Method for identifying digits in blurred images based on blur classifier

A fuzzy image and fuzzy classification technology, applied in image data processing, character and pattern recognition, image enhancement, etc.

Inactive Publication Date: 2013-11-27
NANJING UNIV OF POSTS & TELECOMM
View PDF1 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 provide an off-line recognition method for fuzzy English numerals based on a fuzzy classifier and an implementation process, which are used to solve the problem that the accuracy and versatility of the off-line recognition of fuzzy numbers need to be further improved

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 identifying digits in blurred images based on blur classifier
  • Method for identifying digits in blurred images based on blur classifier
  • Method for identifying digits in blurred images based on blur classifier

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] For the convenience of description, we assume the following application example: There are 500 fuzzy grayscale images each containing 1 number, from which 8 images with more positive and normal numbers are selected for each number as training samples, and the rest are used as test samples. A fuzzy classifier is constructed by using the training samples, and digit recognition is performed on the test samples.

[0044] The specific embodiment of the present invention is:

[0045] Step 1. Construct fuzzy classifier, comprise feature selection and determine the required parameter of classifier, concrete steps are as follows:

[0046] Step (1) Firstly select a number of relatively standardized grayscale images as training samples for numbers 0 to 9, and calculate the features of each known number image according to the following steps:

[0047] Step (11) Adaptive binarization of grayscale images: find the two grayscale values ​​c1 and c2 with the highest frequency of occurr...

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 method for identifying digits in blurred images based on a blur classifier. The method is suitable for identifying the digits in degraded images. The method includes the steps that the degree of truth value that characters in each image are the digits is distinguished according to the distribution characteristics of foreground pixels and external features of the digits, slight slant of the images can be tolerated, the digits in the images can be identified through comprehensive judgment, and the identifying accuracy is high. The method can automatically set parameters needed by the blur classifier based on characteristic value distribution of a small number of training samples, and multi-feature distinguishing and automatic setting of the parameters enable the method to have good universality. The method effectively solves the problems that the accuracy of an existing digit identifying method aiming at the blurred images needs to be improved, and a large number of training samples are needed.

Description

technical field [0001] The invention relates to the fields of pattern recognition and image processing, in particular to a method for off-line recognition of fuzzy numbers by using a fuzzy classifier based on intermediary truth measurement. Background technique [0002] Offline digit recognition is the process of recognizing digits in images. Digit recognition is a hot research problem in pattern recognition, and there are many practical applications that require offline recognition of digits, such as automatic recognition of license plates, automatic recognition of zip codes on envelopes, form processing, automatic recognition of check digits, etc. Digital recognition generally includes preprocessing of input images, feature extraction, feature selection, classification based on various classifiers, and post-processing, among which commonly used classifiers are HMM (Hidden Markov Model), SVM (Support Vector Machine) , k-NN (k nearest neighbor), etc., post-processing is use...

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): G06K9/66G06T5/00
Inventor成卫青洪龙杨庚唐旋
OwnerNANJING UNIV OF POSTS & TELECOMM