Image Compression Using SVD Method
A. SUTCU Ali Degirmenci Ömer Karal I. CANKAYA
AbstractAs is known, it is often difficult to store and transmit images used in various computer applications. A possible solution to this problem is to use one of the known data compression techniques because they help to reconstruct the image with a lower number of measurements. In this study, a new Singular Value Decomposition (SVD)based technique is proposed to compress images. The advantage of using SVD is that it both has energy compression capability and is easily adaptable to local statistical variations of the image. Furthermore, the SVD can be implemented with non-square, non-reversible matrices of size m x n. However, how to determine the threshold value for image compression in the SVD technique is still one of the fundamental problems. In this study, the desired threshold value is calculated by dividing the sum of the differences between the obtained singular values by the rank of the matrix. Simulation results confirm the feasibility of our proposed method.