Advancements in Computer Vision and Image Processing
Abstract
Interest in computer vision and image processing has grown in recent years with the advancement of everyday technologies such as smartphones, computer games, and social robotics. These advancements have allowed for advanced algorithms that have improved the processing capabilities of these technologies. Advancements in Computer Vision and Image Processing is a critical scholarly resource that explores the impact of new technologies on computer vision and image processing methods in everyday life. Featuring coverage on a wide range of topics including 3D visual localization, cellular automata-based structures, and eye and face recognition, this book is geared toward academicians, technology professionals, engineers, students, and researchers seeking current research on the development of sophisticated algorithms to process images and videos in real time.
http://vislab.ucr.edu/PUBLICATIONS/pubs/Journal%20and%20Conference%20Papers/after10-1-1997/Conference/2011/Improved%20Image%20Super-Resolution%20by%20Support%2011.pdf
Support Vector Machine (SVM) can construct a hyperplane in a high or infinite dimensional space which can be used for classification. Its regression version, Support Vector Regression (SVR) has been used in various image processing tasks. In this paper, we develop an image super-resolution algorithm based on SVR. Experiments demonstrated that our proposed method with limited training samples outperforms some of the state-of-the-art approaches and during the super- resolution process the model learned by SVR is robust to reconstruct edges and fine details in various testing images. I. INTRODUCTION ith the wide spread application of video cameras, surveillance systems and hand-held devices that are equipped with moderate image sensors, it is desirable to generate images or video streams with high quality while not increasing the cost of the hardware. The imaging process of these sensors can be modeled by
In many applications, like surveillance, image sequences are of poor quality. Motion blur in particular introduces significant image degradation. An interesting challenge is to merge these many images into one high-quality, estimated still. We propose a method to achieve this. Firstly, an object of interest is tracked through the sequence using region based matching. Secondly, degradation of images is modelled in terms of pixel sampling, defocus blur and motion blur. Motion blur direction and magnitude are estimated from tracked displacements. Finally, a high-resolution deblurred image is reconstructed. The approach is illustrated with video sequences of moving people and blurred script.
Print-from-video can be achieved by using super-resolution techniques. These techniques involve combining information from multiple low resolution images to generate and print a high resolution image. Among the existing super-resolution techniques, the most suitable one for deployment on portable consumer electronics products, in particular on cell-phones, that have limited processing and memory resources is the shift-and-add approach. However, this approach is known to generate artifacts when applied to real video sequences. This paper introduces a number of improvements made to the shift-and-add approach in terms of frame alignment, frame selection, and frame fusion to reduce such artifacts in computationally efficient manner. In addition, a post-processing step named pattern filtering is applied to reduce visual artifacts in printed images. The effectiveness of the developed solution is demonstrated by showing both quantitative and qualitative comparison results for video sequences captured by cell-phone cameras<sup>1</sup>.
ResearchGate has not been able to resolve any references for this publication.