CN113610540B - River crab anti-counterfeiting tracing method and system - Google Patents
River crab anti-counterfeiting tracing method and system Download PDFInfo
- Publication number
- CN113610540B CN113610540B CN202110779147.5A CN202110779147A CN113610540B CN 113610540 B CN113610540 B CN 113610540B CN 202110779147 A CN202110779147 A CN 202110779147A CN 113610540 B CN113610540 B CN 113610540B
- Authority
- CN
- China
- Prior art keywords
- tracing
- concha
- river crab
- traceability
- counterfeiting
- 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
- 238000000034 method Methods 0.000 title claims abstract description 77
- 238000000605 extraction Methods 0.000 claims abstract description 75
- 241000238557 Decapoda Species 0.000 claims abstract description 45
- 125000002496 methyl group Chemical group [H]C([H])([H])* 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 21
- 239000013598 vector Substances 0.000 claims abstract description 18
- 238000012549 training Methods 0.000 claims description 36
- 238000012795 verification Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 8
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 6
- 210000000988 bone and bone Anatomy 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 abstract description 15
- 238000004364 calculation method Methods 0.000 description 14
- 238000010586 diagram Methods 0.000 description 12
- 230000008569 process Effects 0.000 description 11
- 230000005540 biological transmission Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000012258 culturing Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000010330 laser marking Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000000877 morphologic effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000013526 transfer learning Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 241001391944 Commicarpus scandens Species 0.000 description 1
- 241000371997 Eriocheir sinensis Species 0.000 description 1
- 230000008033 biological extinction Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
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
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/80—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in fisheries management
- Y02A40/81—Aquaculture, e.g. of fish
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Finance (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a river crab anti-counterfeiting tracing method and system, comprising the following steps: acquiring a concha image and a tracing code of the river crab to be traced; inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crabs to be traced; inquiring a tracing code in a block chain tracing database to obtain an inquiring result; determining a reference back armor feature corresponding to the traceability code under the condition that the traceability code exists in the blockchain traceability database as a query result; vector comparison processing is carried out on the concha features and the reference concha features so as to obtain the tracing result of anti-counterfeiting tracing of the river crab to be traced. According to the river crab anti-counterfeiting tracing method and system, the stability and the uniqueness of the river crab methyl back characteristics are relied on, the blockchain technology is introduced, and the methyl back characteristics of the river crab to be traced are extracted, so that anti-counterfeiting tracing is finished, the credibility of enterprise river crab products is improved to a great extent, the anti-counterfeiting cost is reduced, the river crab products cannot be copied or counterfeited, and the reliability of tracing results is improved.
Description
Technical Field
The invention relates to the technical field of computers, in particular to a river crab anti-counterfeiting tracing method and system.
Background
The river crab culturing period is long, water quality pollution, insufficient disease monitoring, irregular use of culturing feeds and the like exist in the culturing process, and on the other hand, certain merchants use the river crabs in other producing areas to impersonate the river crabs in the original producing areas in a forging mode, so that the benign development of the industry is not facilitated. Therefore, the method is particularly critical to the source tracing of the river crabs.
At present, the river crab anti-counterfeiting method of enterprises mainly comprises the steps of binding crab buckles printed with electronic identifications such as bar codes or two-dimensional codes on river crab tongs, and enabling consumers to scan the verification identifications through mobile terminal equipment to obtain product information of the river crabs, so that anti-counterfeiting tracing is carried out on the river crabs.
Because crab buckles have strong replicability, are not unique and have higher cost, the risk of being artificially forged or recycled for the second time exists, and the traceability verification result is not credible.
Disclosure of Invention
Aiming at the problems existing in the prior art, the embodiment of the invention provides a river crab anti-counterfeiting tracing method and system.
The invention provides a river crab anti-counterfeiting tracing method, which comprises the following steps: acquiring a concha image and a tracing code of the river crab to be traced; inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crabs to be traced; inquiring a tracing code in a block chain tracing database to obtain an inquiring result; determining a reference back armor feature corresponding to the traceability code under the condition that the traceability code exists in the blockchain traceability database as a query result; vector comparison processing is carried out on the concha features and the reference concha features so as to obtain the tracing result of anti-counterfeiting tracing of the river crab to be traced.
According to the river crab anti-counterfeiting tracing method provided by the invention, vector comparison processing is carried out on the concha features of the river crab to be traced and the reference concha features to obtain the tracing result of anti-counterfeiting tracing on the river crab to be traced, and the method comprises the following steps: comparing the characteristics of the concha of the river crab to be traced with the reference characteristics of the concha to obtain comparison similarity; under the condition that the contrast similarity is larger than a preset threshold value, determining that the tracing result is successful tracing; and under the condition that the contrast similarity is not greater than the preset threshold value, determining the tracing result as tracing failure.
According to the river crab anti-counterfeiting tracing method provided by the invention, before the tracing code is queried by using the blockchain tracing database, the method further comprises the following steps: matching each river crab with a unique traceability code; utilizing the trained back armor feature extraction model to obtain the back armor feature of each river crab as a reference back armor feature; and uploading the reference back splint characteristic and the traceability code of each river crab to the blockchain traceability database.
According to the river crab anti-counterfeiting tracing method provided by the invention, under the condition that the query result is that the tracing code does not exist in the blockchain tracing database, the tracing result is determined to be tracing failure.
According to the river crab anti-counterfeiting tracing method provided by the invention, before the concha image is input into the trained concha feature extraction model, the method further comprises the following steps: and replacing a residual block of the depth residual network with a residual bottleneck block of the pyramid convolution structure to construct a concha feature extraction model to be trained.
According to the river crab anti-counterfeiting tracing method provided by the invention, after the model for extracting the characteristics of the back armor to be trained is constructed, the method further comprises the following steps: and pre-training the to-be-trained manicure feature extraction model by using an ImageNet data set to obtain a pre-trained manicure feature extraction model.
According to the river crab anti-counterfeiting tracing method provided by the invention, after the pre-trained concha feature extraction model is obtained, the method further comprises the following steps:
step 1, forming a training sample by the feature tag of each concha image sample and the concha image sample;
step 2, obtaining a sample set comprising a plurality of training samples;
step 3, dividing all training samples in the sample set into a training set, a verification set and a test set according to the proportion of 7:3:3;
step 4, training the pre-trained feature extraction model by using the training set to obtain a trained feature extraction model of the back bone;
step 5, verifying the trained feature extraction model of the manicure by using the verification set and the test set;
and 6, iterating the steps 4 to 5 until the accuracy and the loss value of the training set and the verification set are converged, and obtaining the trained feature extraction model of the concha.
The invention also provides a river crab anti-counterfeiting traceability system, which comprises: the acquisition unit is used for acquiring the concha images and the tracing codes of the river crabs to be traced; the feature extraction unit is used for inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crab to be traced; the query unit is used for querying the tracing code in the blockchain tracing database to obtain a query result; the determining unit is used for determining a reference back armor feature corresponding to the traceability code when the inquired result is that the traceability code exists in the blockchain traceability database; and the comparison unit is used for carrying out vector comparison processing on the concha characteristic and the reference concha characteristic so as to obtain a tracing result of anti-counterfeiting tracing on the river crab to be traced.
The invention also provides electronic equipment, which comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the processor realizes the steps of any one of the river crab anti-counterfeiting tracing methods when executing the program.
The invention also provides a non-transitory computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the river crab anti-counterfeiting tracing method as described in any one of the above.
According to the river crab anti-counterfeiting tracing method and system, the stability and the uniqueness of the river crab methyl back characteristics are relied on, the blockchain technology is introduced, and the methyl back image characteristics of the river crab to be traced are extracted, so that anti-counterfeiting tracing is completed, the credibility of river crab products of enterprises is improved to a great extent, the anti-counterfeiting cost is reduced, the river crab products cannot be copied or counterfeited, and the reliability of tracing results is improved.
Drawings
In order to more clearly illustrate the invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is one of the flow diagrams of the river crab anti-counterfeiting tracing method provided by the invention;
FIG. 2 is a schematic diagram of a pyramid convolution structure provided by the present invention;
FIG. 3 is a schematic diagram of a model architecture based on a transfer learning and pyramid convolution layer provided by the present invention;
FIG. 4 is a second flow chart of the anti-counterfeiting traceability method for river crabs;
FIG. 5 is a schematic diagram of an image data acquisition device according to the present invention;
FIG. 6 is a schematic structural diagram of the anti-counterfeiting traceability system for river crabs;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that in the description of embodiments of the present invention, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. The specific meaning of the above terms in the present invention can be understood by those of ordinary skill in the art according to the specific circumstances.
The river crab breeding industry in China is rapidly growing, and the total breeding area is about 47 ten thousand hm at present 2 The annual output is about 80 ten thousand tons, the total output value exceeds 500 hundred million yuan, and the method is the most potential prop industry in Chinese fishery production. Because the whole river crab supply chain has the characteristics of long cultivation period, scattered production and processing, multi-source heterogeneous traceability information and the like, consumers cannot acquire credible fine-granularity river crab traceability information. Generally, two problems exist by taking anti-counterfeiting crab buckles as traceability entrances, namely, the anti-counterfeiting means of river crabs such as the crab buckles are unreliable and difficult to acquire consumer trust, and the problem that information is lost and easy to tamper exists due to the fact that data of all nodes of a supply chain are autonomously managed by enterprises by using a traditional traceability system, and therefore, when disputes occur, the problems are difficult to evidence and the responsibility allocation is difficult to clear.
Some researches show that the eriocheir sinensis forms of different local populations, different watersheds and different culture conditions have obvious differences, so that the authenticity can be verified from the morphological characteristics of the river crabs.
In recent years, deep learning has achieved a series of research results in face recognition, medical image recognition and other fields of recognition, and the concha of a river crab has stable and unique morphological features (ravines, textures, bulges and the like), so that the biological features can be extracted by simulating the concha of the river crab as a face. Aiming at the defect that the current anti-counterfeiting mode is not credible, the biological characteristics of the river crab methyl is extracted as verification conditions, so that the credibility of river crab products of enterprises is improved to a great extent.
The river crab anti-counterfeiting tracing method and system provided by the embodiment of the invention are described below with reference to fig. 1 to 7.
Fig. 1 is a schematic flow chart of the anti-counterfeiting traceability method for river crabs, as shown in fig. 1, including but not limited to the following steps.
Firstly, in step S1, a nail image and a tracing code of a river crab to be traced are obtained.
Before the river crabs participate in the production and circulation processes, enterprises need to use a unique traceability code for each single river crab as identity information, the traceability codes are in one-to-one correspondence with the river crabs, the traceability codes unique to the enterprises can be printed on the back nails by using a laser marking machine, the traceability codes can also be made into anti-counterfeiting crab buckles and fixed on the body surfaces of the river crabs, in the follow-up embodiment of the invention, the traceability codes are printed on the river crab back nails for illustration, and the invention is not limited in the protection scope.
And simultaneously, taking the back characteristic of each river crab as a reference back armor characteristic, correlating and corresponding to the traceability code, and uploading the reference back armor characteristic to the blockchain traceability database. The reference back armor features can be obtained by extracting features of the river crab back armor image by using a trained back armor feature extraction model.
The block chain technology is based on key technologies such as distributed storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like, has the characteristics of decentralization, non-falsification of data, traceability, high availability and the like, and can effectively solve the trust problem of upstream and downstream data in the transmission process, thereby constructing a trusted transaction environment which is consistent with the traceability requirement. Therefore, a blockchain technology is introduced in a traceability link, so that the data of the agricultural product production information, the processing information, the transportation information and the sales information can not be modified once the data passes verification and is written into a blockbook, and the reality, the transparency and the reliability of the data are ensured.
When the river crab needs to be traced, a consumer can use terminal equipment such as a mobile phone to acquire a methyl back image of the river crab to be traced, and a tracing code printed on the methyl back of the river crab is identified through a tracing code extraction interface.
Further, in step S2, the concha image is input to a trained concha feature extraction model, and the concha features of the river crab to be traced are obtained.
Specifically, the back nail image of the river crab to be traced is input into a trained back nail feature extraction model, and the back nail features of the river crab to be traced are obtained by extracting the back nail features of the back nail image of the river crab to be traced.
Alternatively, the trained concha feature extraction model may be constructed based on one of the AlexNet, mobileNet, resNet _152, receptionv 4, denseNet, etc. network models.
Further, in step S3, the traceability code is queried in the blockchain traceability database to obtain a query result.
Specifically, the identified traceability codes are input into a blockchain traceability database for inquiry so as to obtain inquiry results.
The query result comprises that the traceability code exists in the blockchain traceability database and the traceability code does not exist in the blockchain traceability database.
Further, in step S4, if the query result is that the traceback code exists in the blockchain tracing database, a reference feature of the back armor corresponding to the traceback code is determined.
Specifically, when the query result is that the traceability code exists in the blockchain traceability database, a reference back-bone feature corresponding to the queried traceability code is determined in the blockchain traceability database.
Further, in step S5, vector comparison processing is performed on the concha feature and the reference concha feature, so as to obtain a tracing result of performing anti-counterfeiting tracing on the river crab to be traced.
Specifically, feature vector similarity calculation is carried out on the concha features of the river crabs to be traced and the reference concha features, and comparison judgment is carried out according to the calculation result and a preset threshold value so as to obtain tracing results of anti-counterfeiting tracing of the river crabs to be traced.
The similarity calculation method can calculate pearson correlation coefficient (Pearson Correlation Coefficient), euclidean distance (Euclidean Distance) or manhattan distance.
The tracing result comprises tracing success and tracing failure. The source tracing success is true and reliable, and the source tracing failure is unknown.
The river crab anti-counterfeiting tracing method provided by the invention relies on the stability and uniqueness of the river crab methyl back characteristics, introduces a blockchain technology, and extracts the methyl back characteristics of the river crab to be traced, thereby completing anti-counterfeiting tracing, greatly improving the credibility of river crab products of enterprises, reducing the anti-counterfeiting cost, being non-replicable and non-counterfeitable, and improving the reliability of tracing results.
Optionally, vector comparison processing is performed on the concha features of the river crab to be traced and the reference concha features to obtain tracing results of anti-counterfeiting tracing of the river crab to be traced, including: comparing the characteristics of the concha of the river crab to be traced with the reference characteristics of the concha to obtain comparison similarity; under the condition that the comparison similarity is larger than a preset threshold value, determining that the tracing result is successful tracing; and under the condition that the comparison similarity is not greater than a preset threshold value, determining the tracing result as tracing failure.
Specifically, similarity calculation is carried out on the characteristics of the concha of the river crab to be traced and the characteristics of the reference concha, and the comparison similarity is obtained.
Under the condition that the comparison similarity is larger than a preset threshold, the tracing result is determined to be tracing success, the tracing success can be prompted, and tracing information of the river crabs to be traced is pushed.
Under the condition that the comparison similarity is not larger than a preset threshold, determining that the tracing result is tracing failure, prompting the tracing failure, pushing common reasons of the tracing failure and maintaining right operation steps.
The preset threshold value can be flexibly selected according to practical situations, and the preset threshold value in the embodiment is selected to be 95%.
According to the river crab anti-counterfeiting tracing method provided by the invention, the tracing result is judged according to the similarity between the characteristics of the back nails of the river crabs to be traced and the reference back nails, the method is simple, and the tracing result has high reliability.
The aquatic products such as river crabs are complex in traceability links and heterogeneous in traceability information, and the traditional traceability technology has the problems that manual intervention data input, data storage and transmission are unsafe and the like.
Optionally, before querying the traceback code using the blockchain traceability database, the method further includes: matching each river crab with a unique traceability code; the trained back armor feature extraction model is utilized to obtain the back armor feature of each river crab as the reference back armor feature; and uploading the reference back splint characteristics and the traceability codes of each river crab to a blockchain traceability database.
Specifically, before the river crabs participate in the production and circulation process, enterprises need to give each single river crab a unique traceability code as identity information, the traceability codes are in one-to-one correspondence with the river crabs, and the trained concha feature extraction model is utilized to obtain the concha feature of each river crab as the reference concha feature; and uploading the reference back splint characteristics and the traceability codes of each river crab to a blockchain traceability database.
The traceability information, the traceability codes and the reference concha features can be associated together and uploaded to the blockchain traceability database in the river crab production and circulation process. The traceability information comprises at least one of the following information: production information, processing information, transportation information, and sales information.
Because blockchains are continuously growing distributed databases that are commonly maintained by multiple parties, trust relationships are established based on distributed networks, cryptography and consensus mechanisms, and value Internet is built through intelligent contracts. Therefore, aiming at the problems of asymmetric information among nodes, high trust cost and the like caused by complex interest game relation of a main body at the upstream and downstream of a supply chain of a river crab supply chain with the characteristics of long chain, scattered production, multi-source information isomerism and the like, the block chain technology and the river crab traceability are combined to form a very effective solution.
In the process of tracing the river crabs by consumers, the characteristics mentioned by the neural network need to be subjected to similarity calculation with the characteristic vectors stored in the blockchain database, if no other identification technology exists, the river crab tracing information which is larger than the threshold value can be obtained only through one-by-one calculation and comparison, but the mode occupies larger calculation resources and has the defects of wrong identification or multiple object identification. The method is similar to ticket checking at a high-speed rail station, each river crab can be provided with a traceability code as an identity number, and the traceability information of the fine granularity of the river crab can be accurately inquired through the individual traceability code, and meanwhile, similarity calculation is only needed once, so that the identification time is shortened, and the waste of calculation resources is avoided.
According to the river crab anti-counterfeiting tracing method provided by the invention, the block chain technology is combined with river crab tracing to realize the centralized management of the scattered resources and the centralized resource scattered service, so that technical support is provided for solving the problems existing in the traditional tracing system at present.
Optionally, in the case that the query result is that the tracing code does not exist in the blockchain tracing database, determining that the tracing result is tracing failure.
Specifically, whether the traceability code exists or not is firstly judged by inquiring whether the traceability code exists or not of the river crab to be traced, and under the condition that the inquired result is that the traceability code does not exist in the blockchain traceability database, the traceability result is determined to be tracing failure, the tracing failure can be prompted, the common cause of the tracing failure is pushed, and the right-maintaining operation step is performed.
According to the river crab anti-counterfeiting tracing method provided by the invention, under the condition that the tracing code does not exist in the blockchain tracing database, the tracing failure is directly judged, the identification time is shortened, and the waste of computing resources is avoided.
Optionally, before inputting the nail image into the trained nail feature extraction model, the method further comprises: and replacing a residual block of the depth residual network with a residual bottleneck block of the pyramid convolution structure to construct a concha feature extraction model to be trained.
Fig. 2 is a schematic diagram of a pyramid convolution structure provided in the present invention, as shown in fig. 2, where the pyramid convolution structure includes n convolution layers of different types of convolution Kernels, and on the premise of not increasing the calculation cost and the parameter number, different scale convolution Kernels (PC 1 Kernels, PC2 Kernels, PC3 Kernels, …, PCn Kernels) process an Input feature map (Input FM), different types of Kernels have different spatial resolutions and depths to capture more detailed information, kernels with smaller fields can concentrate on the detailed information, and increasing the kernel size can provide more reliable information between contexts. As the space size increases, the depth of the convolution kernel decreases from the first level to the nth level, eventually forming a plurality of convolution branches. The feature mapping carries out grouping convolution through different convolution branches, and finally, the features of the different branches are spliced in a cascading way to form a fusion feature.
For the Input feature map (Input FM), different pyramid convolution layers apply convolution kernels { k) of different spatial sizes 12 ，k 22 ，k 32 ，…，k n2 Respectively output corresponding feature graphs { FM } 1 ，FM 2 ，FM 3 ，…，FM n Finally, a fused Output characteristic diagram (Output FM) is obtained through splicing, wherein Output FM=FM 1 +FM 2 +FM 3 +…+FM n 。
The depth residual network (ResNet) is a deep convolutional neural network integrating image, automation coding and classification, which prevents gradient extinction by using feature transmission. The present embodiment replaces residual blocks of res net with residual bottleneck blocks based on a pyramid convolution structure, replacing 3×3 convolution kernels in standard residual blocks with pyramid convolution layers of different kernel levels (9×9,7×7,5×5,3×3), where the depth of the kernels is different at each level.
According to the river crab anti-counterfeiting tracing method provided by the invention, the residual bottleneck blocks of the pyramid convolution structure are used for replacing the residual blocks of the depth residual network, so that the depth of the kernel in the concha feature extraction model is different at each level, and a better feature extraction effect is achieved.
Optionally, after constructing the model for extracting the feature of the concha to be trained, the method further comprises: and pre-training the to-be-trained concha feature extraction model by using the ImageNet data set to obtain a pre-trained concha feature extraction model.
Specifically, the feature extraction model of the back bone to be trained learns by using the parameters after the pre-training of the ImageNet data set, and the pre-trained regional parameters are ground into parameters at the same position as the identification model of the back bone of the river crab.
According to the river crab anti-counterfeiting tracing method provided by the invention, the image Net dataset is utilized to pretrain the concha feature extraction model to be trained, so that the retrained training set can be converged rapidly, the training time is shortened, and the efficiency is improved.
Optionally, after obtaining the pre-trained concha feature extraction model, further comprising:
step 1, forming a training sample by the feature tag of each concha image sample and the concha image sample;
step 2, acquiring a data sample set comprising a plurality of training samples;
step 3, all training samples in the data sample set are processed according to the following ratio of 7:3:3 is divided into a training set, a verification set and a test set;
step 4, training the pre-trained feature extraction model by using a training set to obtain a trained feature extraction model of the back bone;
step 5, verifying the trained feature extraction model of the manicure by using the verification set and the test set;
and 6, iterating the steps 4 to 5 until the accuracy and the loss value of the training set and the verification set are converged, and obtaining a trained feature extraction model of the manicure.
Specifically, in step 1, a dorsal scale image containing clear biological features is preprocessed and expanded, and a training sample is formed by a feature tag of each dorsal scale image sample and the dorsal scale image sample.
The data expansion mainly comprises operations such as rotation, overturning, scaling, noise disturbance, color change and the like of an original acquired image, and the image preprocessing mainly comprises gray value and normalization processing of an expanded data set.
Further, in step 2, a data sample set including a plurality of training samples is obtained, and the number of training samples in the data sample set may be flexibly set according to the actual situation.
Further, in step 3, all training samples in the data sample set are processed as 7:3: the proportion of 3 is divided into three parts of a training set, a verification set and a test set.
Further, in step 4, training is performed on the pre-trained feature extraction model by using the training set, and a trained feature extraction model of the back bone is obtained.
Further, in step 5, the trained feature extraction model of the concha is verified by using the verification set and the test set.
Further, in step 6, iterating step 4 to step 5 until the accuracy and loss values of the training set and the verification set converge, so that model parameters with good recognition performance can be obtained, and a trained concha feature extraction model is obtained.
The trained concha feature extraction model can be used for extracting the reference concha features of the river crabs and storing the reference concha features in a blockchain traceability database.
Fig. 3 is a schematic diagram of a model architecture based on a transfer learning and pyramid Convolution layer, as shown in fig. 3, firstly, pretraining by using an ImageNet dataset (ImageNet dataset), firstly, rolling and Pooling (Pooling) of input data to obtain a feature map (Features Maps), outputting categories through a full connection layer Fe, scoring the categories to a classification layer (Softmax), and finally outputting a comparison similarity.
And obtaining the pre-trained parameters, and transferring the parameters to a feature extraction model of the manicure to be trained to obtain the feature extraction model of the manicure to be trained.
Input Images (Input Images) are Input to a pre-trained feature extraction model of the dorsal horn through Three Channels (Three Channels), and an Input feature map (Input Features Maps) is obtained first. Wherein the Input Images (Input Images) are training samples.
For the input feature map (Input Features Maps), different pyramid convolution layers (Pyconv: FM) 1 kernels，Pyconv：FM 2 kernels，Pyconv：FM 3 kernels，…，Pyconv：FM n kernel applies convolution kernels of different space sizes, and outputs corresponding Feature Maps (FM) 1 ，FM 2 ，FM 3 ，…，FM n ) Finally, the fused Output characteristic mapping Output FM=FM is obtained through splicing 1 +FM 2 +FM 3 +…+FM n 。
In the pyramid convolution structure (Pyramid convolution structure), as the convolution kernel size increases, the channel size decreases, to output a feature map (output Features Maps), through the full connection layer Fe to output a class, to sort layer (Softmax) to score the class, and finally to output a contrast similarity.
According to the river crab anti-counterfeiting tracing method provided by the invention, the pre-trained concha feature extraction model is trained by constructing the data sample set, so that the trained concha feature extraction model is obtained, and the concha feature extraction model obtained by the method has the characteristics of strong fault tolerance and high recognition rate, and provides a basis for tracing of the subsequent river crabs.
Fig. 4 is a second flow chart of the anti-counterfeiting and tracing method for the river crabs, as shown in fig. 4, after receiving the river crabs, a consumer can use terminal equipment such as mobile phones to photograph the river crabs, and obtain a concha figure of the river crabs to be traced. On one hand, feature extraction can be carried out on the back nail image through a back nail feature extraction model to obtain the back nail features of the river crab to be traced; on the other hand, the traceability code in the back-bone image is extracted by using the traceability code extraction interface, the traceability code of the river crab to be traced is obtained, then the traceability code is searched in the blockchain traceability database, if the traceability code does not exist, the traceability is failed, and if the traceability code does exist, the reference back-bone characteristic corresponding to the traceability code is extracted.
Further, the reference methyl back and the methyl back characteristics of the river crab images to be traced extracted by the river crab identification model are used for carrying out similarity calculation, and if the similarity is greater than 95%, the inquiry is successful, and if the similarity is not greater than 95%, the inquiry fails.
Fig. 5 is a schematic structural diagram of an image data acquisition device provided by the invention, as shown in fig. 5, an industrial camera 501 is arranged in a box 502, performs a methyl image acquisition on a river crab 504 placed on a river crab image acquisition platform 503, and transmits the acquired methyl image to a computer 506 through a data transmission channel 505, and the computer 506 acquires the methyl characteristics of the river crab through the methyl image and performs preprocessing and expansion on the methyl image of the river crab to acquire a methyl image sample.
According to the river crab anti-counterfeiting tracing method provided by the invention, the river crab characteristics are extracted by using the deep learning neural network by virtue of the stability and uniqueness of the river crab characteristics, and the problems that the river crab anti-counterfeiting mode is unreliable and the river crab supply chain information is easy to break can be solved by using the blockchain technology to store the river crab link tracing information, so that the trust of consumers on the tracing information is improved.
Fig. 6 is a schematic structural diagram of the anti-counterfeiting traceability system for river crabs, provided by the invention, as shown in fig. 6, including:
the acquiring unit 601 is configured to acquire a concha image and a tracing code of a river crab to be traced;
the feature extraction unit 602 is configured to input a concha image into a trained concha feature extraction model, and obtain the concha features of the river crab to be traced;
the query unit 603 is configured to query a traceback code in the blockchain traceback database to obtain a query result;
a determining unit 604, configured to determine a reference back-nail feature corresponding to the traceback code when the query result is that the traceback code exists in the blockchain traceback database;
the comparison unit 605 is configured to perform vector comparison processing on the concha feature and the reference concha feature, so as to obtain a tracing result of performing anti-counterfeiting tracing on the river crab to be traced.
In the running process of the system, the acquisition unit 601 acquires a concha image and a tracing code of the river crab to be traced; the feature extraction unit 602 inputs the concha image output by the acquisition unit 601 to a trained concha feature extraction model to acquire the concha features of the river crab to be traced; the query unit 603 queries the traceability code output by the acquisition unit 601 in the blockchain traceability database to acquire a query result; in the case that the query result output by the query unit 603 is that the traceback code exists in the blockchain traceback database, the determining unit 604 determines a reference feature of the concha corresponding to the traceback code; the comparison unit 605 performs vector comparison processing on the concha feature output by the feature extraction unit 602 and the reference concha feature output by the determination unit 604, so as to obtain a tracing result of performing anti-counterfeiting tracing on the river crab to be traced.
Optionally, the acquiring unit 601 acquires a back nail image and a tracing code of the river crab to be traced.
Before the river crabs participate in the production and circulation processes, enterprises need to use a unique traceability code for each single river crab as identity information, the traceability codes are in one-to-one correspondence with the river crabs, the unique traceability codes of the enterprises can be printed on the waistcoat by using a laser marking machine in a corresponding mode, and the traceability codes can be made into anti-counterfeiting crab buckles and fixed on the body surface of the river crabs.
And simultaneously, taking the back characteristic of each river crab as a reference back armor characteristic, correlating and corresponding to the traceability code, and uploading the reference back armor characteristic to the blockchain traceability database. The reference back armor features can be obtained by extracting features of the river crab back armor image by using a trained back armor feature extraction model.
The block chain technology is based on key technologies such as distributed storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like, has the characteristics of decentralization, non-falsification of data, traceability, high availability and the like, and can effectively solve the trust problem of upstream and downstream data in the transmission process, thereby constructing a trusted transaction environment which is consistent with the traceability requirement. Therefore, a blockchain technology is introduced in a traceability link, so that the data of the agricultural product production information, the processing information, the transportation information and the sales information can not be modified once the data passes verification and is written into a blockbook, and the reality, the transparency and the reliability of the data are ensured.
When the river crab needs to be traced, a consumer can use terminal equipment such as a mobile phone to acquire a methyl back image of the river crab to be traced, and a tracing code printed on the methyl back of the river crab is identified through a tracing code extraction interface.
Further, the feature extraction unit 602 inputs the concha image to a trained concha feature extraction model to obtain the concha features of the river crab to be traced.
Specifically, the back nail image of the river crab to be traced is input into a trained back nail feature extraction model, and the back nail features of the river crab to be traced are obtained by extracting the back nail features of the back nail image of the river crab to be traced.
Alternatively, the trained concha feature extraction model may be constructed based on one of the AlexNet, mobileNet, resNet _152, receptionv 4, denseNet, etc. network models.
Further, the query unit 603 queries the traceability code in the blockchain traceability database to obtain a query result.
Specifically, the identified traceability codes are input into a blockchain traceability database for inquiry so as to obtain inquiry results.
The query result comprises that the traceability code exists in the blockchain traceability database and the traceability code does not exist in the blockchain traceability database.
Further, in the case where the query result is that the traceback code exists in the blockchain traceback database, the determining unit 604 determines the reference cuisine corresponding to the traceback code.
Specifically, when the query result is that the traceability code exists in the blockchain traceability database, a reference back-bone feature corresponding to the queried traceability code is determined in the blockchain traceability database.
Further, the comparison unit 605 performs vector comparison processing on the concha feature and the reference concha feature to obtain a tracing result of performing anti-counterfeiting tracing on the river crab to be traced.
Specifically, feature vector similarity calculation is carried out on the concha features of the river crabs to be traced and the reference concha features, and comparison judgment is carried out according to the calculation result and a preset threshold value so as to obtain tracing results of anti-counterfeiting tracing of the river crabs to be traced.
The similarity calculation method can calculate pearson correlation coefficient (Pearson Correlation Coefficient), euclidean distance (Euclidean Distance) or manhattan distance.
The tracing result comprises tracing success and tracing failure.
The source tracing success is true and reliable, and the source tracing failure is unknown.
The river crab anti-counterfeiting tracing system provided by the invention relies on the stability and uniqueness of the river crab methyl back characteristics, introduces a blockchain technology, and extracts the methyl back characteristics of the river crab to be traced, thereby completing anti-counterfeiting tracing, greatly improving the credibility of river crab products of enterprises, reducing the anti-counterfeiting cost, being non-replicable and non-counterfeitable, and improving the reliability of tracing results.
It should be noted that, when the anti-counterfeiting traceability system for river crabs provided by the embodiment of the present invention is specifically implemented, the anti-counterfeiting traceability system for river crabs may be implemented based on the anti-counterfeiting traceability method for river crabs described in any one of the above embodiments, and the description of this embodiment is omitted.
Fig. 7 is a schematic structural diagram of an electronic device according to the present invention, and as shown in fig. 7, the electronic device may include: processor 710, communication interface (Communications Interface) 720, memory 730, and communication bus 740, wherein processor 710, communication interface 720, memory 730 communicate with each other via communication bus 740. The processor 710 may call logic instructions in the memory 730 to perform a river crab anti-counterfeiting tracing method, the method comprising: acquiring a concha image and a tracing code of the river crab to be traced; inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crabs to be traced; inquiring a tracing code in a block chain tracing database to obtain an inquiring result; determining a reference back armor feature corresponding to the traceability code under the condition that the traceability code exists in the blockchain traceability database as a query result; vector comparison processing is carried out on the concha features and the reference concha features so as to obtain the tracing result of anti-counterfeiting tracing of the river crab to be traced.
Further, the logic instructions in the memory 730 described above may be implemented in the form of software functional units and may be stored in a computer readable storage medium when sold or used as a stand alone product. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, the present invention also provides a computer program product, the computer program product comprising a computer program stored on a non-transitory computer readable storage medium, the computer program comprising program instructions which, when executed by a computer, enable the computer to perform the river crab anti-counterfeiting tracing method provided by the above methods, the method comprising: acquiring a concha image and a tracing code of the river crab to be traced; inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crabs to be traced; inquiring a tracing code in a block chain tracing database to obtain an inquiring result; determining a reference back armor feature corresponding to the traceability code under the condition that the traceability code exists in the blockchain traceability database as a query result; vector comparison processing is carried out on the concha features and the reference concha features so as to obtain the tracing result of anti-counterfeiting tracing of the river crab to be traced.
In still another aspect, the present invention further provides a non-transitory computer readable storage medium, on which a computer program is stored, the computer program being implemented when being executed by a processor to perform the river crab anti-counterfeiting tracing method provided in the above embodiments, the method comprising: acquiring a concha image and a tracing code of the river crab to be traced; inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crabs to be traced; inquiring a tracing code in a block chain tracing database to obtain an inquiring result; determining a reference back armor feature corresponding to the traceability code under the condition that the traceability code exists in the blockchain traceability database as a query result; vector comparison processing is carried out on the concha features and the reference concha features so as to obtain the tracing result of anti-counterfeiting tracing of the river crab to be traced.
The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (8)
1. The river crab anti-counterfeiting tracing method is characterized by comprising the following steps of:
acquiring a concha image and a tracing code of the river crab to be traced;
inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crab to be traced;
inquiring the tracing code in a block chain tracing database to obtain an inquiring result;
determining a reference back armor feature corresponding to the traceability code under the condition that the inquired result is that the traceability code exists in the blockchain traceability database;
vector comparison processing is carried out on the concha features and the reference concha features so as to obtain a tracing result of anti-counterfeiting tracing on the river crabs to be traced;
before querying the traceability code by using the blockchain traceability database, the method further comprises the following steps:
matching each river crab with a unique traceability code;
utilizing the trained back armor feature extraction model to obtain the back armor feature of each river crab as a reference back armor feature;
associating the tracing information with the tracing code and the reference back armor features, and uploading the tracing information to the blockchain tracing database; wherein the traceability information comprises at least one of the following information: production information, processing information, transportation information, and sales information;
before inputting the nail image into the trained nail feature extraction model, the method further comprises:
and replacing a residual block of the depth residual network with a residual bottleneck block of the pyramid convolution structure to construct a concha feature extraction model to be trained.
2. The river crab anti-counterfeiting tracing method according to claim 1, wherein vector comparison processing is performed on the methyl back feature of the river crab to be traced and the reference methyl back feature to obtain a tracing result of anti-counterfeiting tracing on the river crab to be traced, comprising:
comparing the characteristics of the concha of the river crab to be traced with the reference characteristics of the concha to obtain comparison similarity;
under the condition that the contrast similarity is larger than a preset threshold value, determining that the tracing result is successful tracing;
and under the condition that the contrast similarity is not greater than the preset threshold value, determining the tracing result as tracing failure.
3. The river crab anti-counterfeiting traceability method according to claim 1, wherein the traceability result is determined to be traceability failure under the condition that the query result is that the traceability code does not exist in the blockchain traceability database.
4. The river crab anti-counterfeiting traceability method according to claim 3, further comprising, after constructing a model of extracting the characteristics of the concha to be trained:
and pre-training the to-be-trained manicure feature extraction model by using an ImageNet data set to obtain a pre-trained manicure feature extraction model.
5. The river crab anti-counterfeiting traceability method according to claim 4, further comprising, after obtaining the pre-trained concha feature extraction model:
step 1, forming a training sample by the feature tag of each concha image sample and the concha image sample;
step 2, obtaining a sample set comprising a plurality of training samples;
step 3, dividing all training samples in the sample set into a training set, a verification set and a test set according to the proportion of 7:3:3;
step 4, training the pre-trained feature extraction model by using the training set to obtain a trained feature extraction model of the back bone;
step 5, verifying the trained feature extraction model of the manicure by using the verification set and the test set;
and 6, iterating the steps 4 to 5 until the accuracy and the loss value of the training set and the verification set are converged, and obtaining the trained feature extraction model of the concha.
6. The river crab anti-counterfeiting traceability system is characterized by comprising:
the acquisition unit is used for acquiring the concha images and the tracing codes of the river crabs to be traced;
the feature extraction unit is used for inputting the concha image into a trained concha feature extraction model to obtain the concha features of the river crab to be traced;
the query unit is used for querying the tracing code in the blockchain tracing database to obtain a query result;
the determining unit is used for determining a reference back armor feature corresponding to the traceability code when the inquired result is that the traceability code exists in the blockchain traceability database;
the comparison unit is used for carrying out vector comparison processing on the concha features and the reference concha features so as to obtain a tracing result of anti-counterfeiting tracing on the river crabs to be traced;
the river crab anti-counterfeiting traceability system is used for executing the river crab anti-counterfeiting traceability method according to any one of claims 1 to 5.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the river crab anti-counterfeiting tracing method according to any one of claims 1 to 5 when the computer program is executed by the processor.
8. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the river crab anti-counterfeiting tracing method steps according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110779147.5A CN113610540B (en) | 2021-07-09 | 2021-07-09 | River crab anti-counterfeiting tracing method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110779147.5A CN113610540B (en) | 2021-07-09 | 2021-07-09 | River crab anti-counterfeiting tracing method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113610540A CN113610540A (en) | 2021-11-05 |
| CN113610540B true CN113610540B (en) | 2024-02-02 |
Family
ID=78304354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110779147.5A Active CN113610540B (en) | 2021-07-09 | 2021-07-09 | River crab anti-counterfeiting tracing method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610540B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114241248B (en) * | 2022-02-24 | 2022-07-01 | 北京市农林科学院信息技术研究中心 | River crab origin tracing method and system |
| WO2024033290A1 (en) * | 2022-08-09 | 2024-02-15 | Lagosta Sa | Method and identification device for identification of a shell of a crustacean |
| CN115983874B (en) * | 2023-02-17 | 2023-06-30 | 江苏秀圆果信息科技有限公司 | Wine anti-counterfeiting tracing method and system thereof |
| CN116911883B (en) * | 2023-09-14 | 2023-12-19 | 新立讯科技股份有限公司 | Agricultural product anti-counterfeiting tracing method and cloud platform based on AI (advanced technology) authentication technology and tracing quantification |
| CN117057826A (en) * | 2023-10-12 | 2023-11-14 | 深圳市一航网络信息技术有限公司 | Product traceability verification method based on blockchain technology |
| CN117314908B (en) * | 2023-11-29 | 2024-03-01 | 四川省烟草公司凉山州公司 | Flue-cured tobacco virus tracing method, medium and system |
| CN117709986B (en) * | 2024-02-05 | 2024-05-28 | 福建农业职业技术学院 | Agricultural product production date credible tracing method and system based on deep learning |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4523230A (en) * | 1983-11-01 | 1985-06-11 | Rca Corporation | System for coring an image-representing signal |
| CN105894045A (en) * | 2016-05-06 | 2016-08-24 | 电子科技大学 | Vehicle type recognition method with deep network model based on spatial pyramid pooling |
| CN106305567A (en) * | 2016-08-21 | 2017-01-11 | 盘锦光合蟹业有限公司 | Image identification method used for judging river crabs |
| CN110021425A (en) * | 2019-01-31 | 2019-07-16 | 湖南品信生物工程有限公司 | A kind of relatively detector and its construction method and cervical cancer cell detection method |
| CN110100774A (en) * | 2019-05-08 | 2019-08-09 | 安徽大学 | River crab male and female recognition methods based on convolutional neural networks |
| AU2020100301A4 (en) * | 2020-02-29 | 2020-04-02 | Nanning Novosense Microelectronics Co., Ltd | Method and system for recognizing and tracing river crab based on computer implemented image recognition |
| CN111368078A (en) * | 2020-02-28 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Model training method, text classification device and storage medium |
| CN112184752A (en) * | 2020-09-08 | 2021-01-05 | 北京工业大学 | Video target tracking method based on pyramid convolution |
| CN112215243A (en) * | 2020-10-30 | 2021-01-12 | 百度(中国)有限公司 | Image feature extraction method, device, equipment and storage medium |
| CN112287924A (en) * | 2020-12-24 | 2021-01-29 | 北京易真学思教育科技有限公司 | Text region detection method, text region detection device, electronic equipment and computer storage medium |
-
2021
- 2021-07-09 CN CN202110779147.5A patent/CN113610540B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4523230A (en) * | 1983-11-01 | 1985-06-11 | Rca Corporation | System for coring an image-representing signal |
| CN105894045A (en) * | 2016-05-06 | 2016-08-24 | 电子科技大学 | Vehicle type recognition method with deep network model based on spatial pyramid pooling |
| CN106305567A (en) * | 2016-08-21 | 2017-01-11 | 盘锦光合蟹业有限公司 | Image identification method used for judging river crabs |
| CN110021425A (en) * | 2019-01-31 | 2019-07-16 | 湖南品信生物工程有限公司 | A kind of relatively detector and its construction method and cervical cancer cell detection method |
| CN110100774A (en) * | 2019-05-08 | 2019-08-09 | 安徽大学 | River crab male and female recognition methods based on convolutional neural networks |
| CN111368078A (en) * | 2020-02-28 | 2020-07-03 | 腾讯科技（深圳）有限公司 | Model training method, text classification device and storage medium |
| AU2020100301A4 (en) * | 2020-02-29 | 2020-04-02 | Nanning Novosense Microelectronics Co., Ltd | Method and system for recognizing and tracing river crab based on computer implemented image recognition |
| CN112184752A (en) * | 2020-09-08 | 2021-01-05 | 北京工业大学 | Video target tracking method based on pyramid convolution |
| CN112215243A (en) * | 2020-10-30 | 2021-01-12 | 百度(中国)有限公司 | Image feature extraction method, device, equipment and storage medium |
| CN112287924A (en) * | 2020-12-24 | 2021-01-29 | 北京易真学思教育科技有限公司 | Text region detection method, text region detection device, electronic equipment and computer storage medium |
Non-Patent Citations (6)
| Title |
|---|
| Local-binarized very deep residual network for visual categorization;Liu, XJ 等;NEUROCOMPUTING(第430期);第82-93页 * |
| 基于图像特征的河蟹个体识别算法的研究与应用;冯裕清;中国优秀硕士学位论文全文数据库 农业科技辑(第02期);第D052-604页 * |
| 基于深度中心邻域金字塔结构的显著目标检测;陈琴;朱磊;后云龙;邓慧萍;吴谨;;模式识别与人工智能(第06期);第94-100+114页 * |
| 基于蟹壳图像的中华绒螯蟹防伪体系研究;张炳良 等;科学养鱼(第2期);第77-78页 * |
| 基于迁移学习和金字塔卷积网络的河蟹个体图像识别方法研究;冯裕清 等;渔业现代化;第49卷(第1期);第52-60/71页 * |
| 深度学习在医学图像分析中的应用研究综述;黄江珊;王秀红;;图书情报研究(第02期);第21-31页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113610540A (en) | 2021-11-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113610540B (en) | River crab anti-counterfeiting tracing method and system | |
| CN111079639B (en) | Method, device, equipment and storage medium for constructing garbage image classification model | |
| CN109002755B (en) | Age estimation model construction method and estimation method based on face image | |
| CN110532417A (en) | Image search method, device and terminal device based on depth Hash | |
| CN110598019B (en) | Repeated image identification method and device | |
| CN109165275B (en) | Intelligent substation operation ticket information intelligent search matching method based on deep learning | |
| CN111966875A (en) | Sensitive information identification method and device | |
| CN111461164B (en) | Sample data set capacity expansion method and model training method | |
| CN114092742B (en) | Multi-angle-based small sample image classification device and method | |
| CN113706151A (en) | Data processing method and device, computer equipment and storage medium | |
| CN114298122A (en) | Data classification method, device, equipment, storage medium and computer program product | |
| CN111291695B (en) | Training method and recognition method for recognition model of personnel illegal behaviors and computer equipment | |
| Yu et al. | Exemplar-based recursive instance segmentation with application to plant image analysis | |
| CN112148997A (en) | Multi-modal confrontation model training method and device for disaster event detection | |
| CN111709225A (en) | Event cause and effect relationship judging method and device and computer readable storage medium | |
| CN114898472A (en) | Signature identification method and system based on twin vision Transformer network | |
| CN114782752A (en) | Small sample image grouping classification method and device based on self-training | |
| CN113704534A (en) | Image processing method and device and computer equipment | |
| CN112215066A (en) | Livestock face image recognition method and device | |
| CN104200222B (en) | Object identifying method in a kind of picture based on factor graph model | |
| CN110472495A (en) | A kind of deep learning face identification method based on graphical inference global characteristics | |
| CN116958729A (en) | Training of object classification model, object classification method, device and storage medium | |
| CN116977265A (en) | Training method and device for defect detection model, computer equipment and storage medium | |
| CN113505716B (en) | Training method of vein recognition model, and recognition method and device of vein image | |
| CN106570910B (en) | Based on the image automatic annotation method from coding characteristic and Neighborhood Model |
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 |