Theses and Dissertations
Permanent URI for this collectionhttp://ir.daiict.ac.in/handle/123456789/1
Browse
2 results
Search Results
Item Open Access Practical approach for depth estimation and image restoration using defocus cue(Dhirubhai Ambani Institute of Information and Communication Technology, 2011) Ranipa, Keyur R.; Joshi, Manjunath V.Reconstruction of depth from 2D images is an important research issue in computer vision. Depth from defocus (DFD) technique uses space varying blurring of an image as a cue in reconstructing the 3D structure of a scene. In this thesis we explore the regularization based approach for simultaneous estimation of depth and image restoration from defocused observations. We are given two defocused observations of a scene that are captured with di erent camera parameters. Our method consists of two steps. First we obtain the initial estimates for the depth as well as for the focused image. In the second step we re ne the solution by using a fast optimization technique. Here we use the classic depth recovery method due to Subbarao for ob- taining the initial depth map and Wiener lter approach for initial image restoration. Since the problem we are solving is ill-posed and does not yield unique solution, it is necessary to regularize the solution by imposing additional constraint to restrict the solution space. The regularization is performed by imposing smoothness constraint only. However, for preserving the depth and image intensity discontinuities, they are indenti ed prior to the minimization process from initial estimates of the depth map and the restored image. The nal solution is obtained by using computationally e client gradient descent algorithm, thus avoiding the need for computationally taxing algorithms. The depth as well as intensity edge details of the nal solution correspond to those obtained using the initial estimates. The experimental results indicate that the quality of the restored image is found to be satisfactory even under severe space-varying blur conditions.Item Open Access Single frame superresolution(Dhirubhai Ambani Institute of Information and Communication Technology, 2008) Sattaru, Annamnaidu; Joshi, Manjunath V.Super-resolving an image from single frame observation image. In many cases more than one low resolution observations may not be available, need high spatial resolution images e.g. medical imaging, remote sensing etc.. We obtain the estimate of the high frequency (edges) contents by learning the wavelet coefficients from a database of similar or arbitrary high resolution images. We then employ a suitable regularization approach for edge preservation as well as for ensuring spatial continuity among pixels. The learnt wavelet coefficients are used as edge prior. An Markov Random Field (MRF) model is used for spatial dependence. The final cost function consists of data fitting term and two regularization terms, which is minimized by global optimizing (Gradient Decent) method. The experiments conducted on real images show considerable improvement both perceptually and quantitatively when compared to conventional interpolation (Bicubic Interpolation images) methods. The advantage of the proposed technique is that unlike many other super-resolution techniques, a number of low resolution observations are not required. Finally instead of MRF we used Inhomogeneous markov random field(IGMRF) for maintain the spatial dependency effectively in super-resolved image, the results show that its better than MRF prior.