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

Handwritten Uyghur character recognition method based on classifier integration

A technology of character recognition and classification recognition, which is applied in the fields of handwriting recognition, handwritten Uyghur character recognition, and text recognition. noise effect

Inactive Publication Date: 2012-08-01
XIDIAN UNIV
View PDF1 Cites 26 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] At present, there are few studies on Uyghur single-character recognition of 128 categories, and the recognition rate is generally low

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
  • Handwritten Uyghur character recognition method based on classifier integration
  • Handwritten Uyghur character recognition method based on classifier integration
  • Handwritten Uyghur character recognition method based on classifier integration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] A kind of handwritten Uyghur character recognition method based on classifier integration of the present invention, see figure 1 : The handwritten Uyghur character recognition process includes:

[0053] Step 1 preprocesses the collected handwritten Uyghur characters, removes the additional noise in the process of collecting Uyghur characters, and obtains standardized Uyghur characters. The Uyghur character preprocessing process includes:

[0054] 1.1 Crop the handwritten Uyghur character image, remove the area that does not contain the text track point in the Uyghur character image, and leave the area that contains the text track point.

[0055] 1.2 Normalize the cropped Uyghur characters, and normalize Uyghur character images of different sizes into images of the same size.

[0056] 1.3 Resampling the trajectory points of the normalized Uyghur character image, sampling every few points, sampling every 3 points in this example, if there are pixels in the original imag...

Embodiment 2

[0079] The handwritten Uyghur character recognition method based on classifier integration is the same as that in Embodiment 1, and the present invention will be described in more detail in conjunction with the specific recognition process. Algorithm of the present invention such as figure 1 As shown, it mainly includes five parts: preprocessing, feature extraction, MQDF classifier, BP neural network classifier, and classifier integration.

[0080] The first part, preprocessing. The preprocessing of Uyghur characters consists of four parts, namely cropping, normalization, trajectory point resampling, and filtering.

[0081] (1) Save the trajectory points of the handwritten Uyghur characters collected on the mobile phone to form a Uyghur character image, such as Figure 4 as shown, Figure 4 The first three lines are all handwritten Uyghur characters, and the fourth line is the corresponding printed version of the Uyghur characters.

[0082] Crop the collected Uyghur charac...

Embodiment 3

[0106] The handwritten Uyghur character recognition method based on classifier integration is the same as that of Embodiment 1-2. The performance of the handwritten Uyghur character recognition system of the present invention can be further illustrated by the following experimental tests.

[0107] This experimental test is done on a personal computer with Intel Core 2 Duo T6400 processor, 2GB memory, and 2GHZ main frequency. The experiment adopts the handwritten Uyghur character set of the Intelligent Signal Processing and Pattern Recognition Laboratory of Xidian University. The character set data is collected using the mobile terminal mobile phone platform, which is written by Uyghur people without any writing restrictions, which ensures the accuracy and accuracy of the samples. For practical value, the character set contains 128 character classes, and each character class has 115 sets. 60 sets of them are selected as training samples, and the remaining 55 sets are used as rec...

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 discloses a handwritten Uyghur character recognition method based on classifier integration, which belongs to the pattern recognition field and includes steps of: pre-processing handwritten Uyghur characters, extracting feature vectors of the Uyghur characters by aid of directional line elements, respectively using a modified quadratic discriminant function (MODF) classifier and a back propagation (BP) neural network classifier to classify the feature vectors of the Uyghur characters, and integrating classification recognition results, namely an MODF confidence value set and a BP neural network confidence value set, wherein the step of integrating especially includes achieving integrating through the weighted sum of two confidence values to obtain a final confidence value set and selecting the maximum confidence value to serve as the recognition result. Two classifiers are used in the method, and recognition rate is improved due to result integrating. The handwritten Uyghur character recognition method based on classifier integration has the advantages of being good in algorithm performance, strong in instantaneity, high in reliability and high in recognition rate, is mainly applied to a mobile platform, namely a cell phone, to achieve handwritten Uyghur character recognition, lays a foundation for Uyghur character informatization processing, and provides a new method and an application way for Uyghur character cultural exchange.

Description

technical field [0001] The invention belongs to the technical field of character recognition in pattern recognition, and mainly relates to the field of handwriting recognition, in particular to the field of handwritten Uyghur character recognition, specifically a handwritten Uyghur character recognition method based on classifier integration, which is used for mobile platform i.e. The handwriting input of Uyghur characters is realized on the mobile phone. Background technique [0002] The Uyghur language is one of the main languages ​​used for communication and work of the Uyghur people in Xinjiang. It belongs to the Turkic language family of the Altaic language family and is a cohesive phonetic alphabet. The current Uyghur language has a total of 32 letters, including 8 vowels and 24 consonants. According to the position in the word, each letter has a front connection type, a back connection type, a double connection type, a single vertical type, etc. 2 to 8 writing forms,...

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): G06K9/62G06K9/20
Inventor 李静卢朝阳戴笑来许亚美
Owner XIDIAN 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