Sharif Digital Repository

Sparse signal representations and its applications has been a hot topic of research in recent years. It has been demonstrated that sparsity prior can be effectively used as a regularization term to solve many of the inverse problems. One of these problems in which sparse representations have been used is image super-resolution (SR). SR is the problem of finding a high resolution (HR) image from one or several low resolution (LR) images. In this dissertation, we have focused on the problem of finding a HR image from only one LR image which is known as example-based SR. There are two kinds of methods for example-based SR: the methods which use neighborhood embedding and the methods which use... 

Today digital imaging systems have been widely used due to their ease of use and proper costs, but still they suffer from low contrast and resolution. Because of technical limits and expensiveness of hardware, software techniques like super resolution have been used. By super resolution we mean increasing the density of an image’s pixels. Super resolution can be categorized as “single image super resolution” and “multi-image super resolution”. Single image super resolution is applied on a low quality image which has blur and/or noise of environment and imaging system and increases its quality and density to an acceptable level. In multi-image super resolution some auxiliary images captured... 

Nowadays, millimeter-wave imaging is widely used in security and medical applications. The growing threat from terrorist attacks is driven research on novel ways to enhance security inspection systems. Millimeter-wave imaging not only is an effective option of penetrating into dielectric materials including cloth, but also provides suitable imaging resolution. Moreover, millimeter-wave imaging is capable of identifying different materials making it a promising option for concealed weapon detection. In spite of X-ray, millimeter-wave imaging is non-ionizing, allowing for non-invasive imaging. In this thesis, first we investigate different millimeter-wave imaging systems and reconstruction... 

The resolution is one of the most essential factors in radar imaging. The range and cross-range resolution are inversely proportional to the radar bandwidth and the angular width, respectively. Increasing the bandwidth requires upgrading the hardware of radars and the cost of this procedure is high. Also, to increase the angular width, we need more time to scan the scene from different angles but due to reasons such as movements of targets in the scene, it is unachievable.According to these limitations, we can utilize some signal processing techniques to Improve the radar resolution. Super resolution algorithms are the common approaches to achieving this goal. In this research, we proposed a... 

Image super-resolution is the process of estimating a high-quality image from a low-quality image. With the growth of remote sensing images, computer games, and the development of artificial intelligence applications in medical image analysis, research in this area of machine vision has seen significant growth. In recent years, research on super-resolution has primarily focused on the development of unsupervised models, blind networks, and the use of optimization methods in non-blind models. However, limited research has discussed the loss function in the super-resolution process. The majority of those studies have only used perceptual similarity in a conventional way. This is while the...