A Method of Image Processing Algorithm Evaluation Based on Orthogonal Experimental Design

Orthogonal experimental design, an effective method of multi-factors researches, is capable of reducing the times of experiments, determining the sequence of priority of influencing factors rapidly and figuring out the best parameters and confidence degree. The novel characteristic of this paper is to apply the orthogonal experimental design into the evaluation research of image processing algorithms. It can determine the sequence of priority of influencing factors and confidence degree by analyzing the range and variance of the results with experimental scheme. The experimental results demonstrate that the proposed method can accurately measure the sequence of priority of influencing factors by fewer experiments accurately, and also reflect the algorithm performance scientifically.