A font recognition method based on sparse coding

A font recognition and sparse coding technology, which is applied in character and pattern recognition, instruments, computer parts, etc., can solve the problems that font recognition methods cannot correctly identify similar fonts, and are not particularly obvious

Inactive Publication Date: 2011-11-30
HARBIN INST OF TECH
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to solve the problem that the font recognition method relying on image features cannot correctly identify similar fonts because the differences between some fonts are not particularly obvious at the image feature level, and then provide a font based on sparse coding recognition methods

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 font recognition method based on sparse coding
  • A font recognition method based on sparse coding
  • A font recognition method based on sparse coding

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] The specific steps of the font recognition method based on sparse coding invented by this patent are:

[0010] Step 1: For each type of font in the training library, collect a certain number of grayscale images as training images, for example, 10 images. Each image is randomly divided into a certain number of squares, for example, a grayscale image of 512×512 can be divided into 1000 squares, assuming that the size of the square is d×d.

[0011] Step 2: For the k-th type of font, convert any block obtained after all training images are divided into a B=d×d-dimensional column vector, and use the column vectors corresponding to all blocks of all training images as training samples, using Independent Component Analysis (ICA) method, training a set of basis function matrices and the corresponding filter matrix in Indicates the jth basis function of the kth type font, Indicates the j-th filter representing the k-th type of font, and T represents matrix transposition;...

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 character recognizing method based on a sparse coding. The method provided by the invention takes a gray level image as an input to carry out operations of following two phases on any one image to be tested: in a training phase, the image to be tested of each character is randomly divided into a certain number of diamonds and the number of the diamonds is codetermined by the size of the image and the size of the diamond: for example, a gray level image with the size of 512*512 can be divided into 4096 diamonds with the size of 8*8. To any one type of character, the divided diamonds are used as input and a group of primary function capable of sparsely representing any diamond is trained through utilizing an independent component analyzing method and the primary functions are used as models of the characters. The method provided by the invention can recognize Chinese characters, can recognize characters of other languages and also can recognize characters of different languages. The method can be applied to automatic document analysis, article design and the like.

Description

technical field [0001] The invention relates to a font recognition method based on sparse coding, and belongs to the technical field of image processing and pattern recognition. Background technique [0002] With the rise of network office and the popularization of digital library services, people's access to and exchange of information has become more dependent on electronic documents. How to transform the information recorded in the traditional book form into electronic documents has become a basic problem to be solved by computer automatic document analysis. Font recognition is to identify the type of fonts in text images, and it is one of the important research contents in computer automatic document analysis and processing. Over the past 20 years, OCR (optical character recognition, optical character recognition) has obtained rapid development. At present, printed character recognition technology has basically matured, and the recognition rate has reached the requirem...

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 Applications(China)
IPC IPC(8): G06K9/20G06K9/62
Inventor 姚鸿勋张盛平孙鑫卢修生
Owner HARBIN INST OF TECH
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