Iterative-Interpolation Super-Resolution Image Reconstruction: A Computationally Efficient TechniqueTo my wife, Mitu - Vivek Bannore Preface Preface In many imaging systems, under-sampling and aliasing occurs frequently leading to degradation of image quality. Due to the limited number of sensors available on the digital cameras, the quality of images captured is also limited. Factors such as optical or atmospheric blur and sensor noise can also contribute further to the d- radation of image quality. Super-Resolution is an image reconstruction technique that enhances a sequence of low-resolution images or video frames by increasing the spatial resolution of the images. Each of these low-resolution images contain only incomplete scene information and are geometrically warped, aliased, and - der-sampled. Super-resolution technique intelligently fuses the incomplete scene information from several consecutive low-resolution frames to reconstruct a hi- resolution representation of the original scene. In the last decade, with the advent of new technologies in both civil and mi- tary domain, more computer vision applications are being developed with a demand for high-quality high-resolution images. In fact, the demand for high- resolution images is exponentially increasing and the camera manufacturing te- nology is unable to cope up due to cost efficiency and other practical reasons. |
Contents
Introduction to SuperResolution | 1 |
Overview of SuperResolution Techniques | 9 |
IterativeInterpolation SuperResolution IISR | 18 |
Optimization Approach to SuperResolution Image Reconstruction | 51 |
Image Registration for SuperResolution | 77 |
Software Framework | 93 |
Conclusion and Future Directions | 104 |
References | 109 |
Other editions - View all
Iterative-Interpolation Super-Resolution Image Reconstruction: A ... Vivek Bannore Limited preview - 2009 |
Iterative-Interpolation Super-Resolution Image Reconstruction: A ... Vivek Bannore No preview available - 2009 |
Iterative-Interpolation Super-Resolution Image Reconstruction: A ... Vivek Bannore No preview available - 2010 |
Common terms and phrases
accuracy accurate algorithm aliased approximation Bannore blur computational cost computer vision computer vision applications corrupted LR frames Cubic Polynomial down-sampling error frequency function Gaussian geometrically warped Graphical User Interface grid image high-resolution image IEEE IISR scheme IISR system IISR technique IISR-generated high-resolution image ill-conditioned ill-posed problem image pyramid image registration image super-resolution imaging process interpolation kernel interpolation techniques inverse problem ISBN ISRO Linear low-resolution frames low-resolution images LR images medical imaging method motion estimation noise corrupted LR noiseless LR frames number of iterations number of low-resolution number of LR optical flow optimal value optimization procedure pixels problem of super-resolution PSNR reconstruction process reconstruction quality registration technique regularization matrix regularization parameter regularization term resolution frames resolution images RMSE sampling ratio sensor shown in fig Sinc Lanczos super-resolution image reconstruction super-resolution reconstruction super-resolution techniques Tikhonov regularization translationally shifted true scene under-sampled low-resolution