Image Compression using Neural Networks & Wavelet Transforms

Compression provides a means of reducing storage costs and increases the rate of transmission. Image compression reduces the size of graphic images without reducing image quality. Image performance is calculated using certain parameters such as PSNR (peak signal to noise ratio), CR (compression ratio), MSE (mean square error), and (BPP) per pixel bit. Mean Square error is a network performance parameter, it deals the network's Performance according to the mean of squared errors. The Peak signal to noise ratio is generally used for quality comparison between the original image and a compressed image. The Peak Signal to Noise Ratio and Mean Square Error are the two error parameters used to measure image compression quality. The MSE shows the growing squared error among the original image and compressed, and PSNR shows a calculation of the peak error. The lesser the value of Mean Square Error will reduce the error. The compression ratio (CR) is the ratio of compressed image compared to uncompressed image size. The bits per pixel (BPP) value will fluctuate for different images and different quality of images.

Autorentext

Mr. Saurabh Jain- M. Tech (NIT Bhopal M.P .India)PhD* (University of Petroleum and Energy Studies, Dehradun, India.) Assistant Professor (University of Petroleum and Energy Studies, Dehradun, India.)Mrs. Prachi Jain- M. Tech (RGPV University M.P. India)