Sequence segmentation method of bill seal area

A region and seal technology, which is applied in the field of bill seal region sequence segmentation, can solve the problem of difficult recognition and recognition effect of the seal region, and achieve the effect of meeting business needs and improving recognition accuracy

Inactive Publication Date: 2018-01-19
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF5 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a method for segmenting the region sequence of b

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
  • Sequence segmentation method of bill seal area
  • Sequence segmentation method of bill seal area
  • Sequence segmentation method of bill seal area

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] In order to accurately segment the outer ring area of ​​the bill seal, the embodiment first finds the seal area from the bill, and then transforms the target area into a standard rectangular area by means of area transformation.

[0035] Because the stamp area is generally elliptical, in order to accurately locate and segment the stamp area in the image, the present invention adopts a fast ellipse detection method, which can quickly and effectively detect the stamp area in the image, so as to Meet the real-time requirements of actual image recognition. The specific plan is as follows:

[0036] First extract arcs from the edges of ellipses and cluster them into 4 classes according to their convexity. According to the gradient direction and 8 connected edge pixels in the same direction form an arc. And improve the quality of constructed arcs by removing shorter length arcs and straight arcs. Then assign the clustered arcs to four different quadrants, here we use three ...

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 relates to the field of financial bill processing, and discloses a sequence segmentation method of a bill seal area in order to solve the problem that during OCR, the seal area is difficult to recognize or poor in recognition effect. The method comprises the steps that an ellipse detection method is utilized to quickly and effectively defect the seal area in an image so as to meet the instantaneity requirements for actual image recognition, and after the seal area is positioned, an irregular sequence of the seal area needs to be segmented. In the method, the area transformation method is adopted, and the target sequence in the seal area is transformed into a regular rectangular area. The method is suitable for the sequence segmentation of a financial bill.

Description

technical field [0001] The invention relates to the field of financial bill processing, in particular to a method for segmenting the region sequence of bill seals. Background technique [0002] In recent years, the development of AI technology has advanced by leaps and bounds, and its application fields have become wider and wider, such as robotics, speech recognition, image recognition, computer vision, automatic driving and other fields. In terms of image recognition, OCR recognition based on deep learning is widely used in the industry due to its high recognition accuracy and fast recognition speed. However, the OCR recognition accuracy is not only limited by the quality of the recognition algorithm, but the image preprocessing part also plays a decisive role. effect. When using deep learning to do sequence-based OCR recognition, how to quickly and accurately segment each sequence in the image is the first problem people have to solve. [0003] In OCR bill 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
IPC IPC(8): G06T7/11G06T7/13
Inventor 池明辉牛小明肖欣庭刘东唐军
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap