Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Identifying method for fragmentary printed digits

A digital character and recognition method technology, applied in the field of character recognition, can solve the problems of incomplete character deformation, powerlessness, distortion, reduction of character structure primitives, etc.

Inactive Publication Date: 2005-02-23
SHANGHAI JIAO TONG UNIV
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The technology involved in this article mainly has the following defects and deficiencies: (1) the algorithm is only suitable for handwritten character recognition, although it can effectively overcome the deformation of handwritten characters, it is powerless for the deformation of incomplete characters; (2) the loss of strokes of incomplete characters will Reduce the original structural primitives of characters; (3) The strokes of incomplete characters are lost and the original structural primitives of characters will be changed at the same time, so that distortion occurs when the primitive features are described by statistical methods; (4) Neural network recognition The method must determine the dimensionality of the input feature vector in advance, but the degree of incompleteness of the incomplete characters will affect the dimensionality of the feature vector

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
  • Identifying method for fragmentary printed digits
  • Identifying method for fragmentary printed digits
  • Identifying method for fragmentary printed digits

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0078] Such as figure 1 As shown, it is a schematic diagram of the outline definition of the present invention, wherein the overall outline of the character is decomposed into four directions of outline features of top, bottom, left and right for description. When the bottom contour is damaged, the top features will not be affected, and some valuable information can be extracted from the contour features on the left and right sides.

[0079] The left contour (LP(k), k=1, 2, . . . M) is defined as the horizontal coordinate value of the leftmost boundary pixel of the character.

[0080] LP(i)=min{x|P(x,y)∈C,y=i}i=1, 2...M

[0081] In the formula, P(x, y) represents the pixel point whose coordinates are (x, y) in the image, and C represents the collection of character pixel points. Similarly, the right contour (RP(k), k=1, 2, . . . M) is defined as the horizontal coordinate value of the rightmost boundary pixel of the character.

[0082] RP(i)=max{x|P(x...

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

A method for identifying incomplete print hand of digital character includes dividing complete character to be four local contours of left, right, top and bottom, using coordinate set to present contour and carrying out discrete differentiation to position coordinate of counter picture element, integrating stroke number, contour structural features for setting up digital character model, applying structural statement method to identify incomplete digital character.

Description

technical field [0001] The invention relates to a character recognition method, in particular to a recognition method for incomplete printed digital characters. used in the field of image recognition. Background technique [0002] In recent years, character recognition technology has been widely used in various engineering fields, and the research industry of character recognition has made great achievements. The correct rate of recognition of printed characters is as high as 99%. However, some incomplete characters exist in practical applications, and the incomplete characters and complete characters are mixed together, which makes text recognition difficult. [0003] After literature search, it was found that "Combining statistical and structural approaches for handwritten character description" published by Pasquale Foggia et al. in "Image and Vision Computing" (1999, 17(9), 701-711.) ("Image and Visual Computer") ("Description of Handwritten Characters Combining Statis...

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): G06K9/72
Inventor 胡小锋叶庆泰徐榕
Owner SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com