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

Chinese chess piece visual identification method based on Fourier descriptors

A visual recognition and chess technology, applied in the field of visual recognition of chess pieces based on Fourier descriptors, can solve the problems of low accuracy and low efficiency.

Active Publication Date: 2019-11-19
ZHEJIANG UNIV
View PDF3 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Aiming at the technical problems existing in the prior art, the present invention provides a method for visual recognition of chess pieces based on Fourier descriptors, so as to solve the problem of chess pieces in the prior art. The accuracy rate of recognition is not high enough and the efficiency is not high

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
  • Chinese chess piece visual identification method based on Fourier descriptors
  • Chinese chess piece visual identification method based on Fourier descriptors
  • Chinese chess piece visual identification method based on Fourier descriptors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0068] In order to understand the technical scheme of the present invention better, below in conjunction with accompanying drawing Figure 1 to Figure 11 The embodiment of the present invention is further described: the program compiling platform of the present invention Windows7 system 64, processor is AMD FX-SeriesFX-8350 eight cores, graphics card is A card AMD RadeonR9370Series (sapphire), hard disk is Samsung SSD 850EVO250GB (solid state Hard disk), the memory is ADATA DDR3 1600MHz 8GB. The programming development environment is Microsoft VisualStudio2012, and the image processing library is opencv3.4. The camera is a high-definition industrial camera with a resolution of 3840(H)×1960(V), a minimum pixel size of 2.2um×2.2um, and a CMOS sensor chip.

[0069] Technical solution: the present invention is realized through the following technical solutions.

[0070] A method for visual recognition of chess pieces based on Fourier descriptors, comprising the following steps: ...

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 Chinese chess piece visual identification method based on Fourier descriptors, and belongs to the technical field of Chinese chess piece identification and image processing.The method comprises the following steps: (1) acquiring an original color image of a chessboard through an industrial high-definition camera; (2) roughly positioning angular points based on the background image of the chessboard; (3) judging the chessboard corner state based on the HSV space; (4) segmenting chess piece character and extracting character contour; (5) detecting chess piece circularcontour; (6) extracting character contour; (7) extracting character feature based on chess piece character contour images; (8) realizing chess piece character classification recognition model and recognition; and (9) realizing a Chinese chess character classification and recognition model based on a multi-layer feedforward network. And the chess piece identification accuracy reaches 99.3%. According to the algorithm, chess piece visual identification is realized, and the precision is much higher than that of traditional template matching.

Description

technical field [0001] The invention relates to the technical field of chess piece identification and image processing, in particular to a method for visual recognition of chess pieces based on Fourier descriptors. Background technique [0002] Recognizing chess pieces is the basic technology of chess robots, and it is also one of the most critical technologies. The chess robot can only "think" and complete the chess action after "seeing clearly". With the development of computer vision, computer vision technology is used to process the acquired chessboard image, and finally complete the recognition of the status of each position on the entire chessboard, that is, whether there is a chess piece at a certain position and the specific identity of the chess piece. The data structure represents the chessboard state. The essence of identifying the identity of chess pieces is to identify the characters on the chess, that is, character recognition. [0003] Chess character recog...

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): G06K9/20G06K9/34G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V10/22G06V10/267G06V10/56G06N3/045G06F18/241
Inventor 刘峰王进陈建辉陆国栋
Owner ZHEJIANG 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