Analyzing a kind of space-variant blurred image which was resulted from moving target shot by moving camera

the article presented a method of space-variant blurred image restoration based on image segmentation according to pixel’s motion-blur character. Because of the convolution process of motion blur

the pixels of observed image’s target and background will be displaced and piled up and will produce two superposition regions. As a result

the neighboring pixels in the superposition regions will have similar grey level change. According to the feature

the method could detect the target’s blurred edge of superposition region. And canny operator was recurred to detect the target edge which parallels the motion blur direction. Then the segmentation process obtained the whole target image which has the character of integral convolution between motion blur and real target image. At last

the target image restored by adding zeros and deconvolution algorithms. The practical restoration result indicated that the approach can effectively solve the kind of problem of space-variant motion blurred image restoration.