A method for automatic identification of financial voucher information
A technology for automatic identification of information and vouchers, which is applied in character recognition, neural learning methods, character and pattern recognition, etc., and can solve problems such as inability to use recognition methods and inability to achieve better recognition
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0041] A method for automatic recognition of financial voucher information, the image analysis module extracts image feature information from the image information of the paper financial voucher, and then the image analysis module analyzes the image feature information to obtain data information, and the data information is electronically stored;
[0042] The image feature information includes: category information of paper financial vouchers, amount information of paper financial vouchers and verification information of paper financial vouchers,
[0043] In the category information identification of paper financial vouchers, the image analysis module determines the category of paper financial vouchers according to different category information corresponding to different types of paper financial vouchers;
[0044] In the identification of amount information for paper-based financial vouchers, the image analysis module completes the extraction of image feature information throu...
Embodiment 2
[0063] Embodiment 2: A method for automatic identification of financial voucher information, its principle and implementation method are basically the same as in Embodiment 1, the difference is that: the sizes of the several sub-image areas described are all equal, and the several sub-image areas combine the image The region is divided horizontally or vertically; the error correction analysis sub-steps are specifically:
[0064] Sub-step a, for a single sub-image area, find the first area in each numerical information that is equal in size to the single sub-image area and has the highest confidence, record the first area and its confidence, and the corresponding confidence of all numerical information Among them, the highest confidence degree is determined, and the numerical information corresponding to the highest confidence degree is the candidate numerical information;
[0065] Sub-step b, select a sub-image area adjacent to a single sub-image area, find a second area in th...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

