CN112507895A - Method and device for automatically classifying qualification certificate files based on big data analysis - Google Patents
Method and device for automatically classifying qualification certificate files based on big data analysis Download PDFInfo
- Publication number
- CN112507895A CN112507895A CN202011465009.1A CN202011465009A CN112507895A CN 112507895 A CN112507895 A CN 112507895A CN 202011465009 A CN202011465009 A CN 202011465009A CN 112507895 A CN112507895 A CN 112507895A
- Authority
- CN
- China
- Prior art keywords
- qualification
- image
- neural network
- image block
- clustering center
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012797 qualification Methods 0.000 title claims abstract description 77
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000007405 data analysis Methods 0.000 title claims abstract description 22
- 238000013528 artificial neural network Methods 0.000 claims abstract description 45
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 230000006870 function Effects 0.000 claims description 43
- 238000000605 extraction Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000002087 whitening effect Effects 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 6
- 230000001632 homeopathic effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- 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
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to the technical field of bid inviting purchase management, and provides a method and a device for automatically classifying qualification certificate files based on big data analysis, which are used for solving the classification problem of the qualification files. The invention provides a method for automatically classifying qualification certificate files based on big data analysis, which comprises the following steps: collecting images according to the qualification types; dividing the acquired image into a plurality of image blocks to obtain preprocessed image blocks; parallelizing a K-means algorithm, taking the preprocessed image block information as input, and extracting a dictionary; after a dictionary is extracted, mapping the preprocessed image block information into a new feature expression to obtain input information; training a neural network to obtain a trained qualification image recognition neural network; and acquiring qualification images in the bidding documents to be identified, and inputting the qualification images to identify the neural network for classification. The method improves the classification efficiency of the qualification pictures, greatly improves the accuracy of the evaluation of the suppliers, and improves the speed of tender purchase.
Description
Technical Field
The invention relates to the technical field of bid inviting purchase management, in particular to a method and a device for automatically classifying qualification certificate files based on big data analysis.
Background
According to the overall requirements of 'notice on the analysis table of advanced bidding management reform tasks of the issuing company' of the file No. 2019 of the radio and television enterprise '8', intelligent recommendation, risk analysis and intelligent early warning are realized by utilizing the technologies of supplier data reconstruction and the like, the high compliance efficiency of the selected suppliers for bidding purchase is ensured, and the risks of performing and auditing caused by the self risks of the suppliers in the purchasing process are prevented.
In the tendering procurement process, a bidder needs to provide a large number of scanned documents of qualification documents, and the tenderer needs to classify a large number of qualification documents to evaluate suppliers, but the method for classifying the qualification documents is lacked at present.
Disclosure of Invention
The technical problem solved by the invention is the classification problem of the qualification documents, and provides a method for automatically classifying the qualification certificate documents based on big data analysis.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
a method for automatically classifying qualification certificate files based on big data analysis comprises the following steps:
acquiring qualification types required by tender purchase, and acquiring images according to the qualification types, wherein each qualification type acquires at least one image;
dividing the acquired image into a plurality of image blocks, and performing regularization and whitening processing on each image block to remove interference information and retain key information to obtain a preprocessed image block;
parallelizing a K-means algorithm, taking the preprocessed image block information as input, and extracting a dictionary;
after a dictionary is extracted, a feature mapping function is constructed, and preprocessed image block information is mapped into a new feature expression to obtain input information;
inputting input information into a neural network for training, constructing a loss function, and obtaining a trained qualification image recognition neural network by taking the minimum loss function as a target and enabling a homeopathic function to be smaller than a training threshold;
obtaining a qualification image in a bidding document to be identified, carrying out image block division, regularization and whitening treatment, then carrying out feature extraction, and inputting the qualification image into a qualification image identification neural network for classification.
A large number of image blocks are generated after the qualification pictures are preprocessed, the features are extracted by adopting a clustering algorithm, and then the extracted features are input into a neural network for training to obtain the neural network, so that the qualification pictures can be effectively classified.
The method improves the classification efficiency of the qualification pictures, greatly improves the accuracy of the evaluation of the suppliers, and improves the speed of tender purchase.
Preferably, the dictionary extraction process is as follows: taking the preprocessed image block as the input of the Map nodes, initializing a clustering center, reading the preprocessed image block data in parallel by a plurality of Map nodes, calculating elements distributed to each clustering center, counting all the elements of each category on Reduce nodes, recalculating a new clustering center, comparing whether the change of the new clustering center and the previous clustering center is smaller than a set threshold value, if so, finishing iteration, outputting the clustering center, otherwise, updating the clustering center, and restarting a new iteration process.
Preferably, the method for mapping the preprocessed image block information into a new feature expression includes:
and parallelly distributing the dictionary to a plurality of Map nodes, simultaneously inputting a new label-free image data set to each Map node, performing feature learning on the image data set on the Map nodes, and performing feature mapping on the input image data to obtain new feature expression. After the clustering algorithm is used for processing, new features are obtained and used for neural network classification, so that the accuracy of qualification picture classification can be effectively improved.
Preferably, the loss function is:
where N =1,2, … … N, N representing the total number of samples per category, K =1,2 … … K, K representing the number of categories,
the activation function value of the nth sample calculated by the image recognition neural network is represented in the k-th case,
indicating the probability that the nth sample is of class k,
a value representing a first loss calculation parameter,
represents a second loss calculation parameter value, R () represents regularization, W represents a network parameter of the image recognition neural network,
another network parameter of the neural network is identified for the image.
Preferably, the
Is a softmax function.
An apparatus for automatically categorizing a qualification certificate file based on big data analysis, comprising:
the image acquisition module acquires qualification types required by tender purchase and acquires images according to the qualification types, and each qualification type acquires at least one image;
the image processing device comprises a preprocessing module, a processing module and a processing module, wherein the preprocessing module divides an acquired image into a plurality of image blocks, and carries out regularization and whitening processing on each image block to remove interference information and keep key information to obtain a preprocessed image block;
the clustering module parallelizes the K-means algorithm, takes the preprocessed image block information as input, and extracts the dictionary;
the feature extraction module is used for constructing a feature mapping function after the dictionary is extracted by the feature extraction module, and mapping the preprocessed image block information into a new feature expression to obtain input information;
the training module inputs input information into the neural network for training, constructs a loss function, and obtains a qualified image recognition neural network after training by taking the minimum loss function as a target and enabling a homeopathic function to be smaller than a training threshold;
and the classification module acquires the qualification images in the bid documents to be identified, performs image block division, regularization and whitening treatment, performs feature extraction, and inputs the qualification images into a qualification image identification neural network for classification.
Preferably, the method for extracting the dictionary by the clustering module comprises the following steps:
taking the preprocessed image block as the input of the Map nodes, initializing a clustering center, reading the preprocessed image block data in parallel by a plurality of Map nodes, calculating elements distributed to each clustering center, counting all the elements of each category on Reduce nodes, recalculating a new clustering center, comparing whether the change of the new clustering center and the previous clustering center is smaller than a set threshold value, if so, finishing iteration, outputting the clustering center, otherwise, updating the clustering center, and restarting a new iteration process.
Preferably, the method for mapping the preprocessed image block information into the new feature expression by the feature extraction module includes:
and parallelly distributing the dictionary to a plurality of Map nodes, simultaneously inputting a new label-free image data set to each Map node, performing feature learning on the image data set on the Map nodes, and performing feature mapping on the input image data to obtain new feature expression.
Preferably, the loss function constructed by the training module is:
where N =1,2, … … N, N representing the total number of samples per category, K =1,2 … … K, K representing the number of categories,
the activation function value of the nth sample calculated by the image recognition neural network is represented in the k-th case,
indicating the probability that the nth sample is of class k,
a value representing a first loss calculation parameter,
represents a second loss calculation parameter value, R () represents regularization, W represents a network parameter of the image recognition neural network,
another network parameter of the neural network is identified for the image.
Preferably, the loss function constructed by the training module
Is a softmax function.
Compared with the prior art, the invention has the beneficial effects that: the method improves the classification efficiency of the qualification pictures, greatly improves the accuracy of the evaluation of the suppliers, and improves the speed of tender purchase.
Drawings
Fig. 1 is a schematic diagram of a method for automatically categorizing a qualification certificate file based on big data analysis.
Fig. 2 is a schematic diagram of an apparatus for automatically categorizing a qualification certificate file based on big data analysis.
Detailed Description
The following examples are further illustrative of the present invention and are not intended to be limiting thereof.
A method for automatically categorizing a qualification certificate file based on big data analysis, in some embodiments of the present application, comprising:
s100, acquiring qualification types required by tender purchase, and acquiring images according to the qualification types, wherein each qualification type acquires at least one image;
s200, dividing the acquired image into a plurality of image blocks, and performing regularization and whitening processing on each image block to remove interference information and retain key information to obtain a preprocessed image block;
s300, parallelizing a K-means algorithm, taking the preprocessed image block information as input, and extracting a dictionary;
s400, after a dictionary is extracted, a feature mapping function is constructed, and preprocessed image block information is mapped into a new feature expression to obtain input information;
s500, inputting input information into a neural network for training, constructing a loss function, and obtaining a qualification image recognition neural network after training by taking the minimum loss function as a target until a homeopathic function is smaller than a training threshold value;
s600, obtaining a qualification image in the bidding document to be identified, carrying out image block division, regularization and whitening, then carrying out feature extraction, and inputting the qualification image into a qualification image identification neural network for classification.
A large number of image blocks are generated after the qualification pictures are preprocessed, the features are extracted by adopting a clustering algorithm, and then the extracted features are input into a neural network for training to obtain the neural network, so that the qualification pictures can be effectively classified.
The method improves the classification efficiency of the qualification pictures, greatly improves the accuracy of the evaluation of the suppliers, and improves the speed of tender purchase.
In some embodiments of the present application, the dictionary extraction process is: taking the preprocessed image block as the input of the Map nodes, initializing a clustering center, reading the preprocessed image block data in parallel by a plurality of Map nodes, calculating elements distributed to each clustering center, counting all the elements of each category on Reduce nodes, recalculating a new clustering center, comparing whether the change of the new clustering center and the previous clustering center is smaller than a set threshold value, if so, finishing iteration, outputting the clustering center, otherwise, updating the clustering center, and restarting a new iteration process.
In some embodiments of the present application, a method for mapping the preprocessed image block information into a new feature expression includes:
and parallelly distributing the dictionary to a plurality of Map nodes, simultaneously inputting a new label-free image data set to each Map node, performing feature learning on the image data set on the Map nodes, and performing feature mapping on the input image data to obtain new feature expression.
After the clustering algorithm is used for processing, new features are obtained and used for neural network classification, so that the accuracy of qualification picture classification can be effectively improved.
In some embodiments of the present application, the loss function is:
where N =1,2, … … N, N representing the total number of samples per category, K =1,2 … … K, K representing the number of categories,
the activation function value of the nth sample calculated by the image recognition neural network is represented in the k-th case,
indicating the probability that the nth sample is of class k,
a value representing a first loss calculation parameter,
represents a second loss calculation parameter value, R () represents regularization, W represents a network parameter of the image recognition neural network,
another network parameter of the neural network is identified for the image.
In some embodiments of the present application, the
Is a softmax function.
An apparatus for automatically categorizing a certification document based on big data analysis, in some embodiments of the present application, comprises:
the system comprises an image acquisition module 100, wherein the image acquisition module 100 acquires qualification types of tender purchase requirements, and acquires images according to the qualification types, and each qualification type acquires at least one image;
the image processing device comprises a preprocessing module 200, wherein the preprocessing module 200 divides an acquired image into a plurality of image blocks, and regularizes and whitens each image block to remove interference information and retain key information to obtain a preprocessed image block;
the clustering module 300 parallelizes the K-means algorithm, and extracts the dictionary by taking the preprocessed image block information as input;
the feature extraction module 400, after extracting the dictionary, constructs a feature mapping function, and maps the preprocessed image block information into a new feature expression to obtain input information by the feature extraction module 400;
the training module 500 inputs the input information into the neural network for training, constructs a loss function, and obtains a trained qualification image recognition neural network by taking the minimum loss function as a target and enabling the homeopathic function to be smaller than a training threshold;
and the classification module 600 acquires the qualification images in the bid documents to be identified, performs image block division, regularization and whitening processing, performs feature extraction, and inputs the qualification images into a qualification image identification neural network for classification.
In some embodiments of the present application, the method for extracting a dictionary by the clustering module includes:
taking the preprocessed image block as the input of the Map nodes, initializing a clustering center, reading the preprocessed image block data in parallel by a plurality of Map nodes, calculating elements distributed to each clustering center, counting all the elements of each category on Reduce nodes, recalculating a new clustering center, comparing whether the change of the new clustering center and the previous clustering center is smaller than a set threshold value, if so, finishing iteration, outputting the clustering center, otherwise, updating the clustering center, and restarting a new iteration process.
In some embodiments of the present application, the method for mapping the preprocessed image block information into a new feature expression by the feature extraction module is as follows:
and parallelly distributing the dictionary to a plurality of Map nodes, simultaneously inputting a new label-free image data set to each Map node, performing feature learning on the image data set on the Map nodes, and performing feature mapping on the input image data to obtain new feature expression.
In some embodiments of the present application, the loss function constructed by the training module is:
where N =1,2, … … N, N representing the total number of samples per category, K =1,2 … … K, K representing the number of categories,
the activation function value of the nth sample calculated by the image recognition neural network is represented in the k-th case,
indicating the probability that the nth sample is of class k,
a value representing a first loss calculation parameter,
represents a second loss calculation parameter value, R () represents regularization, W represents a network parameter of the image recognition neural network,
another network parameter of the neural network is identified for the image.
In some embodiments of the present application, the training module constructs a loss function
Is a softmax function.
The above detailed description is specific to possible embodiments of the present invention, and the above embodiments are not intended to limit the scope of the present invention, and all equivalent implementations or modifications that do not depart from the scope of the present invention should be included in the present claims.
Claims (10)
1. A method for automatically classifying qualification certificate files based on big data analysis is characterized by comprising the following steps:
acquiring qualification types required by tender purchase, and acquiring images according to the qualification types, wherein each qualification type acquires at least one image;
dividing the acquired image into a plurality of image blocks, and performing regularization and whitening processing on each image block to remove interference information and retain key information to obtain a preprocessed image block;
parallelizing a K-means algorithm, taking the preprocessed image block information as input, and extracting a dictionary;
after a dictionary is extracted, a feature mapping function is constructed, and preprocessed image block information is mapped into a new feature expression to obtain input information;
inputting input information into a neural network for training, constructing a loss function, and obtaining a trained qualification image recognition neural network by taking the minimum loss function as a target and enabling a homeopathic function to be smaller than a training threshold;
obtaining a qualification image in a bidding document to be identified, carrying out image block division, regularization and whitening treatment, then carrying out feature extraction, and inputting the qualification image into a qualification image identification neural network for classification.
2. The method for automatically categorizing qualification certificate files based on big data analysis according to claim 1, wherein the dictionary extraction process is as follows: taking the preprocessed image block as the input of the Map nodes, initializing a clustering center, reading the preprocessed image block data in parallel by a plurality of Map nodes, calculating elements distributed to each clustering center, counting all the elements of each category on Reduce nodes, recalculating a new clustering center, comparing whether the change of the new clustering center and the previous clustering center is smaller than a set threshold value, if so, finishing iteration, outputting the clustering center, otherwise, updating the clustering center, and restarting a new iteration process.
3. The method for automatically classifying qualification certificate files based on big data analysis according to claim 1, wherein the method for mapping the preprocessed image block information into a new feature expression comprises:
and parallelly distributing the dictionary to a plurality of Map nodes, simultaneously inputting a new label-free image data set to each Map node, performing feature learning on the image data set on the Map nodes, and performing feature mapping on the input image data to obtain new feature expression.
4. The method for automatically categorizing a certification document based on big data analysis of claim 2, wherein the loss function is:
where N =1,2, … … N, N representing the total number of samples per category, K =1,2 … … K, K representing the number of categories,
the activation function value of the nth sample calculated by the image recognition neural network is represented in the k-th case,
indicating the probability that the nth sample is of class k,
a value representing a first loss calculation parameter,
represents a second loss calculation parameter value, R () represents regularization, W represents a network parameter of the image recognition neural network,
another network parameter of the neural network is identified for the image.
5. The method for automatically categorizing a certification document based on big data analysis of claim 1, wherein the method further comprises the step of automatically categorizing the certification document based on big data analysis
Is a softmax function.
6. Device based on big data analysis automatic classification qualification certificate file, its characterized in that includes:
the image acquisition module acquires qualification types required by tender purchase and acquires images according to the qualification types, and each qualification type acquires at least one image;
the image processing device comprises a preprocessing module, a processing module and a processing module, wherein the preprocessing module divides an acquired image into a plurality of image blocks, and carries out regularization and whitening processing on each image block to remove interference information and keep key information to obtain a preprocessed image block;
the clustering module parallelizes the K-means algorithm, takes the preprocessed image block information as input, and extracts the dictionary;
the feature extraction module is used for constructing a feature mapping function after the dictionary is extracted by the feature extraction module, and mapping the preprocessed image block information into a new feature expression to obtain input information;
the training module inputs input information into the neural network for training, constructs a loss function, and obtains a qualified image recognition neural network after training by taking the minimum loss function as a target and enabling a homeopathic function to be smaller than a training threshold;
and the classification module acquires the qualification images in the bid documents to be identified, performs image block division, regularization and whitening treatment, performs feature extraction, and inputs the qualification images into a qualification image identification neural network for classification.
7. The apparatus for automatically categorizing qualification certificate files based on big data analysis of claim 6, wherein the clustering module extracts dictionaries by a method comprising:
taking the preprocessed image block as the input of the Map nodes, initializing a clustering center, reading the preprocessed image block data in parallel by a plurality of Map nodes, calculating elements distributed to each clustering center, counting all the elements of each category on Reduce nodes, recalculating a new clustering center, comparing whether the change of the new clustering center and the previous clustering center is smaller than a set threshold value, if so, finishing iteration, outputting the clustering center, otherwise, updating the clustering center, and restarting a new iteration process.
8. The apparatus for automatically classifying qualification certificate files based on big data analysis according to claim 6, wherein the method for mapping the preprocessed image block information into the new feature expression by the feature extraction module comprises:
and parallelly distributing the dictionary to a plurality of Map nodes, simultaneously inputting a new label-free image data set to each Map node, performing feature learning on the image data set on the Map nodes, and performing feature mapping on the input image data to obtain new feature expression.
9. The apparatus for automatically categorizing qualification certificate files based on big data analysis of claim 6, wherein the loss function constructed by the training module is:
where N =1,2, … … N, N representing the total number of samples per category, K =1,2 … … K, K representing the number of categories,
the activation function value of the nth sample calculated by the image recognition neural network is represented in the k-th case,
indicating the probability that the nth sample is of class k,
a value representing a first loss calculation parameter,
represents a second loss calculation parameter value, R () represents regularization, W represents a network parameter of the image recognition neural network,
another network parameter of the neural network is identified for the image.
10. The apparatus according to claim 6, wherein the training module constructs a loss function
Is a softmax function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011465009.1A CN112507895A (en) | 2020-12-14 | 2020-12-14 | Method and device for automatically classifying qualification certificate files based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011465009.1A CN112507895A (en) | 2020-12-14 | 2020-12-14 | Method and device for automatically classifying qualification certificate files based on big data analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112507895A true CN112507895A (en) | 2021-03-16 |
Family
ID=74972300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011465009.1A Pending CN112507895A (en) | 2020-12-14 | 2020-12-14 | Method and device for automatically classifying qualification certificate files based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112507895A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673849A (en) * | 2021-08-09 | 2021-11-19 | 唐山鑫正工程项目管理有限公司 | Engineering bidding management method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955707A (en) * | 2014-05-04 | 2014-07-30 | 电子科技大学 | Mass image sorting system based on deep character learning |
| CN104933445A (en) * | 2015-06-26 | 2015-09-23 | 电子科技大学 | Mass image classification method based on distributed K-means |
| CN110837856A (en) * | 2019-10-31 | 2020-02-25 | 深圳市商汤科技有限公司 | Neural network training and target detection method, device, equipment and storage medium |
| CN111275114A (en) * | 2020-01-20 | 2020-06-12 | 黄惠芬 | Network qualification image identification method based on ensemble learning under SDN architecture |
| CN111860834A (en) * | 2020-07-09 | 2020-10-30 | 中国科学院深圳先进技术研究院 | Neural network tuning method, system, terminal and storage medium |
-
2020
- 2020-12-14 CN CN202011465009.1A patent/CN112507895A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103955707A (en) * | 2014-05-04 | 2014-07-30 | 电子科技大学 | Mass image sorting system based on deep character learning |
| CN104933445A (en) * | 2015-06-26 | 2015-09-23 | 电子科技大学 | Mass image classification method based on distributed K-means |
| CN110837856A (en) * | 2019-10-31 | 2020-02-25 | 深圳市商汤科技有限公司 | Neural network training and target detection method, device, equipment and storage medium |
| CN111275114A (en) * | 2020-01-20 | 2020-06-12 | 黄惠芬 | Network qualification image identification method based on ensemble learning under SDN architecture |
| CN111860834A (en) * | 2020-07-09 | 2020-10-30 | 中国科学院深圳先进技术研究院 | Neural network tuning method, system, terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 李涛: "基于卷积神经网络的图像分类模型的研究与应用", 《中国优秀硕士学位论文全文数据库信息科技辑》, no. 01, 15 January 2019 (2019-01-15), pages 138 - 3255 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113673849A (en) * | 2021-08-09 | 2021-11-19 | 唐山鑫正工程项目管理有限公司 | Engineering bidding management method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Kumar et al. | Image based leaf segmentation and counting in rosette plants | |
| Oo et al. | Plant leaf disease detection and classification using image processing | |
| White et al. | Generating segmentation masks of herbarium specimens and a data set for training segmentation models using deep learning | |
| JP2022027473A5 (en) | ||
| CN108764361B (en) | Working condition identification method of indicator diagram of beam-pumping unit based on integrated learning | |
| CN109815987B (en) | Crowd classification method and system | |
| CN112785441B (en) | Data processing method, device, terminal equipment and storage medium | |
| CN111401339A (en) | Method and device for identifying age of person in face image and electronic equipment | |
| CN111914902A (en) | Traditional Chinese medicine identification and surface defect detection method based on deep neural network | |
| CN116664944A (en) | Vineyard pest identification method based on attribute feature knowledge graph | |
| CN109614928B (en) | Panda face recognition method based on limited training data | |
| CN111882034A (en) | Neural network processing and face recognition method, device, equipment and storage medium | |
| CN106529490B (en) | Based on the sparse system and method for realizing writer verification from coding code book | |
| CN112507895A (en) | Method and device for automatically classifying qualification certificate files based on big data analysis | |
| CN112613341B (en) | Training method and device, fingerprint identification method and device and electronic equipment | |
| Panigrahi et al. | Evaluations of fractal geometry and invariant moments for shape classification of corn germplasm | |
| CN112508000B (en) | Method and equipment for generating OCR image recognition model training data | |
| CN113706258B (en) | Product recommendation method, device, equipment and storage medium based on combined model | |
| Khavalko et al. | Classification and Recognition of Medical Images Based on the SGTM Neuroparadigm. | |
| Lambert et al. | Automatic identification of diatom morphology using deep learning | |
| Mahalle et al. | Data Acquisition and Preparation | |
| CN114792374A (en) | Image recognition method based on texture classification, electronic device and storage medium | |
| Riyaz et al. | A Novel Prediction Analysing the False Acceptance Rate and False Rejection Rate using CNN Model to Improve the Accuracy for Iris Recognition System for Biometric Security in Clouds Comparing with Traditional Inception Model | |
| Liang et al. | FARLut: a two-stage tobacco foreign body detection model incorporating color information and attention mechanism | |
| Dhali et al. | Pattern Recognition Techniques in Image-Based Material Classification of Ancient Manuscripts |
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 |