Parameter estimation of linear motion blur based on principal component analysis

To estimate the blur parameter of a linear motion blur image accurately and quickly, this paper analyses how the blur length and direction show in a frequency image and a cepstrum image, respectively, and proposes a motion blur parameter estimation method based on the Principal Component analysis (PCA). Firstly, the cepstrum image of the blur image was segmented in a binaryzation based on the Gaussian distribution modeling, and the highlight line region in the cepstrum image was obtained. Then, the principal component of the highlight line was extracted based on the PCA, and the direction of the principal component was the blur direction. After the blur direction was estimated, the Radon transform of frequency image for the blur image under the estimated direction was calculated, then the result of Radon transform was smoothed to reduce some artifacts. Finally, the blur length was estimated via calculating the interval between the two local-minimas of the Radon transform. Experiment results indicate that the errors of the estimated blur direction and length are 0.138 4° and 0.273 9 pixel, respectively, and the calculation speed is nearly 10 times faster than that of the traditional estimated method based on Radon method with the same accuracy. It concludes that the proposed method can estimate the blur parameter accurately and rapidly.