Image blur kernel estimation is critical to blind image deblurring. Most existing approaches exploit handcrafted blur features that are optimized for a certain uniform blur across the image, which is unrealistic in a real blind deconvolution setting, where the blur type is often unknown. To deal with this issue, we aim at identifying the blur type for each input image patch, and then estimating the kernel parameter in this paper. A learning-based method using a pre-trained deep neural network (DNN) and a general regression neural network (GRNN) is proposed to first classify the blur type and then estimate its parameters, taking advantages of both the classification ability of DNN and the regression ability of GRNN. To the best of our knowledge, this is the first time that pre-trained DNN and GRNN have been applied to the problem of blur analysis. First, our method identifies the blur type from a mixed input of image patches corrupted by various blurs with different parameters. To this aim, a supervised DNN is trained to project the input samples into a discriminative feature space, in which the blur type can be easily classified. Then, for each blur type, the proposed GRNN estimates the blur parameters with very high accuracy. Experiments demonstrate the effectiveness of the proposed method in several tasks with better or competitive results compared with the state of the art on two standard image data sets, i.e., the Berkeley segmentation data set and the Pascal VOC 2007 data set. In addition, blur region segmentation and deblurring on a number of real photographs show that our method outperforms the previous techniques even for non-uniformly blurred images.

Image denoising is a well explored topic in the field of image processing. In the past several decades, the progress made in image denoising has benefited from the improved modeling of natural images. In this paper, we introduce a new taxonomy based on image representations for a better understanding of state-of-the-art image denoising techniques. Within each category, several representative algorithms are selected for evaluation and comparison. The experimental results are discussed and analyzed to determine the overall advantages and disadvantages of each category. In general, the nonlocal methods within each category produce better denoising results than local ones. In addition, methods based on overcomplete representations using learned dictionaries perform better than others. The comprehensive study in this paper would serve as a good reference and stimulate new research ideas in image denoising.

Image blur kernel classification and parameter estimation are critical for blind im-age deblurring. Current dominant approaches use handcrafted blur features that are op-timized for a certain type of blur, which is not applicable in real blind deconvolution application when the Point Spread Function (PSF) of the blur is unknown. In this paper, a Two-stage system using Deep Belief Networks (TDBN) is proposed to first classify the blur type and then identify its parameters. To the best of our knowledge, this is the first time that Deep Belief Network (DBN) has been applied to the problem of blur analysis. In the blur type classification, our method attempts to identify the blur type from mixed input of various blurs with different parameters, rather than blur estimation based on the assumption of a single blur type in current methodology. To this aim, a semi-supervised DBN is trained to project the input samples in a discriminative feature space, and then classify those features. Moreover, in the parameter identification, the proposed edge de-tection on logarithm spectrum helps DBN to identify the blur parameters with very high accuracy. Experiments demonstrate the effectiveness of the proposed methods with bet-ter results compared to the state-of-the-art on the Berkeley segmentation dataset and the Pascal VOC 2007 dataset. 1

Exploiting the sparsity within representation models for images is critical for image denoising. The best currently available denoising methods take advantage of the sparsity from image self-similarity, pre-learned, and fixed representations. Most of these methods, however, still have difficulties in tackling high noise levels or noise models other than Gaussian. In this paper, the multiresolution structure and sparsity of wavelets are employed by nonlocal dictionary learning in each decomposition level of the wavelets. Experimental results show that our proposed method outperforms two state-of-the-art image denoising algorithms on higher noise levels. Furthermore, our approach is more adaptive to the less extensively researched uniform noise.