Chinese chess recognition based on log-polar transform and FFT

Authors:
Shi Lei;Pan Hailang;Cao Guo;Li Chengrong
Affiliations:
Institute of Automation of Chinese Academy of Sciences, Beijing, China;School of Electronic and Optical Engineering of Nangjing University of Science And Technology, Nangjing, China;School of Computer Science and Technology of Nangjing University of Science And Technology, Nangjing, China;Institute of Automation of Chinese Academy of Sciences, Beijing, China
Venue:
ICCSA'11 Proceedings of the 2011 international conference on Computational science and its applications - Volume Part IV
Year:
2011

Citing 6
Cited 0

Fast Hough transform: A hierarchical approach

Computer Vision, Graphics, and Image Processing
The Adaptive Hough Transform

IEEE Transactions on Pattern Analysis and Machine Intelligence
A modified Hough scheme for general circle location

Pattern Recognition Letters
Comparative study of Hough transform methods for circle finding

Image and Vision Computing - Special issue: 5th Alvey vision meeting
Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography

Communications of the ACM
Circular Object Detection Using a Modified Hough Transform

International Journal of Applied Mathematics and Computer Science - Applied Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new method for recognizing Chinese chess. Firstly, histogram equalization and Hough gradient transform is used to determining the location of chess center; Secondly, Log-Polar Transform is used to achieve rotation-invariant and scale-invariant after preprocessing; Thirdly, Fast Fourier Transform (FFT) can achieve translation-invariant. A simple measurement is used to assess the similarity after horizontal and vertical projection. Experiment results have shown that the algorithm can effectively recognize all chesses.