A Method of Image Texture Feature Analysis Based on Wavelet Decomposition

Abstract:

A novel algorithm of analyzing the textural features of image is put forward for color difference classify of ceramic tiles. First the image of tile is pretreated. Then two level wavelet decompositions are used on the image, and the energy feature of each sub-graph is extracted. The energy contains color and textural features of image, which be used to classify tiles into different color. Tile under test is classified according to the similarity measurement, which is the similar distance between feature value of tiles under test and the one of standard tiles. Euclid distance is used as similarity algorithm. Experimental results show that this method can reflect spatial relationship of color more effectively, and improves the accuracy of the classification in the production line.

• Periodical: Applied Mechanics and Materials (Volumes 101-102)
• Pages: 577-580
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.101-102.577
• Online since: September 2011
• Authors: Li Jun Zhong, Wen Wen Li, Li Yun Zhang, Ai Bing Yu
• Keywords: Color-Difference, Texture Feature Extraction, Tile, Two Dimension Wavelet Decomposition

References

[1] D. Liu and X.F. Zhu: China Ceramic Industry, Vol. 10 (2003)No. 6, pp.66-69.

[2] B. Yang and Y. G. Xu: Acta Automatica Sinica, Vol. 30 (2004) No. 6, pp.991-998.

[3] K.Q. Wang and X.B. Bai: Jouranl of Harbin Institute of Technology, Vol. 41 (2010) No. 9, pp.232-234.

[4] J.Y. Ai: South China University of Technology, Vol. 6 (2003), pp.46-50.

[5] G. Zhang and Z.M. Ma: Journal of Image and Graphics, Vol. 15 (2010)No. 2, pp.247-254.

[6] Y.B. Li and H. Piao: Journal of Chinese Computer Systems, Vol. 31 (2010)No. 6, pp.1213-1216.

[7] L. Liu and G.Y. Kuang: Journal of Image and Graphics, Vol. 14 (2009)No. 4, pp.622-627.