Cosine Transform and Shift Number Coding uses for 24-Bit Bitmap image Coding

Abstract

This paper represents an approach for image coding which consists of three parts: The first part is DCT which is used one dimensional discrete cosine transform converts each (n-pixel) into frequency domain, then reduces number of frequency domain elements by deleting half number of elements. The second part applies SNC (Shift Number Coding) on the remained coefficient elements, these elements are converted to integer number. SNC does not need to compute the probability for an image file, just compute the values for each coefficient in frequency domain matrix. The value is computed by selecting maximum number in matrix, then it divides the interval {0…1} by maximum number. This value is shifted by shift function then sum with previous value, the total values represent Compression Value. Finally the arithmetic coding used to compress the matrix of compression value into stream of bits. This approach is tested with three types of images, and compared with JPEG, PNG, and TIFF by using Compression Ratio and PSNR.