The Finite Ridgelet Transform for Defeat Detection of Quill

Abstract:

A defeat detection method for quill using the finite ridgelet transform is mentioned. This method reduce the average gray values of quill and analytic statistics methods are used in ridgelet transform according to points of quill. After ridgelet transform the linear singularity is further highlighted and the quantization errors caused by cutting image of quill is overcomed. With this method the differences between background and quill are eliminated too and automaticly adjusting the sub-image size for transformation according to the width of quill is realized. The experiment results show that this method can effectively detect smaller linear defects and hence satisfy the industrial production needs.

• Periodical: Advanced Materials Research (Volumes 317-319)
• Pages: 915-918
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.317-319.915
• Online since: August 2011
• Authors: Hong Jiang Liu, Ren Huang Wang, Jun Feng Ming, Xue Cong Li
• Keywords: Defeat Detection, Finite Radon Transform, Finite Ridgelet Transform

References

[1] S. Ozdemir, A. Baykut, R. Meylani, A. Ercil, and A. Ertuzun, "Comparative evaluation of texture analysis algorithms for defect inspection of textile products", In International Conference on Pattern Recognition, 1998, pp.1738-1740.

DOI: 10.1109/icpr.1998.712061

[2] X. Guo and W. Liu, "An Automatic Feather Selecting System by Image Processing", Modern Electronics Technique, Vol. 27 No. 3 (2004), P. 30-31. (in Chinese)

[3] J. Jia and L. Jiao, "Implementation of Digital Ridgelet Transform and a New Method", Journal of Computer Research and Development, Vol. 43 No. 1 (2006), P. 115-119. (in Chinese)

DOI: 10.1360/crad20060118

[4] M. Tang and L. Cheng, "Edge Detection Based on Adaptive Ridgelet Transform", Journal of Computer Applications, Vol. 26 No. 11 (2006), pp.2713-2715. (in Chinese)