Vinoth Kumar BALASUBRAMANIAN, Karpagam MANAVALAN

A problem approximation surrogate model (PASM) for fitness approximation in optimizing the quantization table for the JPEG baseline algorithm

The quantization table in the baseline Joint Photographic Experts Group (JPEG) algorithm plays an important role in compression/quality trade-off. Hence the detection of the optimal quantization table is viewed as an optimization problem. The genetic algorithm (GA) is an attractive optimization tool by many researchers for this application due to its ability in dealing with complex problems. In spite of its advantages, the GA requires more computation time to achieve an optimal solution if it has an expensive fitness evaluation. This paper proposes a problem approximation surrogate model (PASM) for fitness approximation to assist the GA in optimizing the quantization table for a target bits per pixel. This proposal reduces the computational time of the GA without any loss in performance. The PASM uses an image block clustering process and an indirect evaluation method to approximate the fitness value. The number of clusters in the clustering process may influence the performance of the PASM. A performance analysis with different number of clusters has been done and a suitable cluster number is identified with the help of measuring criteria such as mean squared difference, correct selection, potentially correct selection, and rank correlation. In addition, the results acquired from these measuring criteria are confirmed using statistical hypothesis tests such as Friedman s ANOVA and Wilcoxon signed rank. The PASM with suitable cluster number has been tested in a classical genetic algorithm and knowledge based genetic algorithm. Several benchmark images with different complexity levels have been examined in three different target bits per pixel to validate the performance of the PASM. The results proved that the PASM guarantees better results in terms of peak signal-to-noise ratio with a reduction in computational time.

PDF

___

[1] Vinothkumar B, Karpagam M. Knowledge based genetic algorithm approach to quantization table generation for the jpeg baseline algorithm. Turk J Elec Eng & Comp Sci 2016; 24: 16151635.
[2] Wallace G. The JPEG still picture compression standard. IEEE T Consum Electr 1992; 38: 18-34.
[3] Bo L, Qingfu Z, Georges GEG. A gaussian process surrogate model assisted evolutionary algorithm for medium scale expensive optimization problems. IEEE T Evolut Comput 2014; 18: 180-192.
[4] Loshchilov IG. Surrogate-assisted evolutionary algorithms. PhD, Paris-Sud University, Paris, France, 2013.
[5] Shi L, Rasheed K. A survey of fitness approximation methods applied in evolutionary algorithms. In: Tenne Y, Goh CK, editors. Computational Intelligence in Expensive Optimization Problems. Berlin, Germany: Springer-Verlag, 2010. pp. 251-258.
[6] Laura AA, Goldberg DE. Efficient discretization scheduling in multiple dimensions. In: Genetic and Evolutionary Computation Conference; 913 July 2002; New York. NY, USA: Morgan Kaufmann. pp. 271-278.
[7] Bo Y, Xin Y, Bin L, Thomas W. A new memetic algorithm with fitness approximation for the defect-tolerant logic mapping in crossbar-based nano-architectures. IEEE T Evolut Comput 2013; 18: 846-859.
[8] Achille M, Anoop AM. A computationally efficient metamodeling approach for expensive multi objective optimization. Optim Eng 2008; 9: 37-67.
[9] Horng SC, Lin SY. Evolutionary algorithm assisted by surrogate model in the framework of ordinal optimization and optimal computing budget allocation. Inform Sciences 2013; 233: 214-229.
[10] Tawatchai K, Sujin B. Surrogate-assisted multi objective evolutionary algorithms for structural shape and sizing optimization. Math Probl Eng 2013; 2013: 1-13.
[11] Wang C, Duan Q, Gong W, Ye A, Di Z, Miao C. An evaluation of adaptive surrogate modeling based optimization with two benchmark problems. Environ Modell Softw 2014; 60: 167-179.
[12] Yoon JW, Cho SB. An efficient genetic algorithm with fuzzy c-means clustering for traveling salesman problem. In: IEEE 2011 Evolutionary Computation Congress; 58 June 2011, New Orleans, LA. New York, NY, USA: IEEE.pp. 1452-1456.
[13] Sun X, Gong D, Jin Y. A new surrogate-assisted interactive genetic algorithm with weighted semi supervised learning. IEEE T Syst Man Cy B 2013; 43: 685-698.
[14] Jin Y, H¨usken M, Sendhoff B. Quality measures for approximate models in evolutionary computation. In: Springer 2003 Genetic and Evolutionary Computation Conference; 911 July 2003; Chicago. Berlin Heidelberg, Germany: Springer. pp. 170-173.
[15] Ebrahimi M, Vrscay ER. Self-similarity in imaging 20 years after fractals everywhere. In: TICSP 2008 Local and Non-Local Approximation in Image Processing Workshop; 2324 August 2008; Lausanne, Switzerland. Finland: TICSP. pp. 165-172.
[16] Taubman D. High performance scalable image compression with ebcot. IEEE T Image Process 2000; 9: 1158-1170.
[17] Zhou W, Bovik AC. Mean squared error - love it or leave it. IEEE Signal Proc Mag 2009; 26: 98-117.
[18] Smith JE, Clark AR, Staggemeier AT, Serpell MC. A genetic approach to statistical disclosure control. IEEE T Evolut Comput 2011; 16: 431-441.