Different Implemented Techniques of Super Resolution Imaging

2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07, 2007

This work considers a combination classificationregression based framework with the proposal of using learned kernels in modified support vector regression to provide superresolution. The usage of both generative and discriminative learning techniques is examined first by assuming a distribution for image content for classification and then providing regression via semi-definite programming (SDP) and quadratically constrained quadratic programming (QCQP) problems. The advantage of the proposed method over other learning-based superresolution algorithms include reduced problem complexity, specificity with regard to image content, added degrees of freedom from the nonlinear approach, and excellent generalization that a combined methodology has over its individual counterparts.

Image Processing Series, 2000

This chapter develops a superresolution methodology and specifies an architecture to magnify and make clear small-sized and/or low-fidelity images. Superresolution is particularly relevant for multimedia applications due to the poor quality of images imposed by low bandwidth requirements. The method is based on the fact that data dependent bases are able to reconstruct signals with a resolution above the one imposed by the Shannon sampling theorem, provided that statistical information about the signals is utilized to specify the bases. Here we propose to learn the bases and the reconstruction kernels using the information available in local neighborhoods and across scales. First, local neighborhoods of a training image are clustered based on local features. Each cluster is assigned to a reconstruction kernel that is designed as an optimal mapping relating homologous neighborhoods across scales. A superresolved image is obtained by feeding an image through the architecture, or equivalently, by convolving the image with the learned family of kernels. Several examples are presented demonstrating the effectiveness of the approach.

Signal, Image and Video Processing, 2014

This paper presents a fast single-image superresolution approach that involves learning multiple adaptive interpolation kernels. Based on the assumptions that each high-resolution image patch can be sparsely represented by several simple image structures and that each structure can be assigned a suitable interpolation kernel, our approach consists of the following steps. First, we cluster the training image patches into several classes and train each class-specific interpolation kernel. Then, for each input lowresolution image patch, we select few suitable kernels of it to make up the final interpolation kernel. Since the proposed approach is mainly based on simple linear algebra computations, its efficiency can be guaranteed. And experimental comparisons with state-of-the-art super-resolution reconstruction algorithms on simulated and real-life examples can validate the performance of our proposed approach.

In order to overcome the problems that the single dictionary cannot be adapted to variety types of images and the reconstruction quality couldn't meet the application, we propose a novel Multi-Dictionary Learning algorithm for feature classification. The algorithm uses the orientation information of the low resolution image to guide the image patches in the database to classify, and designs the classification dictionary which can effectively express the reconstructed image patches. Considering the nonlocal similarity of the image, we construct the combined nonlocal mean value(C-NLM) regularizer, and take the steering kernel regression(SKR) to formulate a local regularization ,and establish a unified reconstruction framework. Extensive experiments on single image validate that the proposed method, compared with several other state-of-the-art learning based algorithms, achieves improvement in image quality and provides more details.

2007 International Joint Conference on Neural Networks, 2007

Support vector machine (SVM) regression is considered for a statistical method of single frame superresolution in both the spatial and Discrete Cosine Transform (DCT) domains. As opposed to current classification techniques, regression allows considerably more freedom in the determination of missing high-resolution information. In addition, since SVM regression approaches the superresolution problem as an estimation problem with a criterion of image correctness rather than visual acceptableness, its optimization results have better mean-squared error. With the addition of structure in the DCT coefficients, DCT domain image superresolution is further improved.

2013

A hybrid method for image super-resolution consisting of steering kernel regression (SKR) and example based super-resolution (EBSR) techniques has been proposed. In this model the output of SKR is given as the input to the EBSR module. It is observed that though the image super-resolution performed by SKR gives a reasonable result, in terms of perceptual quality, the regression techniques have inherent disadvantage of generating artifacts. EBSR on the other hand augments the image with high frequency information to the image, thereby sharpening the edges. In this paper, we demonstrate that the proposed hybrid scheme performs better than the individual methods described above.

2014 2nd International Conference on Artificial Intelligence, Modelling and Simulation, 2014

In this paper, we propose a new super resolution technique based on iterative interpolation followed by registering them using back projection (BP). Firstly the low resolution image is interpolated and then decimated to four low resolution images. The four low resolution images are interpolated and registered by using BP in order to generate a sharper high resolution image then high resolution image is down sampled and back to the first step. The proposed method has been tested on some bench mark images. The peak signal-tonoise ratio (PSNR) and structural similarity index (SSIM) results as well as the visual results shows the superiority of the proposed technique over the conventional and state-of-art image super resolution techniques. In Average, the PSNR is 2.72 dB higher than the bicubic interpolation.

Lecture Notes in Computer Science, 2012

Super-resolution; PSNR; filter; image restoration; image enhancement This paper introduces an algorithm to super-resolve an image based on a self-training filter (STF). As in other methods, we first increase the resolution by interpolation. The interpolated image has higher resolution, but is blurry because of the interpolation. Then, unlike other methods, we simply filter this interpolated image to recover some missing high frequency details by STF. The input image is first downsized at the same ratio used in super-resolution, then upsized. The super-resolution filters are obtained by minimizing the mean square error between the upsized image and the input image at different levels of the image pyramid. The best STF is chosen as the one with minimal error in the training phase. We have shown that STF is more effective than a generic unsharp mask filter. By combining interpolation and filtering, we achieved competitive results when compared to support vector regression methods and the kernel regression method.

IEEE Transactions on Neural Networks, 1999

An adaptive two step paradigm for the super-resolution of optical images is developed in this paper. The procedure locally projects image samples onto a family of kernels that are learned from image data. First, an unsupervised feature extraction is performed on local neighborhood information from a training image. These features are then used to cluster the neighborhoods into disjoint sets for which an optimal mapping relating homologous neighborhoods across scales can be learned in a supervised manner. A superresolved image is obtained through the convolution of a low resolution test image with the established family of kernels. Results demonstrate the effectiveness of the approach.