Image thresholding using standard deviation

Jung-Min Sung; Dae-Chul Kim; Bong-Yeol Choi; Yeong-Ho Ha

doi:10.1117/12.2040990

Translator Disclaimer

7 March 2014 Image thresholding using standard deviation

Jung-Min Sung, Dae-Chul Kim, Bong-Yeol Choi, Yeong-Ho Ha

Author Affiliations +

Proceedings Volume 9024, Image Processing: Machine Vision Applications VII; 90240R (2014) https://doi.org/10.1117/12.2040990
Event: IS&T/SPIE Electronic Imaging, 2014, San Francisco, California, United States

Abstract

Threshold selection using the within-class variance in Otsu’s method is generally moderate, yet inappropriate for expressing class statistical distributions. Otsu uses a variance to represent the dispersion of each class based on the distance square from the mean to any data. However, since the optimal threshold is biased toward the larger variance among two class variances, variances cannot be used to denote the real class statistical distributions. Therefore, to express more accurate class statistical distributions, this paper proposes the within-class standard deviation as a criterion for threshold selection, and the optimal threshold is then determined by minimizing the within-class standard deviation. Experimental results confirm that the proposed method produced a better performance than existing algorithms.

Citation Download Citation

Jung-Min Sung, Dae-Chul Kim, Bong-Yeol Choi, and Yeong-Ho Ha "Image thresholding using standard deviation", Proc. SPIE 9024, Image Processing: Machine Vision Applications VII, 90240R (7 March 2014); https://doi.org/10.1117/12.2040990

ACCESS THE FULL ARTICLE