1. PROBLEM STATEMENT Tracking of regions in image sequences plays a fundamental role in important applications (search and retrieval in video databases, object based coding such as in MPEG-4, surveillance), and although numerous approaches to region tracking have been developed, they all suffer from severe constraints imposed on the nature of the image sequence. Some assume a particular motion ...

The structured regions in an image usually contain important clues for information understanding. Proper extraction of those regions is often a key to success for a computer vision system. In this work, we propose a method to detect the irregularly arranged region-ofinterest with a fixed structure. Different from the existing techniques, our approach is able to deal with more influential factor...

Local feature descriptors are widely used in many computer vision applications. Over the past couple of decades, several local feature descriptors have been proposed which are robust to challenging conditions. Since they show different characteristics in different environment, it is necessary to evaluate their performance in an intensive and consistent manner. However, there has been no relevan...

This paper describes a method for video retrieval system based on local invariant region descriptors. A novel framework is proposed for combined video segmentation, content extraction and retrieval. A similarity measure, previously proposed by the authors based on local region features, is used for video segmentation. The local regions are tracked throughout a shot and stable features are extra...

In this work, we study local feature extraction methods and evaluate their performance in detecting local features from the salient regions of images. In order to measure the detectors’ performance, we compared the detected regions to gaze fixations obtained from the eye movement recordings of human participants viewing two types of images: natural images (photographs) and abstract/surreal imag...

This paper presents a new method for multiobjective optimisation based on gradient projection and local region search. The gradient projection is conducted through the identi®cation of normal vectors of an ecient frontier. The projection of the gradient of a nonlinear utility function onto the tangent plane of the ecient frontier at a given ef®cient solution leads to the de®nition of a feasib...

Face recognition in real-world applications is often hindered by uncontrolled settings including pose, expression, and illumination changes, and/or ageing. Additional challenges related to changes in facial appearance due to plastic surgery have become apparent recently. We exploit the fact that plastic surgery bears on appearance in a non-uniform fashion using a recognition approach that integ...

We used the FUSE (Far Ultraviolet Spectroscopic Explorer) satellite to observe O VI emission along two sightlines towards the edge of the interaction zone (IZ) between the Loop I superbubble and the Local Bubble. One sightline was chosen because material in the interaction zone blocks distant X-ray emission, and should thus do the same for non-local O VI emission. We measured an O VI intensity ...

In modern days the increasing social networking mediums with digital images are uploaded day by day. Image Retrieval using image content is the interesting field in digital image processing improves pictorial information for human interpretation and processing of image data for storage, transmission, and representation for machine perception. Content-Based Image Retrieval (CBIR) and querying ac...