Image super‐resolution via adaptive sparse representation and self‐learning

Abstract

This study proposes a novel super-resolution regularisation model based on adaptive sparse representation and selflearning frameworks. The fidelity term in the model ensures that the reconstructed image is consistent with the observation image. The adaptive sparsity regularisation term constrains the reconstructed image with an adaptive sparse representation, which successfully harmonises the sparse representation and the collaborative representation adaptively via producing suitable coefficients. To construct a more effective dictionary, the high-frequency features from the underlying image patches are extracted, and the dictionary learning and sparse representation are integrated. To this end, the alternating minimisation algorithm is used to divide this model into three subproblems, and the alternating direction method of multipliers and iterative back-projection method are used to solve the subproblems. To illustrate the effectiveness of the proposed method, additional experiments are conducted on some generic images. Compared with some state-of-the-art algorithms, the experimental results demonstrate that the proposed method achieves better results in terms of both visual quality and noise immunity.

Literature Review on Single Image Super Resolution

“…In this algorithm [1]- [3] back projection error is used to construct super resolution image. In this approach the HR image is estimated by back projecting the error between the simulated LR image and captured LR image.…”

“…Classification of Super Techniques2. LITERATURE SURVEY[1] This study proposes a novel super regularization model based on adaptive sparse representation and self-learning frameworks. The fidelity term in the model ensures that the…”

TV2++: A Novel Spatial-Temporal Total Variation for Super Resolution with Exponential-type Norm

“…At present, the mainstream of super resolution algorithms can be divided into two types of categories, namely: the reconstruction-based methods [11,12,13,14] and the learning-based methods [15,16,17,18]. Recently, learning-based methods have gained huge attentions because of its efficiency and generalization.…”

“…The learning-based methods acquire the co-occurrence prior knowledge between the low resolution and high resolution image blocks through the learning process. From sparse representation [16,19], anchored neighborhood regression [17] to later transformed selfexemplars [18,20] and deep convolutional networks [21,22,23], by learning from examples based on huge databases consisting of low resolution and high resolution image pairs, these methods can recover details and enhance texture information. Extracting the high frequency information based on local features from the training images, and then adding the high frequency detail for low resolution image can guide a high resolution image reconstruction [15], however, it also results that these methods deeply rely on selected data and sometimes may bring some artifacts.…”

“…Conversely, the bulk of reconstructed based methods usually get high resolution image from a sequence of low resolution images by optimizing the cost function which have prior restriction [11]. The reconstruction based methods are to invert high resolution images from the low resolution image through the image degradation model, which is to solve the inverse problem of the image, and often requires prior knowledge of gradient [26], sparse [16,27,28], spatial-temporal feature [29,30] and so on. Iterative back projection method(IBP) proposed by Pejman et al [12] obtained the high resolution image through iterative back projection for deviation of simulated low resolution image and observed image.…”