Sorting Batteries from Waste Paper Based on Invariant Moments and Fractal Dimension

Abstract:

In this paper a new method is proposed for intelligent sort of battery from waste paper based on Invariant Moments and Fractal Dimension (IMFD). In IMFD, a new distinctive feature that based on the edge contours is extracted to describe the target picture. At first invariant moments technique is used to extract Hus seven moments as the global descriptors from the target image. Then the fractal dimensions are extracted as local invariant descriptors by using Fractal Dimension. At last, a combing descriptor is built according the distinctive feature, which combines the global descriptor and the local descriptor together. The features are highly distinctive, and can be matched with high probability against a large database of features. The practical tests performed in this article show that the proposed method has a significant effect on increasing the stability, the accuracy of classification, and also can effectively against the huge-information during the image processing.

• Periodical: Applied Mechanics and Materials (Volumes 475-476)
• Pages: 792-797
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.475-476.792
• Online since: December 2013
• Authors: Dong Ri Shan*, Xiu Hua Men, Hai Ming Xin
• Keywords: Fractal Dimension, Global/Local Invariant Descriptors, Intelligent Sorting, Invariant Moments

References

[1] Esin Dogantekin, Mustafa Yilmaz, Akif Dogantekin, Engin Avci and Abdulkadir Sengur: A robust technique based on invariant moments–ANFIS for recognition of human parasite eggs in microscopic images. Expert Systems with Applications. 2008, 35, p.728.

DOI: 10.1016/j.eswa.2007.07.020

[2] M. J. Islam, and M. S. Islam: Generalized Cantor Set and its Fractal Dimension . BANGLADESH JOURNAL OF SCIENTIFIC AND INDUSTRIAL RESEARCH. 2011, 46(4), pp.499-506.

DOI: 10.3329/bjsir.v46i4.9598

[3] Sarkar N., B.B. Chaudhuri: An efficient differential box-counting approach to compute fractal dimension of image, IEEE Transaction on System Man and Cybernet, vol. 24, no. 1, 1994, pp.115-120.

DOI: 10.1109/21.259692

[4] Jayamohan M., And K. Revathy: An improved domain classification scheme based on local fractal dimension. Indian Journal of Computer Science and Engineering. Vol. 3 No. 1 Feb-Mar 2012, pp.138-145.

[5] A.A. Barrett 1, P.F. Cesar2, S.S. Scherrer: Reliability of fractal dimension analysis based on round-robin tests. Dental materials, 2010, 26s, p.66.

DOI: 10.1016/j.dental.2010.08.149

[6] Song-tao Liu: An improved differential box-counting approach to compute fractal dimension of gray-level image. International Symposium on Information Science and Engieering. 2008, pp.303-306.

DOI: 10.1109/isise.2008.218

[7] Goshtasby A, Gage S H and Bartholic: A two-stage crosscorrelat ion approach to temple matching. IEEE Trans. Pattern Anal. Machine Intell. May 1984, p.374–378.

DOI: 10.1109/tpami.1984.4767532