Evaluation of edge detection methods through psychological tests-is the detected edge really desirable for humans?

摘要

We propose a method to quantitatively evaluate image processing methods on how well they simulate human visual processing through psychological and statistical tests. First, we focus on edge detection, an image processing technique. To set all edge detection methods fairly, we collect the edge data detected by humans. Then, the signal processing parameters for each edge detection method are adjusted with the same optimizing method based on minimizing the error between the edges detected by the detector and by humans. Two psychological experiments are conducted, confirming whether the edge detection parameters are optimized and evaluating the performance of edge detection methods. The results indicate that the optimizing method functioned comparatively well. The effectiveness rank of edge detection methods is also obtained.