An accurate gradient-based predictive algorithm for image compression

Abstract

Many prediction algorithms have been proposed and implemented so far for efficient storage and transmission. In this paper, we propose an algorithm for predictive coding. This new algorithm evaluates and uses the values of the known pixels in much more different directions than previous algorithms such as Median Edge Detection (MED) and Gradient Adjusted Prediction (GAP). The proposed algorithm, MED, and GAP algorithms are implemented and tested on different image contents and sizes. The experimental results show that the prediction error of the proposed algorithm is much less than other algorithms. In other words, the quality of obtained predicted images via the proposed method is better than MED and GAP algorithms. Additionally, the accuracy of the proposed technique is independent from the image contents and image sizes.