An Improved Algorithm for Motion Blurred Image

Konferenz: ISCTT 2021 - 6th International Conference on Information Science, Computer Technology and Transportation
26.11.2021 - 28.11.2021 in Xishuangbanna, China

Tagungsband: ISCTT 2021

Seiten: 4Sprache: EnglischTyp: PDF

Persönliche VDE-Mitglieder erhalten auf diesen Artikel 10% Rabatt

Yan, Yuxin; Tang, Ying; Mou, Weidong; Xiao, Junqiu (School of Mechanical and Electrical Engineering, Chengdu University of Technology, Chengdu, Sichuan, China)

A novel image deblurring algorithm was proposed to overcome the problem of noise amplification in the image restoration processing of Lucy-Richardson (L-R) algorithm. This algorithm firstly used bilateral filtering method and Otsu to improve the traditional Canny algorithm, and used the improved Canny algorithm to extract the edge of the image and got the edge feature. Then, the L-R algorithm was used to process motion-blurred images, and the bilateral filtering method was used to denoise the images processed by the L-R algorithm. Finally, wavelet transform was used to combine the edge features with the smoothed image to obtain the restored image. The test result shown that compared with the classic L-R algorithm, this algorithm can improve the quality of motion blurred images more effectively, reduce the influence of noise on iterative restoration, and the image restoration effect is more stable, and the expected results are achieved.