A new approach to enhance the estimation of blur parameters in blurred images

Abstract

One of the main objectives of blur parameters estimation is the restoration of blurred images. A novel blur parameters estimation algorithm is presented in the present paper. For estimating the blur angle of the degraded image, Hough transform is applied upon two parallel linear edges on two sides of the central bright stripe that appear in the frequency domain. For blur length estimation, the proposed method has two sequential phases. In the first phase, the frequency domain is used for feature extraction. Also, for obtaining a superior performance in the algorithm in the second stage, a wavelet-based parameter was used, which can determine the extent of the blur in the image. For the prediction of the blur length in a particular blurred image, RBFNN is employed with frequency-domain features of the related blurred image and blur extent parameter, coming from the wavelet transform as the input. Blur length in blurred images is estimated at a higher accuracy using this method. The concentration of this approach is on motion blur parameter estimation. Through comparison with available approaches, the results of simulations indicate the ability and strength of the suggested approach in predicting blur parameters.