Minimizing Loss of Information at Competitive PLIP Algorithms for Image Segmentation with Noisy Back Ground


In this paper, two training systems for selecting PLIP parameters have been demonstrated. The first compares the MSE of a high precision result to that of a lower precision approximation in order to minimize loss of information. The second uses EMEE scores to maximize visual appeal and further reduce information loss. It was shown that, in the general case of basic addition, subtraction, or multiplication of any two images, γ, k, and λ = 1026 and β = 2 are effective parameter values. It was also found that, for more specialized cases, it can be effective to use the training systems outlined here for a more application-specific PLIP. Further, the case where different parameter values are used was shown, demonstrating the potential practical application of data hiding.

[1] Sos Agaian, Blair Silver, and Karen Panetta, ―Transform Coefficient Histogram Based Image Enhancement Algorithms Using Contrast Entropy,‖ IEEE Trans. Image Processing, Vol. 16, No. 3, pp. 751—758, March, 2007.

[2] M. Heat, S. Sarkar, T. Sanocki, and K. Bowyer, ―Comparison of Edge Detectors: A Methodology and Initial Study,‖ Computer Vision and Image Understanding, Vol. 69, No. 1, pp. 38—54, 1998.

[3] S. Agaian, K. Panetta, and A. M. Grigoryan. ―A New Measure of Image Enhancement,‖ inProc. IASTED 2000 Int. Conf. Signal Processing & Communication, Marbella, Spain, 2000.

[4] M. K. Kundu and S. K. Pal, ―Thresholding for Edge Detection Using Human Psychovisual Phenomena,‖ Pattern Recognition Letters, Vol. 4, No. 6, December 1986, pp. 433—441.

[5] Sos S. Agaian, Karen Panetta, and Artyom Grigoryan, ―Transform based imageenhancement with performance measure,‖ IEEE Transactions On Image Processing, Vol. 10, No. 3, pp.367—381, March, 2001.

[6] H. S. Kim, et al., ―An Anisotropic Diffusion Based on Diagonal Edges,‖ in Proc. 9th Int. Conf. Advanced Communication Technology, pp. 384—388, February, 2007.

[7] Y. Bao and H. Krim, ―Smart Nonlinear Diffusion: A Probabilistic Approach,‖ IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 1, pp. 63—72, January, 2004.