CN111340515B - Feature information generation and article tracing method and device - Google Patents
Feature information generation and article tracing method and device Download PDFInfo
- Publication number
- CN111340515B CN111340515B CN202010136593.XA CN202010136593A CN111340515B CN 111340515 B CN111340515 B CN 111340515B CN 202010136593 A CN202010136593 A CN 202010136593A CN 111340515 B CN111340515 B CN 111340515B
- Authority
- CN
- China
- Prior art keywords
- image
- source
- acquiring
- article
- point
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/018—Certifying business or products
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Accounting & Taxation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a characteristic information generation and article tracing method and device, and relates to the technical field of computers. One embodiment of the method comprises the following steps: acquiring an integral image and a local image of a source object; and extracting the characteristics of the whole image and the local image, and fusing the extracted whole characteristics and local characteristics to obtain the source characteristic information of the source object. According to the embodiment, for the source article which is registered for the first time, the picture features are extracted to establish a file 'uplink', and subsequently when the article circulates in the trade market, the features of the extracted position images are compared, so that the aim of tracing the source without changing the original attribute of the article is fulfilled.
Description
Technical Field
The present invention relates to the field of computer technologies, and in particular, to a method and apparatus for generating feature information and tracing an object.
Background
In the trade market, the problem of true and false articles and the problem of tracing sources are very troublesome. The buyer cannot know the specific information of the transaction times, the transaction time points, whether maintenance is performed or not, and the like, so that expert authentication is required during the transaction. Currently, identification is mainly performed by filling an electronic chip or spraying a unique code (ultraviolet irradiation display) in an article.
In carrying out the present invention, the inventors have found that at least the following problems exist in the prior art:
the existing mode can destroy the object, change the original attribute of the object, and the authentication process is complicated. In addition, the anti-counterfeiting modes of different transaction parties are different, so that unified management is difficult in the process of article circulation. Because the transaction parties are stakeholders on the circulation chain, when the information is unfavorable, the information can be tampered, so that the identification accuracy is difficult to guarantee, especially online transaction, and the authenticity is difficult to distinguish and the fish is mixed.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a method and a device for generating characteristic information and tracing an article, which at least can solve the problem that articles in the prior art are damaged to some extent.
To achieve the above object, according to an aspect of an embodiment of the present invention, there is provided a feature information generating method including:
acquiring an integral image and a local image of a source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
and extracting the characteristics of the whole image and the local image, and fusing the extracted whole characteristics and local characteristics to obtain the source characteristic information of the source object.
Optionally, the overall dimension is a plane dimension, and the local dimension includes a part dimension and a point dimension;
the acquiring the whole image and the partial image of the source object comprises the following steps:
acquiring a planar image of the source article based on the planar dimension;
acquiring an image of an area where at least one part is located in the plane image based on the part dimension to obtain a part image;
and acquiring an image of the region of at least one point in the position image based on the point dimension to obtain a point image.
Optionally, the acquiring, based on the point dimension, an image of the region at least one point in the part image to obtain a point image further includes:
acquiring material characteristics of the source object at a single point from the basic information of the source object, and amplifying and acquiring an image of an area where the single point is positioned based on amplification factors corresponding to the material characteristics to obtain an amplified point image; and
recording the magnification when the single point position acquires the point position image.
Optionally, the method further comprises:
determining the position of the point in the position image to obtain point position distribution;
Determining the position of the part in the plane image to obtain part distribution;
and taking the point position distribution and the position distribution as image acquisition positions of the source object.
Optionally, after the obtaining the source characteristic information of the source article, the method further includes: if the source object is registered for the first time, acquiring an identity code of the source object, and establishing a file of the source object by combining the integral image, the local image and the source characteristic information.
Optionally, the establishing the profile of the source article further includes: determining the operation behavior of the source article, and acquiring the operation image information of the source article in the operation behavior; wherein the operational behavior includes at least one of production, transaction, maintenance, component replacement.
Optionally, the establishing the profile of the source article further includes: encrypting the source characteristic information based on an information abstract algorithm to obtain encrypted source characteristic information.
To achieve the above object, according to an aspect of the embodiments of the present invention, there is provided an article tracing method, including:
determining a source object according to the identity code of the object to be traced, and acquiring the image acquisition position and source characteristic information of the source object; the source characteristic information is obtained by carrying out characteristic extraction and fusion on a source image of the source object, and the source image corresponds to the image acquisition position;
Acquiring an image of the object to be traced based on the image acquisition position, and carrying out feature extraction and fusion on the image to obtain feature information of the object to be traced;
and performing feature matching on the feature information and the source feature information, and if the matching result is accordant, determining that the tracing is successful.
Optionally, the image acquisition positions include a location distribution and a point location distribution;
the step of acquiring the image of the article to be traced based on the image acquisition position comprises the following steps:
acquiring a first plane image of the article to be traced based on a plane dimension;
determining the position of the part in the first plane image based on the part distribution, and further acquiring a first part image;
and determining the position of the point in the first position image based on the point position distribution, so as to acquire a first point position image.
Optionally, determining, based on the point location distribution, a location where a point location is located in the first location image, so as to obtain a first point image, and further includes:
and amplifying and acquiring an image positioned at the point position in the first position image based on the amplification factor corresponding to the point position, so as to obtain an amplified first point position image.
To achieve the above object, according to another aspect of the embodiments of the present invention, there is provided a feature information generating apparatus including:
the image acquisition module is used for acquiring an integral image and a local image of the source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
and the source feature extraction module is used for extracting features of the whole image and the local image, and fusing the extracted whole features and local features to obtain source feature information of the source object.
Optionally, the overall dimension is a plane dimension, and the local dimension includes a part dimension and a point dimension;
the image acquisition module is used for:
acquiring a planar image of the source article based on the planar dimension;
acquiring an image of an area where at least one part is located in the plane image based on the part dimension to obtain a part image;
and acquiring an image of the region of at least one point in the position image based on the point dimension to obtain a point image.
Optionally, the image acquisition module is further configured to:
acquiring material characteristics of the source object at a single point from the basic information of the source object, and amplifying and acquiring an image of an area where the single point is positioned based on amplification factors corresponding to the material characteristics to obtain an amplified point image; and
Recording the magnification when the single point position acquires the point position image.
Optionally, the system further comprises a position distribution module for:
determining the position of the point in the position image to obtain point position distribution;
determining the position of the part in the plane image to obtain part distribution;
and taking the point position distribution and the position distribution as image acquisition positions of the source object.
Optionally, the method further comprises a profiling module for: if the source object is registered for the first time, acquiring an identity code of the source object, and establishing a file of the source object by combining the integral image, the local image and the source characteristic information.
Optionally, the profiling module is further configured to: determining the operation behavior of the source article, and acquiring the operation image information of the source article in the operation behavior; wherein the operational behavior includes at least one of production, transaction, maintenance, component replacement.
Optionally, the profiling module is further configured to: encrypting the source characteristic information based on an information abstract algorithm to obtain encrypted source characteristic information.
To achieve the above object, according to an aspect of the embodiments of the present invention, there is provided an article tracing apparatus, including:
The article determining module is used for determining the source article according to the identity code of the article to be traced and acquiring the image acquisition position and the source characteristic information of the source article; the source characteristic information is obtained by carrying out characteristic extraction and fusion on a source image of the source object, and the source image corresponds to the image acquisition position;
the feature extraction module is used for acquiring the image of the object to be traced based on the image acquisition position, and carrying out feature extraction and fusion on the image to obtain feature information of the object to be traced;
and the feature matching module is used for carrying out feature matching on the feature information and the source feature information, and if the matching result is accordant, successful tracing is determined.
Optionally, the image acquisition positions include a location distribution and a point location distribution;
the feature extraction module is used for:
acquiring a first plane image of the article to be traced based on a plane dimension;
determining the position of the part in the first plane image based on the part distribution, and further acquiring a first part image;
and determining the position of the point in the first position image based on the point position distribution, so as to acquire a first point position image.
Optionally, the feature extraction module is further configured to: and amplifying and acquiring an image positioned at the point position in the first position image based on the amplification factor corresponding to the point position, so as to obtain an amplified first point position image.
In order to achieve the above object, according to still another aspect of the embodiment of the present invention, there is provided a feature information generating and article tracing electronic device.
The electronic equipment of the embodiment of the invention comprises: one or more processors; and the storage device is used for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors are enabled to realize the characteristic information generation and article tracing method.
To achieve the above object, according to still another aspect of the embodiments of the present invention, there is provided a computer readable medium having stored thereon a computer program, which when executed by a processor, implements any of the above-described feature information generation and article tracing methods.
According to the solution provided by the present invention, one embodiment of the above invention has the following advantages or beneficial effects: for the first registered article, based on the blockchain anti-counterfeiting tracing technology, a file is established to be "up-chain" so as to store source image information and characteristic information of the article, and then when the article circulates in the trade market again, the image at the same position is shot again, and image characteristic matching is carried out on the article and the source article which is "up-chain", so that the aim of tracing the source without changing the original attribute of the article is fulfilled.
Further effects of the above-described non-conventional alternatives are described below in connection with the embodiments.
Drawings
The drawings are included to provide a better understanding of the invention and are not to be construed as unduly limiting the invention. Wherein:
fig. 1 is a schematic flow chart of a feature information generating method according to an embodiment of the present invention;
FIG. 2 is a flow chart of an alternative feature information generation method according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of an article tracing method according to an embodiment of the invention;
FIG. 4 is a flow chart of a specific method for tracing an object according to an embodiment of the invention;
fig. 5 is a schematic diagram of main blocks of a feature information generating apparatus according to an embodiment of the present invention;
fig. 6 is a schematic diagram of main modules of an article tracing device according to an embodiment of the present invention;
FIG. 7 is an exemplary system architecture diagram in which embodiments of the present invention may be applied;
fig. 8 is a schematic diagram of a computer system suitable for use in implementing an embodiment of the present invention.
Detailed Description
Exemplary embodiments of the present invention will now be described with reference to the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding, and are to be considered merely exemplary. Accordingly, those of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the invention. Also, descriptions of well-known functions and constructions are omitted in the following description for clarity and conciseness.
The article in the present invention refers to a transaction object with a high value/quality relationship ratio, such as a case, clothing, jewelry, 3C electronic product, and the like. Considering that the invention mainly uses image characteristics to perform anti-counterfeiting authentication, while diamonds, porcelain and the like usually use optical characteristics to perform anti-counterfeiting, the invention mainly considers articles such as clothing, case and bag accessories and the like which can be authenticated through images.
For an item, it is often difficult to intuitively derive detailed information thereof. Taking the case as an example, even if the case is printed with a code, a certain step is required to acquire the information. Especially in the second hand trade market, it is important how to trace the source because the user wants to know whether the article has been cured, repaired, changed the accessory, etc. before.
Referring to fig. 1, a main flowchart of a feature information generating method provided by an embodiment of the present invention is shown, including the following steps:
s101: acquiring an integral image and a local image of a source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
s102: and extracting the characteristics of the whole image and the local image, and fusing the extracted whole characteristics and local characteristics to obtain the source characteristic information of the source object.
In the above embodiment, for step S101, the image of the source object is mainly represented in two dimensions, namely, the whole and part, specifically, three dimensions of a plane, a site and a point location. The user or the shooting device shoots the object based on the three dimensions, and image data of the three dimensions are obtained:
firstly, the plane shape of the article is photographed by a plane angle, so that workers can primarily know the brand, style, color and other profile information of the article. The plane here may be six-sided, including front, rear, left, right, top, bottom (and perspective). For planar articles, only front and rear views may be included.
Then, a worker performs selective clicking on a plurality of key parts or parts of the article to perform part shooting, and detail information such as leather textures, printed patterns, accessories and the like is recorded in a key shooting mode. The part image may be regarded as a partial image because only the partial position of the object is imaged with respect to the planar image.
Finally, microscopic equipment such as a microscopic camera is used for amplifying and shooting important key positions (mainly selected points of workers) of the object, and the important key positions generally need to be shot to a micron level so as to observe some characteristics which cannot be seen by naked eyes, such as details of fiber morphology, thickness of a coating and the like, and obtain point position images (or called microscopic images).
Further, the magnification of the point location shooting can be related to the material characteristics of the selected point location, for example, the material characteristics 1-magnification factor 100-300 times and the material characteristics 2-magnification factor 100-2000 times; wherein the material characteristics may be derived from basic information of the article.
It should be noted that, for the selection of the location and the point in the location photographing and the point photographing, the general production depends on the selection of the location and the point by experience of a worker (such as an identification expert), and the number of the plane photographing, the location photographing and the point photographing may be one or more, but the grouping is required according to the plane image. For example, the clothing is selected to take only its main face, forming a set of images at this time; for a more stereoscopic object, if six views are taken, six sets of images are formed.
The image of the article can be recorded along with circulation, and the image information of the article is obtained by taking the image of the article after the article is produced by an article manufacturing factory, taking the image of the article by a seller in the process of transaction circulation or taking the image of the article by a maintenance factory in the process of maintenance, and independently grouping the image information according to the operation process.
The method can shoot the object from three dimensions of a plane, a part and a point location, and can obtain a plurality of images. And the parts shot at the parts/points are marked in the plane image, so that the characteristics of the parts can be conveniently verified during the follow-up tracing of the object. In order to facilitate the comparison of the features of the same subsequent position, the positions of the position and the point in the image are marked, and the subsequent position image and the point image can be directly shot at the positions.
For step S102, a plurality of images generated from capturing an article in three dimensions of a plane, a location, and a point location are used, the images describing features of the article at different scales from the plane to the location, and then to the point location. Therefore, the invention selects to adopt a cascade feature extraction network and fuses the features on the same scale.
In addition, before feature extraction, the image of the object is subjected to data processing so that the data more meets the requirements of a feature extraction network, and therefore more effective source features are extracted.
According to the method provided by the embodiment, on the basis of not changing the object, the object image is shot from the whole dimension and the local dimension, the feature extraction is carried out, and a source feature basis is provided for the tracing of the subsequent object.
Referring to fig. 2, a flowchart of an optional feature information generating method according to an embodiment of the present invention is shown, including the following steps:
s201: acquiring an integral image and a local image of a source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
s102: extracting features of the whole image and the local image, and fusing the extracted whole features and local features to obtain source feature information of the source object;
S203: if the source object is registered for the first time, acquiring an identity code of the source object, and establishing a file of the source object by combining the integral image, the local image and the source characteristic information.
In the above embodiment, for the steps S201 and S202, reference may be made to the descriptions of the steps S101 and S102 shown in fig. 1, and the descriptions are not repeated here.
In the above embodiment, for step S203, for the source item in the database, it is necessary to first maintain its basic information in the system to generate a unique code based on its identity. Further, identity marks, such as two-dimensional codes, bar codes and the like, which are convenient to scan can be generated based on the unique codes, and information can be checked after scanning.
Although the identity code is a unique code of the article, the article is identified only by the identity code, and the accuracy of the result is difficult to ensure. For example, the factory a produces the article B, and the unique number is printed in the article B, but a large number of highly imitated B exist in the market, and the number may be imitated, so that the authenticity of the article to be traced cannot be identified only by the identity code.
The generation of the unique code is generated for the first time the source item is registered in the system/database. Respectively establishing files for each piece of source articles, and uploading data such as factory information (such as production places, batches and the like) and attribute information (such as images of planes, parts and points) of each piece of source articles by using a genuine article tracing system based on a blockchain technology, and generating unique codes; among other things, blockchains guarantee non-tamperable, publicly transparent, and time stamping capabilities in data storage scenarios.
It should be noted that, the article will change during the use, and the data comparison will have differences, so the circulation information (such as time of each sale, maintenance condition, etc.) of the source article can be stored in the file as well, so that the subsequent feature comparison is convenient, besides the factory feature comparison, the circulation feature comparison can be also performed, so as to improve the identification accuracy.
In addition, after the features of the source article are extracted, the features can be encrypted, the corresponding relation between the unique codes and the encrypted features is established, and then the corresponding relation, the unique codes and the encrypted features are stored in a system/database, so that the risk of tampering of the features is prevented.
According to the method provided by the embodiment, for the first registered article, the file is built based on the image information and the source article characteristic information, but for the non-first registered article, the image and the characteristic information in the file are updated based on the operation behavior, and a data basis is provided for tracing the source of the subsequent article.
Referring to fig. 3, a main flowchart of an article tracing method provided by an embodiment of the present invention is shown, including the following steps:
s301: determining a source object according to the identity code of the object to be traced, and acquiring the image acquisition position and source characteristic information of the source object; the source characteristic information is obtained by carrying out characteristic extraction and fusion on a source image of the source object, and the source image corresponds to the image acquisition position;
S302: acquiring an image of the object to be traced based on the image acquisition position, and carrying out feature extraction and fusion on the image to obtain feature information of the object to be traced;
s303: and performing feature matching on the feature information and the source feature information, and if the matching result is accordant, determining that the tracing is successful.
In the above-described embodiment, for step S301, in the embodiment shown in fig. 1, the shooting position determination is performed on the source object by the staff member or the shooting device, and then the image is shot and the features at these positions are extracted.
In order to reduce the comparison range, improve the comparison accuracy and reduce human participation factors, consider the same thought of identity codes of the same article, and can determine the source article from the database through the identity codes of the article to be traced.
For step S302, the image of the same position in the object to be traced is photographed by using the photographing position (i.e., the image obtaining position, including the point location distribution and the position location distribution) of the object to be traced, so as to obtain the image of the object to be traced. Specifically:
acquiring a first plane image of an object to be traced based on a plane dimension;
determining the position of the part in the first plane image based on the part distribution, and further acquiring a first part image;
And determining the position of the point in the first position image based on the point position distribution, and further acquiring the first point position image.
In addition, when the point position image of the source article is considered to be acquired, the corresponding magnification is determined based on the point position material characteristics, so that
And amplifying and acquiring an image positioned at the point position in the first position image based on the amplification factor corresponding to the point position, so as to obtain an amplified first point position image. And when the first point position image of the object to be traced is acquired, the operation is also performed based on the magnification, so that the point position image and the first point position image are in a unified level.
For step S303, the feature information of the article to be traced is matched with the source feature information of the source article, and if the matching is successful, it indicates whether the article is genuine.
For the tracing result, a corresponding label can be added to the article to be traced, but it should be noted that the label herein does not change the article itself, and is only used for indicating the identification result.
In addition, under the condition of no identity code or no corresponding source article, in order to reduce the comparison range, the category of the article to be traced can be determined according to the basic information of the article to be traced, and then only the source article set belonging to the category is extracted from the database, and the characteristic comparison is carried out on the source articles in the source article set and the article to be traced.
Furthermore, the extracted source objects can be intensively screened again based on the attribute of the object to be traced so as to further reduce the matching range, and only the source objects which are the same as or similar to the attribute are extracted, so that the matching speed is increased.
According to the method provided by the embodiment, the source object is determined according to the identity code of the object to be traced, so that the comparison range is narrowed; the multi-dimensional shooting is carried out on the object to be traced based on the shooting position of the source object, so that the feature extraction and comparison precision is improved; besides factory characteristics, characteristics of the commodity circulation process are considered, and accuracy of comparison results is guaranteed.
Referring to fig. 4, a schematic diagram of an article tracing flow according to an embodiment of the present invention is shown, including the following steps:
s401: acquiring an integral image and a local image of a source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
s402: extracting features of the whole image and the local image, and fusing the extracted whole features and local features to obtain source feature information of the source object;
s403: if the source object is registered for the first time, acquiring an identity code of the source object, and establishing an archive of the source object by combining the integral image, the local image and the source characteristic information;
S404: determining a source object according to the identity code of the object to be traced, and acquiring the image acquisition position and source characteristic information of the source object;
s405: acquiring an image of the object to be traced based on the image acquisition position, and carrying out feature extraction and fusion on the image to obtain feature information of the object to be traced;
s406: and performing feature matching on the feature information and the source feature information, and if the matching result is accordant, determining that the tracing is successful.
According to the method provided by the embodiment of the invention, on the basis of not changing the object, the true and false identification and tracing are carried out by utilizing the attribute of the object and the image processing technology based on deep learning:
firstly, shooting images from three angles of a plane, a part and a point position of an article, and extracting image features; for the first registered articles, based on a blockchain anti-counterfeiting tracing technology, files are established and are "chained" so as to store operation information (such as places of production, batches and the like) and image information (such as images of planes, parts and points);
secondly, when the article circulates in the trade market again, images of the plane, the position and the point position dimension are shot again, image feature matching is carried out on the images and the source article which is 'uplinked', the matching speed is accelerated, and the aim of tracing the source without changing the original attribute of the article is fulfilled.
Referring to fig. 5, a schematic diagram of main modules of a feature information generating apparatus 500 according to an embodiment of the present invention is shown, including:
an image acquisition module 501, configured to acquire an overall image and a partial image of a source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
the source feature extraction module 502 is configured to perform feature extraction on the whole image and the local image, and fuse the extracted whole feature and local feature to obtain source feature information of the source object.
In the implementation device of the invention, the whole dimension is a plane dimension, and the local dimension comprises a part dimension and a point dimension;
the image acquisition module 501 is configured to:
acquiring a planar image of the source article based on the planar dimension;
acquiring an image of an area where at least one part is located in the plane image based on the part dimension to obtain a part image;
and acquiring an image of the region of at least one point in the position image based on the point dimension to obtain a point image.
In the embodiment of the present invention, the image acquisition module 501 is further configured to:
acquiring material characteristics of the source object at a single point from the basic information of the source object, and amplifying and acquiring an image of an area where the single point is positioned based on amplification factors corresponding to the material characteristics to obtain an amplified point image; and
Recording the magnification when the single point position acquires the point position image.
The implementation device of the present invention further includes a location distribution module 503 (not shown in the figure) for:
determining the position of the point in the position image to obtain point position distribution;
determining the position of the part in the plane image to obtain part distribution;
and taking the point position distribution and the position distribution as image acquisition positions of the source object.
The implementation device of the present invention further includes a gear establishment module 504 (not shown in the drawings) for: if the source object is registered for the first time, acquiring an identity code of the source object, and establishing a file of the source object by combining the integral image, the local image and the source characteristic information.
In the embodiment of the present invention, the profiling module 504 is further configured to: determining the operation behavior of the source article, and acquiring the operation image information of the source article in the operation behavior; wherein the operational behavior includes at least one of production, transaction, maintenance, component replacement.
In the embodiment of the present invention, the profiling module 504 is further configured to: encrypting the source characteristic information based on an information abstract algorithm to obtain encrypted source characteristic information.
Referring to fig. 6, a schematic diagram of main modules of an article tracing device 600 according to an embodiment of the present invention is shown, including:
the article determining module 601 is configured to determine a source article according to an identity code of the article to be traced, and acquire an image acquisition position and source characteristic information of the source article; the source characteristic information is obtained by carrying out characteristic extraction and fusion on a source image of the source object, and the source image corresponds to the image acquisition position;
the feature extraction module 602 is configured to obtain an image of the object to be traced based on the image obtaining position, and perform feature extraction and fusion on the image to obtain feature information of the object to be traced;
and the feature matching module 603 is configured to perform feature matching on the feature information and the source feature information, and if the matching result is in accordance with the feature information, determine that tracing is successful.
In the embodiment of the invention, the image acquisition position comprises position distribution and point position distribution;
the feature extraction module 602 is configured to:
acquiring a first plane image of the article to be traced based on a plane dimension;
determining the position of the part in the first plane image based on the part distribution, and further acquiring a first part image;
And determining the position of the point in the first position image based on the point position distribution, so as to acquire a first point position image.
In the embodiment of the present invention, the feature extraction module 602 is further configured to: and amplifying and acquiring an image positioned at the point position in the first position image based on the amplification factor corresponding to the point position, so as to obtain an amplified first point position image.
In addition, the implementation of the apparatus in the embodiments of the present invention has been described in detail in the above method, so that the description is not repeated here.
Fig. 7 illustrates an exemplary system architecture 700 in which embodiments of the present invention may be applied.
As shown in fig. 7, a system architecture 700 may include terminal devices 701, 702, 703, a network 704, and a server 705 (by way of example only). The network 704 is the medium used to provide communication links between the terminal devices 701, 702, 703 and the server 705. The network 704 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.
A user may interact with the server 705 via the network 704 using the terminal devices 701, 702, 703 to receive or send messages or the like. Various communication client applications can be installed on the terminal devices 701, 702, 703.
The terminal devices 701, 702, 703 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smartphones, tablets, laptop and desktop computers, and the like.
The server 705 may be a server providing various services, such as a background management server (by way of example only) providing support for shopping-type websites browsed by users using the terminal devices 701, 702, 703.
It should be noted that, the method provided by the embodiment of the present invention is generally performed by the server 705, and accordingly, the apparatus is generally disposed in the server 705.
It should be understood that the number of terminal devices, networks and servers in fig. 7 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.
Referring now to FIG. 8, there is illustrated a schematic diagram of a computer system 800 suitable for use in implementing an embodiment of the present invention. The terminal device shown in fig. 8 is only an example, and should not impose any limitation on the functions and the scope of use of the embodiment of the present invention.
As shown in fig. 8, the computer system 800 includes a Central Processing Unit (CPU) 801 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 802 or a program loaded from a storage section 808 into a Random Access Memory (RAM) 803. In the RAM 803, various programs and data required for the operation of the system 800 are also stored. The CPU 801, ROM 802, and RAM 803 are connected to each other by a bus 804. An input/output (I/O) interface 805 is also connected to the bus 804.
The following components are connected to the I/O interface 805: an input portion 806 including a keyboard, mouse, etc.; an output portion 807 including a display such as a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and a speaker; a storage section 808 including a hard disk or the like; and a communication section 809 including a network interface card such as a LAN card, a modem, or the like. The communication section 809 performs communication processing via a network such as the internet. The drive 810 is also connected to the I/O interface 805 as needed. A removable medium 811 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 810 as needed so that a computer program read out therefrom is mounted into the storage section 808 as needed.
In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication section 809, and/or installed from the removable media 811. The above-described functions defined in the system of the present invention are performed when the computer program is executed by a Central Processing Unit (CPU) 801.
The computer readable medium shown in the present invention may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, 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. In the context of this document, a computer 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. In the present invention, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer 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 computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The modules involved in the embodiments of the present invention may be implemented in software or in hardware. The described modules may also be provided in a processor, for example, as: a processor includes an image acquisition module, a source feature extraction module. The names of these modules do not constitute a limitation on the module itself in some cases, and for example, the source feature extraction module may also be described as "extract source feature module".
As another aspect, the present invention also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by a device, cause the device to include:
acquiring an integral image and a local image of a source object; the whole image and the local image are obtained through a whole dimension and a local dimension respectively;
and extracting the characteristics of the whole image and the local image, and fusing the extracted whole characteristics and local characteristics to obtain the source characteristic information of the source object.
According to the technical scheme provided by the embodiment of the invention, on the basis of not changing the object, the true and false identification and tracing are carried out by utilizing the attribute of the object and the image processing technology based on deep learning:
firstly, shooting images from three angles of a plane, a part and a point position of an article, and extracting image features; for the first registered articles, based on a blockchain anti-counterfeiting traceability technology (with a non-tamperable distributed account book recording characteristic), establishing a file to be "uplink" so as to store operation information (such as a production place, a batch and the like) and image information (such as images of planes, parts and points);
Secondly, when the article circulates in the trade market again, images of the plane, the position and the point position dimension are shot again, and image feature matching is carried out on the images and the source article which is 'up-chain', so that the aim of tracing the source can be fulfilled without changing the original attribute of the article.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives can occur depending upon design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (14)
1. A characteristic information generation method, characterized by comprising:
acquiring an integral image and a local image of a source object; the whole image and the local image are respectively obtained through a whole dimension and a local dimension, the local dimension comprises a position dimension and a point position dimension, the position and the point position are obtained through manual clicking, and the point position is in a micron level;
extracting features of the whole image and the local image, and fusing the extracted whole features and local features to obtain source feature information of the source object; the method comprises the steps of selecting a cascading feature extraction network, and fusing the features on the same scale.
2. The method of claim 1, wherein the overall dimension is a planar dimension;
the acquiring the whole image and the partial image of the source object comprises the following steps:
acquiring a planar image of the source article based on the planar dimension;
acquiring an image of an area where at least one part is located in the plane image based on the part dimension to obtain a part image;
and acquiring an image of an area where at least one point in the position image is located based on the point dimension, and obtaining a point image.
3. The method of claim 2, wherein the acquiring an image of an area in which at least one point in the location image is located based on the point dimension, to obtain a point image, further comprises:
acquiring material characteristics of the source object at a single point from the basic information of the source object, and amplifying and acquiring an image of an area where the single point is positioned based on amplification factors corresponding to the material characteristics to obtain an amplified point image; and
recording the magnification when the single point position acquires the point position image.
4. The method as recited in claim 2, further comprising:
Determining the position of the point in the position image to obtain point position distribution;
determining the position of the part in the plane image to obtain part distribution;
and taking the point position distribution and the position distribution as image acquisition positions of the source object.
5. The method of claim 1, further comprising, after said deriving source signature information for said source item:
if the source object is registered for the first time, acquiring an identity code of the source object, and establishing a file of the source object by combining the integral image, the local image and the source characteristic information.
6. The method of claim 5, wherein said creating a profile of said source item further comprises:
determining the operation behavior of the source article, and acquiring the operation image information of the source article in the operation behavior; wherein the operational behavior includes at least one of production, transaction, maintenance, component replacement.
7. The method of claim 5, wherein said creating a profile of said source item further comprises:
encrypting the source characteristic information based on an information abstract algorithm to obtain encrypted source characteristic information.
8. An article tracing method, comprising:
determining a source object according to the identity code of the object to be traced, and acquiring the image acquisition position and source characteristic information of the source object; the source characteristic information is obtained by carrying out characteristic extraction and fusion on a source image of the source object, and the source image corresponds to the image acquisition position;
acquiring an image of the object to be traced based on the image acquisition position, and carrying out feature extraction and fusion on the image to obtain feature information of the object to be traced;
and performing feature matching on the feature information and the source feature information, and if the matching result is accordant, determining that the tracing is successful.
9. The method of claim 8, wherein the image acquisition locations comprise a location distribution and a point location distribution;
the step of acquiring the image of the article to be traced based on the image acquisition position comprises the following steps:
acquiring a first plane image of the article to be traced based on a plane dimension;
determining the position of the part in the first plane image based on the part distribution, and further acquiring a first part image;
and determining the position of the point in the first position image based on the point position distribution, so as to acquire a first point position image.
10. The method of claim 9, wherein determining, based on the dot location distribution, a location of a dot location in the first location image, thereby obtaining a first dot image, further comprises:
and amplifying and acquiring an image positioned at the point position in the first position image based on the amplification factor corresponding to the point position, so as to obtain an amplified first point position image.
11. A feature information generating apparatus, comprising:
the image acquisition module is used for acquiring an integral image and a local image of the source object; the whole image and the local image are respectively obtained through a whole dimension and a local dimension, the local dimension comprises a position dimension and a point position dimension, the position and the point position are obtained through manual clicking, and the point position is in a micron level;
the source feature extraction module is used for extracting features of the whole image and the local image, and fusing the extracted whole features and local features to obtain source feature information of the source object; the method comprises the steps of selecting a cascading feature extraction network, and fusing the features on the same scale.
12. An article traceability device, comprising:
The source article determining module is used for determining the source article according to the identity code of the article to be traced and acquiring the image acquisition position and the source characteristic information of the source article; the source characteristic information is obtained by carrying out characteristic extraction and fusion on a source image of the source object, and the source image corresponds to the image acquisition position;
the feature extraction module is used for acquiring the image of the object to be traced based on the image acquisition position, and carrying out feature extraction and fusion on the image to obtain feature information of the object to be traced;
and the feature matching module is used for carrying out feature matching on the feature information and the source feature information, and if the matching result is accordant, successful tracing is determined.
13. An electronic device, comprising:
one or more processors;
storage means for storing one or more programs,
when executed by the one or more processors, causes the one or more processors to implement the method of any of claims 1-10.
14. A computer readable medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the method according to any of claims 1-10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136593.XA CN111340515B (en) | 2020-03-02 | 2020-03-02 | Feature information generation and article tracing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136593.XA CN111340515B (en) | 2020-03-02 | 2020-03-02 | Feature information generation and article tracing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111340515A CN111340515A (en) | 2020-06-26 |
| CN111340515B true CN111340515B (en) | 2023-09-26 |
Family
ID=71187168
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010136593.XA Active CN111340515B (en) | 2020-03-02 | 2020-03-02 | Feature information generation and article tracing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111340515B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112100430B (en) * | 2020-11-06 | 2021-03-30 | 北京沃东天骏信息技术有限公司 | Article tracing method and device |
| CN115205552A (en) * | 2022-07-14 | 2022-10-18 | 欧冶链金再生资源有限公司 | Metal packaging block feature extraction and identification system and method based on feature identification |
| CN117094736A (en) * | 2023-08-09 | 2023-11-21 | 云海链控股股份有限公司 | Product authentication method, device, equipment and computer readable storage medium |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871044A (en) * | 2012-12-14 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Image signature generating method and image verifying method and device |
| WO2017215669A1 (en) * | 2016-06-17 | 2017-12-21 | 北京市商汤科技开发有限公司 | Method and device for object recognition, data processing device, and computing device |
| CN107657463A (en) * | 2017-09-29 | 2018-02-02 | 北京京东尚科信息技术有限公司 | Article is traced to the source platform and method and device |
| CN108229302A (en) * | 2017-11-10 | 2018-06-29 | 深圳市商汤科技有限公司 | Feature extracting method, device, computer program, storage medium and electronic equipment |
| CN108389062A (en) * | 2018-05-10 | 2018-08-10 | 江南大学 | A kind of fruit anti-fake traceability system and method based on image procossing |
| CN108416590A (en) * | 2018-04-08 | 2018-08-17 | 程昔恩 | A kind of block chain technical certification method based on topography |
| CN108898128A (en) * | 2018-07-11 | 2018-11-27 | 宁波艾腾湃智能科技有限公司 | A kind of method for anti-counterfeit and equipment matching digital three-dimemsional model by photo |
| WO2019001481A1 (en) * | 2017-06-28 | 2019-01-03 | 北京市商汤科技开发有限公司 | Vehicle appearance feature identification and vehicle search method and apparatus, storage medium, and electronic device |
| CN109214834A (en) * | 2018-09-10 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | Product traceability method and apparatus based on block chain |
| CN110175660A (en) * | 2019-04-16 | 2019-08-27 | 广州云上区块链技术有限公司 | Logistics based on block chain is traced to the source implementation method |
| CN110648299A (en) * | 2018-06-26 | 2020-01-03 | 株式会社理光 | Image processing method, image processing apparatus, and computer-readable storage medium |
| CN110766706A (en) * | 2019-09-26 | 2020-02-07 | 深圳市景阳信息技术有限公司 | Image fusion method and device, terminal equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4089718B2 (en) * | 2005-08-31 | 2008-05-28 | ブラザー工業株式会社 | Image processing apparatus and program |
-
2020
- 2020-03-02 CN CN202010136593.XA patent/CN111340515B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103871044A (en) * | 2012-12-14 | 2014-06-18 | 阿里巴巴集团控股有限公司 | Image signature generating method and image verifying method and device |
| WO2017215669A1 (en) * | 2016-06-17 | 2017-12-21 | 北京市商汤科技开发有限公司 | Method and device for object recognition, data processing device, and computing device |
| WO2019001481A1 (en) * | 2017-06-28 | 2019-01-03 | 北京市商汤科技开发有限公司 | Vehicle appearance feature identification and vehicle search method and apparatus, storage medium, and electronic device |
| CN107657463A (en) * | 2017-09-29 | 2018-02-02 | 北京京东尚科信息技术有限公司 | Article is traced to the source platform and method and device |
| CN108229302A (en) * | 2017-11-10 | 2018-06-29 | 深圳市商汤科技有限公司 | Feature extracting method, device, computer program, storage medium and electronic equipment |
| CN108416590A (en) * | 2018-04-08 | 2018-08-17 | 程昔恩 | A kind of block chain technical certification method based on topography |
| CN108389062A (en) * | 2018-05-10 | 2018-08-10 | 江南大学 | A kind of fruit anti-fake traceability system and method based on image procossing |
| CN110648299A (en) * | 2018-06-26 | 2020-01-03 | 株式会社理光 | Image processing method, image processing apparatus, and computer-readable storage medium |
| CN108898128A (en) * | 2018-07-11 | 2018-11-27 | 宁波艾腾湃智能科技有限公司 | A kind of method for anti-counterfeit and equipment matching digital three-dimemsional model by photo |
| CN109214834A (en) * | 2018-09-10 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | Product traceability method and apparatus based on block chain |
| CN110175660A (en) * | 2019-04-16 | 2019-08-27 | 广州云上区块链技术有限公司 | Logistics based on block chain is traced to the source implementation method |
| CN110766706A (en) * | 2019-09-26 | 2020-02-07 | 深圳市景阳信息技术有限公司 | Image fusion method and device, terminal equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 徐科 ; 梁泽华 ; 孙媛 ; .基于区块链技术的中药材质量追溯研究与体系构建.现代计算机(专业版).2018,(32),第69-74页. * |
| 田华 ; 蒋平安 ; 武红旗 ; 刘汉坤 ; 李彪 ; 王金晶 ; .新疆特色林果产品溯源系统的设计与实现.广东农业科学.2013,(16),第182-185页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111340515A (en) | 2020-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111340515B (en) | Feature information generation and article tracing method and device | |
| US11978245B2 (en) | Method and apparatus for generating image | |
| TW202002569A (en) | Blockchain-based data verification method and apparatus, and electronic device | |
| CA3025064A1 (en) | Secure and traceable manufactured parts | |
| JP5805918B1 (en) | Information acquisition method and information acquisition apparatus | |
| CN108882025A (en) | Video frame treating method and apparatus | |
| CN111783142B (en) | Data protection method, device, server and medium | |
| US20170113412A1 (en) | System and method for printing a three-dimensional object incorporating an image | |
| CN109118456A (en) | Image processing method and device | |
| CN114153412A (en) | Display system and method for encrypted digital collection | |
| CN112258619A (en) | Image processing method and device | |
| CN107818323B (en) | Method and apparatus for processing image | |
| CN112862502A (en) | Authentication and transaction tracing method, system and storage medium based on block chain | |
| CN108492284A (en) | Method and apparatus for the perspective shape for determining image | |
| CN112100430B (en) | Article tracing method and device | |
| CN113989058A (en) | Service generation method and device | |
| CN109871890A (en) | Image processing method and device | |
| CN111797642B (en) | Bar code identification method and terminal | |
| CN109034085B (en) | Method and apparatus for generating information | |
| CN115563942A (en) | Contract generation method and device, electronic equipment and computer readable medium | |
| CN112765641B (en) | Efficient desensitization method and device | |
| CN108921792A (en) | Method and apparatus for handling picture | |
| CN108491258A (en) | Method and apparatus for handling image | |
| CN107368597B (en) | Information output method and device | |
| CN112016348A (en) | Face authenticity identification method and 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 |