Convolutional neural network-based credit file identification method

A convolutional neural network and recognition method technology, applied in neural learning methods, biological neural network models, neural architectures, etc., can solve problems such as the recognition of handwritten signatures that cannot be used by customers, and the lack of legal validity of documents, so as to improve the accuracy rate, recognition The effect of convenient credit file, improved robustness and generalization ability

Pending Publication Date: 2021-03-16
河北地质大学 +1
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method cannot recognize handwritten Chinese characters or numbers at present, which will cause many shortcomings in the a

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Convolutional neural network-based credit file identification method
  • Convolutional neural network-based credit file identification method
  • Convolutional neural network-based credit file identification method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0048] Embodiment Credit file identification method based on convolutional neural network

[0049] A credit file identification method based on convolutional neural network, the credit file identification flow chart is as follows figure 1 As shown, the training flow chart of its convolutional neural network model is as follows figure 2As shown, it specifically includes the following steps:

[0050] S1. After the collected credit file image is geometrically corrected by calling the affine transformation method in the opencv function library, it is then expanded by image enhancement technology. The schematic diagram of image expansion is as follows image 3 As shown, the self-made data set is obtained. The self-made data set includes 10 types of credit files, namely organization code certificate, tax registration certificate, business license, project approval documents, credit analysis report, loan application form, loan contract, financial statement, and low-voltage guarante...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of computer vision, and discloses a convolutional neural network-based credit file identification method, which comprises the steps of performing geometriccorrection on a collected credit file image, and then performing expansion through an image enhancement technology to obtain a self-made data set; constructing a convolutional neural network architecture based on a deep learning open source framework Tensorflow, and training the convolutional neural network architecture to obtain a convolutional neural network model; and scanning the credit file,and loading the scanned picture into the convolutional neural network model for identification and classification. The method is high in recognition accuracy, stronger in generalization, high in robustness, and more convenient and safer in credit file recognition, and improves the work efficiency. The method is suitable for credit file identification.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to a credit file recognition method, in particular to a credit file recognition method based on a convolutional neural network. Background technique [0002] Credit files are important documents and evidences that are formed during the credit business process of the enterprise to record and reflect the credit business. It includes relevant contracts and certificates, basic information of the borrower, and credit business information of the borrower, etc. The data shows that credit loans are still the main loan mode in my country so far, occupying 78.61% of the loan market share. According to statistical forecasts, by 2020, corporate credit will reach a scale of more than 10 trillion, and the industry has great potential for development. However, in the process of handling credit business, companies need to submit a large number of credit file paper materials to the lending ban...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/00G06N3/04G06N3/08G06Q40/02
CPCG06N3/08G06V30/40G06V30/413G06N3/045G06Q40/03
Inventor 李明亮许雷周沛松
Owner 河北地质大学
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products