A method and device for optical recognition of bills

A technology of optical recognition and bills, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of heavy workload, low accuracy, and time-consuming, so as to reduce workload, improve work efficiency, and high accuracy Effect

Inactive Publication Date: 2018-11-20
SICHUAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above-mentioned method of manually sorting bills is to identify the bills one by one by workers. When the number of bills is huge, relying solely on manual labor will result in a large workload, time-consuming, low efficiency, and low accuracy.

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
  • A method and device for optical recognition of bills
  • A method and device for optical recognition of bills

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] An embodiment of the present invention provides a method for optical recognition of bills, such as figure 1 shown, including:

[0048] 101. Scan the bill to be recognized, so as to input the image of the bill to be recognized.

[0049] 102. After scanning, the graphics of the to-be-recognized account bills are sorted obliquely.

[0050] 103. Use a classification algorithm to classify the bills to be identified after oblique sorting.

[0051] 104. Extract the uppercase amount font and the lowercase amount font in the bill image to be recognized after classification, and divide the uppercase amount font and the lowercase amount font into individual characters, so as to obtain the uppercase amount character image and lowercase amount character image.

[0052] 105. Convert the uppercase amount character image and the lowercase amount character image into an uppercase amount binary image and a lowercase amount binary image.

[0053] 106. Remove noise points in the upperc...

Embodiment 2

[0066] An embodiment of the present invention provides an optical recognition device for bills, such as figure 2 shown, including:

[0067] 21. A scanning unit, configured to scan the bill to be recognized, so as to input the image of the bill to be recognized.

[0068] 22. A collating unit, used for oblique sorting of the to-be-recognized chart graphics after scanning.

[0069] 23. A classification unit, configured to use a classification algorithm to classify the bills to be identified after oblique sorting.

[0070] 24. A digging unit, configured to dig out the uppercase amount font and the lowercase amount font in the bill image to be recognized after classification, and divide the uppercase amount font and the lowercase amount font into individual characters, so as to obtain uppercase An amount character image and a lowercase amount character image.

[0071] 25. A conversion unit, configured to convert the uppercase amount character image and the lowercase amount char...

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 discloses a bill optical identification method and device, relating to the automatic identification device field. The bill optical identification method and device reduce workload of arranging bills, improves working efficiency and has high accuracy. The bill optical identification method comprises steps of performing scanning, inclination arrangement and classification on bills to be identified, extracting fonts of amount in words and amount in figures, segmenting the fonts of amount in words and amount in figures into individual characters, converting character images of amount in words and amount in figures to binary images, removing noisy points, performing size normalization, extracting amount character characteristic values of the binary images of the amount in words and amount in figures, performing identification on the extracted characteristic values according to a preset characteristic value template database, obtaining an identification result after identification is finished and outputting the identification result. The bill optical identification method and device are used in the bill identification.

Description

technical field [0001] The invention relates to the field of automatic identification devices, in particular to a method and device for optical identification of bills. Background technique [0002] With the rapid development of the economy, a large number of bills are generated every day in banking, taxation and other industries. It is a heavy workload to organize and archive all the bills. Therefore, a quick bill sorting method or software has become the current Hot market demand. [0003] In the prior art, bills are generally sorted out manually, that is, workers identify, classify, count and file the bills one by one. [0004] The above-mentioned method of manually sorting bills is to use workers to identify the bills one by one. When the number of bills is large and complex, relying solely on manual labor will result in a large workload, time-consuming, low efficiency, and low accuracy. Contents of the invention [0005] The method and device for optical recognition...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G07D7/20G07D7/206
CPCG07D7/2008G07D7/2016
Inventor 李强袁熙盛小东逯峻雨林若男
Owner SICHUAN UNIV
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