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

Statistic handwriting identification and verification method based on separate character

A verification method, handwriting technology, applied in character and pattern recognition, computing, computer parts, etc.

Inactive Publication Date: 2004-03-17
TSINGHUA UNIV
View PDF0 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This is a method not used in any other literature so far

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
  • Statistic handwriting identification and verification method based on separate character
  • Statistic handwriting identification and verification method based on separate character
  • Statistic handwriting identification and verification method based on separate character

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0236] Embodiment 1: handwriting identification system

[0237] Handwriting identification system based on the present invention such as Figure 11 shown. In the experiment, 16 pages of handwriting documents written by 27 people were used, and each page contained 20 handwritings of Chinese characters. First use a scanner to input these handwriting documents into a computer, and then use OCR software to obtain handwriting samples of individual characters. Normalize each single-character handwriting sample to a size of 65×65. The division method of neutron blocks in four-direction line element feature extraction is as follows: Figure 7 way of division. Here N 1 =13, L=5, N 2 =7. according to Figure 4 The process extracts four-directional linear feature. Two methods are used for feature transformation, one is the direct LDA transformation method, 10 samples are used for training, and 6 samples are used for testing. The experimental results are shown in Table 1. The ot...

Embodiment 2

[0242] Embodiment 2: Ministry of Public Security handwriting verification (writer verification) system

[0243] The function that the handwriting verification system of the Ministry of Public Security needs to complete is to train a verification database file through a given sample, and judge whether the inspection material is written by the criminal suspect who wrote the sample, so as to provide a basis for judicial judgment. This problem is actually a two-class problem, and the difficulty lies in the fact that the training process is real-time and there are no pseudo-samples.

[0244] The block diagram of the whole verification system is as follows: Figure 12 shown. It mainly consists of three parts:

[0245] ●Pseudo sample generation part

[0246] This part is mainly used to generate pseudo-sample library. We use 1806 sets of first-level handwritten Chinese characters (3755 Chinese characters) samples collected by different people in the laboratory as pseudo-samples of...

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 handwriting authentication and verification method based on single character characterized by that, four traverse line element characteristic is extracted to better reflect the feature of the Chinese characters, then one of the following methods is used to reflect the optical diagnostic character of the difference between different writers, one is to extract the most distinctive feature through direct LDA (linear differentiation analysis) transformation, the other is to first extract the most distinctive feature through direct PCA (principal component analysis) transformation dimensionality reduction, then using LDA transformation to obtain the most distinctive diagnostic character. In accordance with the invention, an Euler's distance classifier is used for categorization authentication.íí

Description

technical field [0001] A statistical handwriting identification and verification method based on a single character belongs to the field of handwriting identification. Background technique [0002] It is of great theoretical and practical significance to identify and verify the identity of the writer by using the difference in handwriting written by the writer. Under the current situation that people's knowledge and experience are usually used for handwriting identification, how to use computers to identify handwriting, eliminate the influence of human factors, and carry out handwriting identification objectively has special significance. There are usually two methods for handwriting identification and verification, one is a text-independent method and the other is a text-related method. Text-related methods use the same text (called feature characters) as processing objects for handwriting identification and verification. In the process of handwriting identification and v...

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): G06F17/16G06K9/20G06K9/36G06K9/48
Inventor 丁晓青王贤良刘长松彭良瑞方驰
Owner TSINGHUA 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