{"title":"Image Compression with Back-Propagation Neural Network using Cumulative Distribution Function","authors":"S. Anna Durai, E. Anna Saro","volume":17,"journal":"International Journal of Computer and Information Engineering","pagesStart":1571,"pagesEnd":1576,"ISSN":"1307-6892","URL":"https:\/\/publications.waset.org\/pdf\/7050","abstract":"Image Compression using Artificial Neural Networks\nis a topic where research is being carried out in various directions\ntowards achieving a generalized and economical network.\nFeedforward Networks using Back propagation Algorithm adopting\nthe method of steepest descent for error minimization is popular and\nwidely adopted and is directly applied to image compression.\nVarious research works are directed towards achieving quick\nconvergence of the network without loss of quality of the restored\nimage. In general the images used for compression are of different\ntypes like dark image, high intensity image etc. When these images\nare compressed using Back-propagation Network, it takes longer\ntime to converge. The reason for this is, the given image may\ncontain a number of distinct gray levels with narrow difference with\ntheir neighborhood pixels. If the gray levels of the pixels in an image\nand their neighbors are mapped in such a way that the difference in\nthe gray levels of the neighbors with the pixel is minimum, then\ncompression ratio as well as the convergence of the network can be\nimproved. To achieve this, a Cumulative distribution function is\nestimated for the image and it is used to map the image pixels. When\nthe mapped image pixels are used, the Back-propagation Neural\nNetwork yields high compression ratio as well as it converges\nquickly.","references":"[1] M.Egmont-Petersen, D.de.Ridder, Handels, \"Image Processing with\nNeural Networks - a review\", Pattern Recognition 35(2002) 2279-\n2301, www.elsevier.com\/locate\/patcog\n[2] Bogdan M.Wilamowski, Serdar Iplikci, Okyay Kaynak, M. Onder Efe\n\"An Algorithm for Fast Convergence in Training Neural Networks\".\n[3] Fethi Belkhouche, Ibrahim Gokcen, U.Qidwai, \"Chaotic gray-level\nimage transformation, Journal of Electronic Imaging -- October -\nDecember 2005 -- Volume 14, Issue 4, 043001 (Received 18 February\n2004; accepted 9 May 2005; published online 8 November 2005.\n[4] Hahn-Ming Lee, Chih-Ming Cheb, Tzong-Ching Huang, \"Learning\nimprovement of back propagation algorithm by error saturation\nprevention method\", Neurocomputing, November 2001.\n[5] Mohammed A.Otair, Walid A. Salameh, \"Speeding up Back-propagation\nNeural Networks\" Proceedings of the 2005 Informing Science and IT\nEducation Joint Conference.\n[6] M.A.Otair, W.A.Salameh (Jordan), \"An Improved Back-Propagation\nNeural Networks using a Modified Non-linear function\", The IASTED\nConference on Artificial Intelligence and Applictions, Innsbruck,\nAustria, February 2006.\n[7] Simon Haykin, \"Neural Networks - A Comprehensive foundation\", 2nd\nEd., Pearson Education, 2004.\n[8] B.Verma, B.Blumenstin and S. Kulkarni, Griggith University, Australia,\n\"A new Compression technique using an artificial neural network\".\n[9] Rafael C. Gonazalez, Richard E.Woods, \"Digital Image Processing\", 2nd\nEd., PHI, 2005.","publisher":"World Academy of Science, Engineering and Technology","index":"Open Science Index 17, 2008"}