A Smart Algorithm for Quantization Table Optimization: A Case Study in JPEG Compression

Image compression is a significant dilemma in digital image processing. JPEG is the ultimate standard for compressing still images in the last few decades. Quantization table in JPEG determines the quality of the image and the performance of the JPEG algorithm. Smartness is capacity to derive or extract knowledge from previous experience and uses the same for current. With this notion in mind, this chapter presents a smart algorithm for quantization table optimization in the JPEG baseline algorithm. Section 13.1 portrays JPEG Standard as a case study where the need for quantization table optimization is described and also we discuss the overview of differential evolution (DE) as a solution for this optimization problem with its strength and weakness. Section 13.2 deals with the need for augmenting knowledge in DE algorithm and explains the design of smart optimization algorithms. Further, we enumerate the methodology for achieving the same. Sections 13.3 and 13.4 compare the applicability of smart optimization algorithms for various test images along with the simulation results, verified using statistical hypothesis testing.

[1]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .

[2]  R. Storn,et al.  Differential Evolution: A Practical Approach to Global Optimization (Natural Computing Series) , 2005 .

[3]  G. R. Karpagam,et al.  Performance Analysis of Deterministic Centroid Initialization Method for Partitional Algorithms in Image Block Clustering , 2015 .

[4]  Wali Khan Mashwani.  Enhanced versions of differential evolution: state-of-the-art survey , 2014, Int. J. Comput. Sci. Math..

[5]  Hui Li,et al.  Enhanced Differential Evolution With Adaptive Strategies for Numerical Optimization , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[6]  G. R. Karpagam,et al.  Knowledge-based differential evolution approach to quantisation table generation for the JPEG baseline algorithm , 2016, Int. J. Adv. Intell. Paradigms.

[7]  Carlos A. Coello Coello,et al.  Knowledge Incorporation in Multi-objective Evolutionary Algorithms , 2008, Multi-Objective Evolutionary Algorithms for Knowledge Discovery from Databases.

[8]  Vinoth Kumar Balasubramanian,et al.  Knowledge-based genetic algorithm approach to quantization table generation for the JPEG baseline algorithm , 2016 .

[9]  Enrique Alba,et al.  Best practices in measuring algorithm performance for dynamic optimization problems , 2013, Soft Comput..

[10]  Stefan Winkler,et al.  Image complexity and spatial information , 2013, 2013 Fifth International Workshop on Quality of Multimedia Experience (QoMEX).

[11]  Y.-G. Wu,et al.  GA-based DCT quantisation table design procedure for medical images , 2004 .

[12]  Ponnuthurai N. Suganthan,et al.  An Adaptive Differential Evolution Algorithm With Novel Mutation and Crossover Strategies for Global Numerical Optimization , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[13]  Balasubramanian Vinoth Kumar,et al.  Differential evolution versus genetic algorithm in optimising the quantisation table for JPEG baseline algorithm , 2015, Int. J. Adv. Intell. Paradigms.

[14]  Patricio A. Vela,et al.  A Comparative Study of Efficient Initialization Methods for the K-Means Clustering Algorithm , 2012, Expert Syst. Appl..

[15]  Alistair R. Clark,et al.  A Genetic Approach to Statistical Disclosure Control , 2012, IEEE Trans. Evol. Comput..

[16]  Efrén Mezura-Montes,et al.  Differential evolution in constrained numerical optimization: An empirical study , 2010, Inf. Sci..

[17]  Qingfu Zhang,et al.  A Gaussian Process Surrogate Model Assisted Evolutionary Algorithm for Medium Scale Expensive Optimization Problems , 2014, IEEE Transactions on Evolutionary Computation.