Whilst storage and capture technologies are able to cope with huge numbers of images, image retrieval is in danger of rendering many repositories valueless because of the difficulty of access. This paper proposes a similarity measure that imposes only very weak assumptions on the nature of the features used in the recognition process. This approach does not make use of a pre-defined set of feature measurements which are extracted from a query image and used to match those from database images, but instead generates features on a trial and error basis during the calculation of the similarity measure. This has the significant advantage that features that determine similarity can match whatever image property is important in a particular region whether it be a shape, a texture, a colour or a combination of all three. It means that effort is expended searching for the best feature for the region rather than expecting that a fixed feature set will perform optimally over the whole area of an image and over every image in a database. The similarity measure is evaluated on a problem of distinguishing similar shapes in sets of black and white symbols.
This paper details work undertaken on the application of an algorithm for visual attention (VA) to region of interest (ROI) coding in JPEG 2000 (JP2K). In this way, an ''interest ordered'' progressive bit-stream is produced where the regions highlighted by the VA algorithm are presented first in bit-stream. The paper briefly outlines the terminology used in JP2K, the packet structure of the bit-stream, and the methods available to achieve ROI coding in JP2K (tiling, coefficient scaling, and code-block selection). The paper then describes how the output of the VA algorithm is post-processed so that an ROI is produced that can be efficiently coded using coefficient scaling in JP2K. Finally, a two alternative forced choice (2AFC) visual trial is undertaken to compare the visual quality of images encoded using the proposed VA ROI algorithm and conventional JP2K. The experimental results show that, while there is no overall preference for the VA ROI encoded images; there is an improvement in perceived image quality at low bit rates (below 0.25 bits per pixel). It is concluded that an overall increase in image quality only occurs when the increase in quality of the ROI more than compensates for the decrease in quality of the image background (i.e., non-ROI).
This paper proposes a novel video sequence matching method based on temporal ordinal measurements. Each frame is divided into a grid and corresponding grids along a time series are sorted in an ordinal ranking sequence, which gives a global and local description of temporal variation. A video sequence matching means not only finding which video a query belongs to, but also a precise temporal localization. Robustness and discriminability are two important issues of video sequence matching. A quantitative method is also presented to measure the robustness and discriminability attributes of the matching methods. Experiments are conducted on a BBC open news archive with a comparison of several methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.