Comparison of decomposition and reconstruction of 2D signal using slantlet transform and DCT

In this paper we present implementation and analysis of Slantlet Transform and Discrete Cosine Transform (DCT) for 2-D signal. The Slantlet Transform is known as Orthogonal Discrete Wavelet Transform. By applying the Slantlet transform to an image, we obtain four sub-bands HH, HL, LH, and LL. The DCT tranforms an image from spatial domain to frequency domain. It separates the image into spectral sub-bands with respect to the parts of differing importance. This paper discusses the decomposition and reconstruction of different images using Slantlet transform and DCT. Image decomposition and reconstruction is an important tool for image enhancement and denoising operations. To measure amount of distortion between input image and reconstructed image, and to measure quality of reconstructed image statistical parameters are calculated. The quality of reconstructed images by using Slantlet transform and DCT is measured by applying various statistical parameters such as Mean Squared Error (MSE), Peak Signal to Noise Ratio (PSNR) and Sum Squared Error (SSE) to analyse performance of both the transforms respectively. Our experimental results have shown that MSE using DCT is less than MSE Slantlet transform. Hence DCT proves better for image decomposition and reconstruction than Slantlet Transform for 2-D signal.