Image Super-Resolution via Sparse Representation

  1. ABSTRACT :

                                   This project presents a new approach to single-image super resolution, based on sparse signal representation. Research on image statistics suggests that image patches can be well represented as a sparse linear combination of elements from an appropriately chosen over-complete dictionary. Inspired by this observation, we seek a sparse representation for each patch of the low-resolution input, and then use the coefficients of this

representation to generate the high-resolution output. Theoretical results from compressed sensing suggest that under mild conditions, the sparse representation can be correctly recovered from the down sampled signals. By jointly training two dictionaries for the low- and high-resolution image patches, we can enforce the similarity of sparse representations between the low resolution and high resolution image patch pair with respect to their own dictionaries. Therefore, the sparse representation of a low resolution image patch can be applied with the high resolution image patch dictionary to generate a high resolution image patch. The learned dictionary pair is a more compact representation of the patch pairs, compared to previous approaches, which simply sample a large amount of image patch pairs, reducing the computational cost substantially. The effectiveness of such a sparsity prior is demonstrated for both general image super resolution and the special case of face hallucination. In both cases, our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by

other similar SR methods. In addition, the local sparse modeling of our approach is naturally robust to noise, and therefore the proposed algorithm can handle super-resolution with noisy inputs in a more unified framework.

  2. EXISTING SYSTEM :

                                            Super-resolution (SR) image reconstruction is currently a very active area of research, as it offers the promise of overcoming some of the inherent resolution limitations of low-cost imaging sensors (e.g. cell phone or surveillance cameras) allowing better utilization of the growing capability of high-resolution displays (e.g. high-definition LCDs). Such resolution-enhancing technology may also prove to be essential in medical imaging and satellite imaging where diagnosis or analysis from low-quality images can be extremely difficult. Conventional approaches to generating a super-resolution image normally require as input multiple low-resolution images of the same scene, which are aligned with sub-pixel accuracy. The fundamental reconstruction constraint for SR is that the recovered image, after applying the

same generation model, should reproduce the observed low resolution images. However, SR image reconstruction is generally a severely ill-posed problem because of the insufficient number of low resolution images, ill-conditioned registration  and unknown blurring operators, and the solution from the reconstruction constraint is not unique.

                             Another category of SR approach is based on machine learning techniques, which attempt to capture the co-occurrence prior between low-resolution and high-resolution image patches. [9] proposed an example-based learning strategy that applies to generic images where the low-resolution

to high-resolution prediction is learned via a Markov Random Field (MRF) solved by belief propagation extends this approach by using the Primal Sketch priors to enhance blurred edges, ridges and corners.

  3. PROPOSED SYSTEM :

                                                    A   novel approach towards single image super-resolution is proposed based on sparse representations in terms of coupled dictionaries jointly trained from high- and low resolution image patch pairs. The compatibilities among adjacent patches are enforced both locally and globally. Experimental results demonstrate the effectiveness of the sparsity as

a prior for patch-based super-resolution both for generic and face images. Our algorithm generates high-resolution images that are competitive or even superior in quality to images produced by other similar SR methods. In addition, the local sparse modeling of our approach is naturally robust to noise, and therefore the proposed algorithm can handle super-resolution with noisy inputs

in a more unified framework. This work focuses on the problem of recovering the super resolution version of a given low-resolution image. Similar to the aforementioned learning-based methods, we will rely on patches from the input image. However, instead of working directly with the image patch pairs sampled from high and low-resolution images , we learn a compact representation for these patch pairs to capture the co-occurrence prior, significantly improving the speed of the algorithm. Our approach is motivated by recent results in sparse signal representation, which suggest that the linear relationships among high-resolution signals can be accurately recovered from their low-dimensional projections ]. Although the super-resolution problem is very ill-posed, making precise recovery impossible, the image patch sparse representation demonstrates both effectiveness and robustness in regularizing the inverse problem.

  4.HARDWARE REQUIREMENTS:

•         System                : Pentium IV 2.4 GHz.

•         Hard Disk            : 40 GB.

•         Floppy Drive       : 1.44 MB.

•         Monitor                : 15 VGA Colour.

•         Mouse                 : Logitech.

•         Ram                     : 256 MB.

   5.SOFTWARE REQUIREMENTS:

•         Operating System       : - Windows XP Professional.

•         Front End                               : - Asp .Net 2.0.

•         Coding Language       : - Visual C# .Net.