Efficient Image Compression Technique Based on Vector Quantization Using Social Spider Optimization Algorithm
Hema Rajini N
Hema Rajini N, Department of Computer Science and Engineering, Alagappa Chettiar Government College of Engineering and Technology, Karaikudi (Tamilnadu), India.
Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 359-366 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5259058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In past few decades, Linde Buzo Gray (LBG) is considered as an important vector quantization (VQ) technique to construct local optimum codebook to compress images. Presently, swarm intelligence based optimization algorithms like firefly algorithm (FA), particle swarm optimization (PSO) and honey bee mating optimization (HBMO) are developed to generate a near global codebook. The FA suffers from the drawback of random movement in case of the absence of brighter fireflies whereas PSO becomes instable in case of high particle velocities. Keeping these limitations in mind, in this paper, we present a social spider (SS) algorithm which undergoes optimization of the LBG codebook. The presented SS-LBG approach ensures that the global codebook will be generated to effectively compress the images. The proposed SS-LBG method is experimented on benchmark images and the results are assessed interms of compression performance as well as reconstructed image quality. The experimental outcome verified that the SS-LBG shows superior performance over the compared methods significantly. The presented method exhibits superior performance with a maximum compression performance with an average compression ratio (CR) of 0.44305, space saving (SS) of 55.696, bit rate of 3.60815 and peak signal to noise ratio (PSNR) of 52.86348.
Keyword: Image Compression, LBG, Social spider, Vector quantization.
Scope of the Article: Component-Based Software Engineering.