Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method for recognizing print hand Arabic alphabets based on boundary characteristic

A boundary feature and recognition method technology, applied in the field of optical character recognition, can solve the problems of slow recognition speed, slow algorithm speed, unequal width of four forms, etc., and achieve the feature extraction process is simple and clear, easy to implement, and fast algorithm speed Effect

Inactive Publication Date: 2009-05-27
HARBIN ENG UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 2. There are no vowels in Arabic, and vowels are reflected by marking auxiliary characters called "moving symbols" on consonants
[0006] 4. The width of the letters is not equal, not only the width of different letters may be different, but also the four forms of a certain letter are not equal in width;
Among these methods, although the recognition methods based on image density and moment-invariant features are relatively simple, the algorithm speed is slow, and these methods do not make full use of the rich shape features of Arabic letters; the recognition method based on primitive features requires a refinement process, Its recognition speed is slow, and at the same time, due to the complex structure of Arabic letters, there will be breaks, burrs and other phenomena during the thinning process, resulting in a low recognition rate of this method

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
  • Method for recognizing print hand Arabic alphabets based on boundary characteristic
  • Method for recognizing print hand Arabic alphabets based on boundary characteristic
  • Method for recognizing print hand Arabic alphabets based on boundary characteristic

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be further described below in conjunction with accompanying drawing and specific embodiment:

[0018] combine Figure 1-Figure 4 , where HW is the letter aspect ratio, W is the letter width, H is the letter height, LN 1 is the number of wave elements in the left boundary, LN 2 is the number of wave elements in the upper boundary, LN 3 is the number of wave elements in the right boundary, LN 4 is the number of wave elements in the lower boundary, SN 1 is the number of zero straight lines in the left boundary, SN 2 is the number of zero straight lines in the upper boundary, SN 3 is the number of zero straight lines in the right boundary, SN 4 is the number of zero straight lines in the lower boundary, SL 31 is the length of the first zero straight line in the right boundary, SL 41 is the length of the first zero line in the lower boundary, MSL 2 is the length of the longest zero line in the upper boundary, MSL 3 is the length of the lo...

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 provides a print-form Arabic alphabet identification method based on boundary characteristic, wherein the upside, downside, left and right boundaries is regarded as a wave, each boundary is regarded as an assembly of a series of wave elements, and the following boundary characteristics are extracted therefrom: the number of the component wave, the number of the zero line, the length of the first zero line in the right boundary, the length of the first zero line in the downside boundary, the length of the longest zero line in the upside boundary, the length of the longest zero line in the right boundary, the length of the longest zero line in the upside boundary, the length of the longest zero line in the downside boundary and the number of the positive line in the upside boundary, moreover, the height width ratio of the alphabets and the alphabet auxiliary part are involved as the identification characteristics, finally, each print-form Arabic alphabet is identified by using four decision trees according to the four kinds of formats of the alphabets-the independent, the beginning, the middle and the end.

Description

(1) Technical field [0001] The invention relates to an optical character recognition method, in particular to a printed Arabic letter recognition method. (2) Background technology [0002] Among various languages ​​and characters, Arabic is one of the most widely used characters. Including the letter Lam-Alif, there are 29 Arabic alphabets. Simply put, the Arabic alphabet has the following characteristics: [0003] 1. Each Arabic letter has 2 to 4 different forms according to different positions in the word, which are independent, beginning, middle and end forms; [0004] 2. There are no vowels in Arabic, and vowels are reflected by marking auxiliary characters called "moving symbols" on consonants. In Arabic, there are two "movements" for vowels, namely Hamaza and Madda; [0005] 3. The letters Lam and the letters Alif can be connected together to form a new letter Lam-Alif; [0006] 4. The width of the letters is not equal, not only the width of different letters may ...

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): G06K9/72
Inventor 郑丽颖田凯唐降龙
Owner HARBIN ENG 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
Eureka Blog
Learn More
PatSnap group products