Spatial Super Resolution Based Image Reconstruction udusing IBP and Evolutionary Method ud

摘要

Spatial image resolution explains about the pixel spacing in a digital image. As a udresult more the number of pixels more detailed visibility of information contained in the udimage. Increasing the sensor elements per unit area in camera is the solution to high udresolution images but at higher cost, since increase in camera resolution increases the cost of udthe camera. Another limitation to this is hardware part of the camera i.e. we cannot minimize udthe sensor element size beyond the optimum limit. Therefore an imaging system with udinadequate sensor array will generate low resolution image which causes pixelization effect udin them. udTo resolve the above problem software level techniques are adopted. Interpolation of uda 2D signal improves the size of the image with additional row and column values. As udinterpolation averages pixel intensity with neighboring pixels and assigns the result to new udpixels in HR image, the HR image loses edge information because of blurring or aliasing. To udimprove image resolution while avoiding aliasing effect we are using Super Resolution udImage Reconstruction technique. As the application of image reconstruction in Computer udTomography (CT) is capturing multiple 2D images with known depth information can create ud3D picture of an infected tissue, here we are using multiple number of low resolution images udwith subpixel shift that provide non-redundant information about the scene and generate a udHR image with more high frequency details. udThis reconstruction problem uses iterative back projection technique along with udevolutionary techniques for optimization. In our image observation model, three lacunae of udLR images have been considered, i.e. relative motion between scene and camera, sensor blur udand down-sampling during image acquisition. In the inverse model we use the above udcalculated parameters in back projection. Iteratively the reverse model is solved to find the udHR image; this method is also called as gradient based method. As the gradient remains udconstant over here, the solution it provides may not be the best and hence the requirement of udoptimization technique. The nature inspired optimization algorithm used here is Cuckoo udoptimization algorithm with Lèvy flights. i