{
"title": "Image Mapping with Cumulative Distribution Function for Quick Convergence of Counter Propagation Neural Networks in Image Compression",
"authors": "S. Anna Durai, E. Anna Saro",
"country": null,
"institution": null,
"volume": "16",
"journal": "International Journal of Computer, Electrical, Automation, Control and Information Engineering",
"pagesStart": 1084,
"pagesEnd": 1090,
"ISSN": "1307-6892",
"URL": "http:\/\/waset.org\/publications\/2194",
"abstract": "In general the images used for compression are of\r\ndifferent types like dark image, high intensity image etc. When these\r\nimages are compressed using Counter Propagation Neural Network,\r\nit takes longer time to converge. The reason for this is that the given\r\nimage may contain a number of distinct gray levels with narrow\r\ndifference with their neighborhood pixels. If the gray levels of the\r\npixels in an image and their neighbors are mapped in such a way that\r\nthe difference in the gray levels of the neighbor with the pixel is\r\nminimum, then compression ratio as well as the convergence of the\r\nnetwork can be improved. To achieve this, a Cumulative Distribution\r\nFunction is estimated for the image and it is used to map the image\r\npixels. When the mapped image pixels are used the Counter\r\nPropagation Neural Network yield high compression ratio as well as\r\nit converges quickly.",
"references": null,
"publisher": "World Academy of Science, Engineering and Technology",
"index": "International Science Index 16, 2008"
}