Search

This paper describes a BioAPI compatible Architecture for mobile biometric fingerprint identification and verification, based on a XML Web Service and a Field Programmable Gate Array (FPGA). We present a client-server system that uses a Personal Digital Assistant (PDA) with a built-in fingerprint sensor and wireless LAN (WLAN) connectivity as a mobile client, and a Biometric Service Provider (BSP) running as a BioAPI compatible XML Web Service on the server side. BioAPI high level functions enrolment, identification and verification are implemented using BSP primitives, capture, process,createtemplate, verifymatch, and identifymatch that are partially hardware implemented using Handel-C and the Celoxica RC1000-PP platform.

This paper analyzes different ways of coupling the information from multiple visual features in the representation of visual contents using temporal models based on Markov chains. We assume that the optimal combination is given by the Cartesian product of all feature state spaces. Simpler model structures are obtained by assuming independencies between random variables in the probabilistic structure. The relative entropy provides a measure of the information loss of a simplified structure with respect to a more complex one. The loss of information is then compared to the loss of accuracy in the representation of visual contents in video sequences, which is measured in terms of shot retrieval performance. We reach three main conclusions: (1) the full-coupled model structure is an accurate approximation to the Cartesian product structure, (2) the largest loss of information is found when direct temporal dependencies are removed, and (3) there is a direct relationship between loss of information and loss of representation accuracy.

We present a shot segmentation method based on the representation of visual contents in video using a coupled Markov chains approach. This representation allows us to combine different image features and to keep information about all the images since the beginning of the shot, instead of simply comparing adjacent frames. We also define an adaptative detection threshold that depends on the distance measures that are obtained, instead of trying to find a fixed threshold. Results show that the combination of color and motion image features in the same representation provides a more robust detection of shot boundaries than using each feature separately.

The color appearance of digital video imagery acquired from analog sources is affected by intrinsic device imperfections. Although the human visual system (HVS) is capable of perceiving color variations when comparing different acquisitions of the same video, it is able to identify the colors in an isolated image as well. Color based computer vision processes applied within digital video libraries do not have this capability and their performance is severely reduced. This paper presents a method for modeling the intrinsic color appearance given by acquisition devices. It is based on the approximation of the distribution of colors generated by a device using a mixture of Gaussians in RGB space. Its parameters are encoded in a specifically designed pattern, which provides a dense estimation of the distribution of colors along the whole RGB space. In this way, the model can be attached to every acquired video in order to put its original color appearance on record. The approximation by mixtures of Gaussians lets us define transformations between them that preserve the identity of colors. This fact is shown in the case of skin color segmentation, where the underlying concept of color is captured from samples obtained by a particular device. Other applications of color correction in digital video are pointed out in this paper as well.

TV commercials recognition is a need for advertisers in order to check the fulfillment of their contracts with TV stations. In this paper we present an approach to this problem based on compacting a representative frame of each shot by a PCA of its color histogram. We also present a new algorithm for scene break detection based on the analysis of local color variations in consecutive frames of some specific regions of the image.