International Journal of Computer Science Issues
Images in their uncompressed form require large amount of storage capacity and uncompressed data needs large transmission bandwidth for the transmission. Image compression technique is used to reduce the storage requirement per image, while maintaining image quality. The proposed method investigates biometric image compression using Gaussian Pyramid Compression (GPC) in which the performance is observed down to 0.23 bits/pixel attributed to noise reduction without a significant loss of texture. Objective measures were used such as Signal to Noise Ratio (SNR), Peak Signal to Noise Ratio (PSNR), Mean Squared Error (MSE) and Bit Rate (BR) to evaluate the image quality for both gray and RGB biometric images.