Research Article

Optimized Image Compression through Artificial Neural Networks and Wavelet Theory

by  Raghvendra Pratap Singh, Choudhary Mahfooz Alam, J P Saini
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 79 - Issue 13
Published: October 2013
Authors: Raghvendra Pratap Singh, Choudhary Mahfooz Alam, J P Saini
10.5120/13801-1797
PDF

Raghvendra Pratap Singh, Choudhary Mahfooz Alam, J P Saini . Optimized Image Compression through Artificial Neural Networks and Wavelet Theory. International Journal of Computer Applications. 79, 13 (October 2013), 21-25. DOI=10.5120/13801-1797

                        @article{ 10.5120/13801-1797,
                        author  = { Raghvendra Pratap Singh,Choudhary Mahfooz Alam,J P Saini },
                        title   = { Optimized Image Compression through Artificial Neural Networks and Wavelet Theory },
                        journal = { International Journal of Computer Applications },
                        year    = { 2013 },
                        volume  = { 79 },
                        number  = { 13 },
                        pages   = { 21-25 },
                        doi     = { 10.5120/13801-1797 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2013
                        %A Raghvendra Pratap Singh
                        %A Choudhary Mahfooz Alam
                        %A J P Saini
                        %T Optimized Image Compression through Artificial Neural Networks and Wavelet Theory%T 
                        %J International Journal of Computer Applications
                        %V 79
                        %N 13
                        %P 21-25
                        %R 10.5120/13801-1797
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

Many techniques have been developed for image compression. An efficient image compression technique promises to give high compression ratio, maintaining the quality of the image. The paper proposes an image compression technique which combines both Artificial Neural Networks and Wavelet theory to optimize the compression ratio and peak signal to noise ratio. Results show that high compression ratio is achievable as per requirement, maintaining good reconstruction quality.

References
  • R. C. Gonzalez and R. E. Woods, "Digital Image Processing", Addision Wesley, New York, USA, 1981.
  • S. Haykin, "Neural Networks- A Comprehensive Foundation", 2nd Edition, Pearson Publication, 2004.
  • Vikash Kumar, Jitu Sharma and Shahanaz Ayub. Article: Image Compression using FFN for ROI and SPIHT for background. International Journal of Computer Applications 46(18):30-35, May 2012.
  • D. Kornreich, Y. Benbenisti, H. B. Mitchell, P. Schaefer, "A High Performance Single Structure Image Compression Neural Network", IEEE Trans. Aerospace Electronic Systems, p. p. 1060-1073, 1997.
  • A. Namphol, S. Chin, M. Arozullah, "Image Compression with A Hierarchical Neural Network", IEEE Trans. Aerospace Electronic Systems, p. p. 326-337, 1996.
  • Dong Changhong, "Neural Networks and Applications", 2nd edition, Beijing, China: National Defence Industry, p. p. 14-120, 2009.
  • C. Ben Amar and O. Jemai, "Wavelet Networks Approach for Image Compression", GVIP Special Issue on Image Compression, ICGST, p. p. 15-23, 2007.
  • Weiwei Xiao, Haiyan Liu, "Using Wavelet Networks in Image Compression", Seventh International Conference on Natural Computations, p. p. 700-704, 2011.
  • Hamdy S, Soliman, Mohammed Omari, "A Neural Network Approach to Image Compression Applied Soft Computing", Vol. 6, Issue 3, p. p. 258-271, 2006.
  • Rufai, Awwal Mohammed, Gholamreza Anbarjafari, and Hasan Demirel. "Lossy image compression using singular value decomposition and wavelet difference reduction. " Digital Signal Processing (2013).
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

ROI SPIHT FFN.

Powered by PhDFocusTM