Image mixed blur classification and parameter identification based on cepstrum peak detection
Yingjie Li, Xiaoguang Di · 2016
Motion blur and out-of-focus blur are two main components of image blur in most cases. Blur classification and parameter identification are very important for image processing such as image restoration. In this paper, a novel method based on cepstrum peak detection is presented to classify and identify three types of image blur including motion blur, out-of-focus blur and mixed blur. First, frequency information of detected image is utilized to determine the image blur. Then we classify the image blur in cepstrum domain. Next the parameters of image blur are identified according to the peak distribution of blurred image in cepstrum domain. Lastly, extensive experiments are carried out to verify the performance of our algorithm. Experiment results show that our method leads to performance improvements over state-of-the-arts methods.