Image Super‐Resolution Based on Sparse Representation via Direction and Edge Dictionaries

Abstract

Sparse representation has recently attracted enormous interests in the field of image super-resolution. The sparsity-based methods usually train a pair of global dictionaries. However, only a pair of global dictionaries cannot best sparsely represent different kinds of image patches, as it neglects two most important image features: edge and direction. In this paper, we propose to train two novel pairs of Direction and Edge dictionaries for super-resolution. For single-image super-resolution, the training image patches are, respectively, divided into two clusters by two new templates representing direction and edge features. For each cluster, a pair of Direction and Edge dictionaries is learned. Sparse coding is combined with the Direction and Edge dictionaries to realize superresolution. The above single-image super-resolution can restore the faithful high-frequency details, and the POCS is convenient for incorporating any kind of constraints or priors. Therefore, we combine the two methods to realize multiframe super-resolution. Extensive experiments on image super-resolution are carried out to validate the generality, effectiveness, and robustness of the proposed method. Experimental results demonstrate that our method can recover better edge structure and details.

Design of Cascaded CNN for Medical Image Super Resolution

“…So, for the identity metrics hyper sphere space is used, for the training data set CNN used and in the same way for the feature extraction Euclidian distance is used. Zhu et al (2017) performed the scaling the images with scaling factor of 2 author has used VDSR which is based on bi cubic interpolation and then for training data set with residual learning CNN is used in Zhu et al (2017). Convergence speed is maximized and gradient clipping is used to ensure the training stability which is able to overcome the problem in SRCNN.…”

Deep Learning Algorithms for Single Image Super-Resolution: A Systematic Review

“…Sparse coding assumes the image as a sparse linear combination of elements, which can be selected from a pre-constructed and sparse enough dictionary [5]. Zhu et al [17] demonstrated an example of using sparse coding via direction and edge dictionary for image resolution. Yang et al [18,19] developed a sparse coding network to train a joint dictionary to find a highly sparse and over-complete coefficient matrix.…”

Efficient Edge-Based Image Interpolation Method Using Neighboring Slope Information

“…A good interpolation algorithm needs to be simple and must have low complexity, so that it can easily be implemented. Many researchers [5]- [18] have proposed algorithms for upscaling digital images. Nearest neighbors, bilinear and bicubic [4] are popular and time-efficient interpolations.…”

“…Zhao et al [16], Timofte et al [17], and Zhu et al [18] have proposed dictionary learning based image interpolation methods named Self-learning and Adaptive Sparse Representation (SL-ASR), Anchored Neighborhood Regression (ANR) and Single Image Super Resolution (SISR), respectively. SISR uses multiple dictionaries that make it far more complex method compared to ANR and SL-ASR.…”