constant;
step S204: sequentially counting the commodity category numbers corresponding to each preset area region in the first nine-grid image according to a preset counting sequence to form a one-dimensional matrix corresponding to each commodity region, wherein the one-dimensional matrix is used as a distinguishing feature corresponding to each commodity region;
step S205: the steps S201 to S204 are repeated in sequence to generate a plurality of distinguishing features for each image.
2. The commodity image reproduction detection method according to claim 1, further comprising the steps of:
-when it is determined that the image to be detected is not a reproduction image, supplementing the image to be detected and the corresponding target discriminating characteristic to the characteristic database;
and sending a reproduction reminding message when the image to be detected is judged to be a reproduction image.
3. The merchandise image reproduction detection method according to claim 1, wherein the step S2 includes the steps of:
step S201: a preset commodity category numbering sequence;
step S202: counting the number of commodity areas corresponding to each commodity category number on each image according to the commodity category number sequence to form a one-dimensional matrix corresponding to each image, wherein the one-dimensional matrix is used as a distinguishing feature corresponding to each image;
the step S4 includes the following steps:
step S401: detecting an image to be detected, and identifying a plurality of target commodity areas on the image to be detected and commodity category numbers corresponding to each target commodity area;
step S402: and counting the number of the commodity areas corresponding to each commodity category number on each image to be detected according to the commodity category number sequence to form a one-dimensional matrix corresponding to each image to be detected as a target distinguishing characteristic corresponding to each image to be detected.
4. The merchandise image reproduction detection method according to claim 3, wherein the step S5 includes the steps of:
step S501: subtracting each element in the target distinguishing feature from a corresponding element in a distinguishing feature, and then squaring to generate a plurality of first element difference cardinalities;
step S502: adding a plurality of first element difference bases and then squaring to generate a first feature difference base between the target distinguishing feature and a distinguishing feature;
step S503: judging whether the first feature difference cardinality is smaller than a preset first feature difference cardinality threshold, when the feature difference cardinality is smaller than the first feature difference cardinality threshold, judging that the image to be detected corresponding to the target distinguishing feature is a copied image, and when the feature difference cardinality is larger than or equal to the first feature difference cardinality threshold, triggering step S504;
step S504: and repeatedly executing the steps S501 to S503, and when the feature difference base number between the target distinguishing feature and each distinguishing feature in the feature database is greater than or equal to the first feature difference base number threshold, judging that the image to be detected corresponding to the target distinguishing feature is not a copied image.
5. The merchandise image reproduction detection method according to claim 1, wherein the step S4 includes the steps of:
step S401: expanding the periphery of each target commodity area in each image to be detected by a preset area to form a second nine-check image, wherein the target commodity area is positioned in the center of the second nine-check image;
step S402: judging whether a target commodity region exists in each preset area region corresponding to each target commodity region in the second nine-grid image;
step S403: when a target commodity region exists in a preset area region in the second nine-check image, acquiring a commodity category number of the target commodity region, and when a target commodity region does not exist in a preset area region in the second nine-check image, setting the commodity category number corresponding to the preset area region as a constant;
step S404: according to the statistical sequence, sequentially counting the commodity category numbers corresponding to each preset area region in the second nine-grid image to form a one-dimensional matrix corresponding to each target commodity region, and taking the one-dimensional matrix as a target distinguishing feature corresponding to each target commodity region;
step S405: and repeating the steps S401 to S404 to generate a plurality of target distinguishing characteristics of each image to be detected.
6. The merchandise image reproduction detection method according to claim 1, wherein the step S5 includes the steps of:
step S501: comparing the to-be-detected commodity image with each image in the characteristic database, judging whether the to-be-detected commodity image is a reproduction image or not when the commodity category number corresponding to a target commodity area in the to-be-detected commodity image cannot be inquired in the commodity category number corresponding to each image in the characteristic database, and otherwise triggering the step S502;
step S502: judging whether each element in the target distinguishing feature corresponding to a target commodity region in the commodity image to be detected is the same as each corresponding element in the distinguishing feature corresponding to the commodity region with the same commodity category number in the image;
step S503: when each element in the target distinguishing feature is the same as each corresponding element in the distinguishing feature corresponding to the commodity region with the same commodity category number in an image, judging that the target commodity region is the same as the commodity region with the same commodity category number in the image, and otherwise, judging that the target commodity region is different from the commodity region with the same commodity category number in the image;
step S504: and repeating the step S502 to the step S503, when the ratio of the number of the target commodity areas in the to-be-detected commodity image, which are the same as the commodity area of one image, to the total number of the target commodity areas in the to-be-detected commodity image is greater than a preset proportional threshold, judging that the to-be-detected commodity image is a copied image, and otherwise, judging that the to-be-detected commodity image is not the copied image.
7. A commodity image duplication detection system for implementing the commodity image duplication detection method according to any one of claims 1 to 6, comprising:
the commodity area identification module is used for acquiring a plurality of images and detecting each image so as to identify a plurality of commodity areas on each image and a commodity category number corresponding to each commodity area;
the distinguishing feature generation module is used for generating at least one distinguishing feature corresponding to each image according to the commodity category number corresponding to each commodity area on each image;
the characteristic database generating module is used for generating a characteristic database according to the distinguishing characteristic corresponding to each image;
the target distinguishing feature generation module is used for detecting an image to be detected, identifying a plurality of target commodity areas and commodity category numbers corresponding to each target commodity area on the image to be detected, and generating the target distinguishing features of the image to be detected according to the commodity category numbers corresponding to the target commodity areas;
and the characteristic comparison module is used for comparing the target distinguishing characteristics with the distinguishing characteristics in the characteristic database and judging whether the image to be detected is a reproduced image.
8. A commodity image reproduction detection apparatus, comprising:
a processor;
a memory having stored therein executable instructions of the processor;
wherein the processor is configured to execute the steps of the merchandise image duplication detection method according to any one of claims 1 to 6 via execution of the executable instructions.
9. A computer-readable storage medium storing a program, wherein the program is executed to implement the steps of the article image duplication detection method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810844896.XA CN109034067B (en) | 2018-07-27 | 2018-07-27 | Method, system, equipment and storage medium for commodity image reproduction detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810844896.XA CN109034067B (en) | 2018-07-27 | 2018-07-27 | Method, system, equipment and storage medium for commodity image reproduction detection |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109034067A CN109034067A (en) | 2018-12-18 |
| CN109034067B true CN109034067B (en) | 2021-08-24 |
Family
ID=64646348
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810844896.XA Active CN109034067B (en) | 2018-07-27 | 2018-07-27 | Method, system, equipment and storage medium for commodity image reproduction detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109034067B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117576425B (en) * | 2024-01-17 | 2024-04-16 | 南京掌控网络科技有限公司 | Method and system for detecting scurrying image |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521614A (en) * | 2011-12-20 | 2012-06-27 | 中山大学 | Identification method of coping digital image |
| CN102592276A (en) * | 2011-12-20 | 2012-07-18 | 中山大学 | Image area description method and copy image detection method based on same |
| CN102930264A (en) * | 2012-09-29 | 2013-02-13 | 李炳华 | System and method for acquiring and analyzing commodity display information based on image identification technology |
| EP3182349A2 (en) * | 2015-12-18 | 2017-06-21 | Ricoh Company, Ltd. | Planogram matching |
-
2018
- 2018-07-27 CN CN201810844896.XA patent/CN109034067B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102521614A (en) * | 2011-12-20 | 2012-06-27 | 中山大学 | Identification method of coping digital image |
| CN102592276A (en) * | 2011-12-20 | 2012-07-18 | 中山大学 | Image area description method and copy image detection method based on same |
| CN102930264A (en) * | 2012-09-29 | 2013-02-13 | 李炳华 | System and method for acquiring and analyzing commodity display information based on image identification technology |
| EP3182349A2 (en) * | 2015-12-18 | 2017-06-21 | Ricoh Company, Ltd. | Planogram matching |
Non-Patent Citations (2)
| Title |
|---|
| Effective and Efficient Global Context Verification for Image Copy Detection;Zhili Zhou 等;《IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY》;20160817;第48-63页 * |
| 基于同态补偿翻拍图像的方向预测方法;谢哲 等;《计算机应用》;20140910;第34卷(第9期);第2687-2690页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109034067A (en) | 2018-12-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108416403B (en) | Method, system, equipment and storage medium for automatically associating commodity with label | |
| KR102543508B1 (en) | Automated object tracking in a video feed using machine learning | |
| US9720936B2 (en) | Biometric matching engine | |
| US20170200205A1 (en) | Method and system for analyzing user reviews | |
| CN102572390B (en) | Apparatus and method for monitoring motion of monitored objects | |
| US20180247361A1 (en) | Information processing apparatus, information processing method, wearable terminal, and program | |
| TWI747674B (en) | Computer-implemented system for artificial intelligence-based product categorization and method for categorizing products using artificial intelligence | |
| US9811537B2 (en) | Product identification via image analysis | |
| KR20190093733A (en) | Items recognition system in unmanned store and the method thereof | |
| KR102064244B1 (en) | Method for linking block-chain using hyper-chain, and apparatus therefor | |
| WO2022227764A1 (en) | Event detection method and apparatus, electronic device, and readable storage medium | |
| CN112100425A (en) | Label labeling method and device based on artificial intelligence, electronic equipment and medium | |
| JP6494799B2 (en) | Fixing a facility with images located using geolocation | |
| CN109784172A (en) | Ground heap commodity occupied area evaluation method, system, equipment and medium in market | |
| JPWO2019123714A1 (en) | Information processing equipment, product recommendation methods, and programs | |
| CN109034067B (en) | Method, system, equipment and storage medium for commodity image reproduction detection | |
| WO2021024459A1 (en) | Processing device, accounting device, processing method, and program | |
| JP6565661B2 (en) | Image processing system, image similarity determination method, and image similarity determination program | |
| CN116580390A (en) | Price tag content acquisition method, price tag content acquisition device, storage medium and computer equipment | |
| CN111091416A (en) | Method and device for predicting probability of hotel purchase robot | |
| CN107908724B (en) | Data model matching method, device, equipment and storage medium | |
| JP6857373B1 (en) | Information processing equipment, information processing methods, and programs | |
| WO2022199078A1 (en) | Method and apparatus for generating item dynamic information, device, and computer-readable medium | |
| US20220076015A1 (en) | Fast multi-modal object recognition system | |
| US20230101001A1 (en) | Computer-readable recording medium for information processing program, information processing method, and information processing device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |