Abstract

Abstract
The primary goal of the research on image segmentation is to produce better segmentation algorithms. In spite of almost 50 years of research and development in this Held, the general problem of splitting in image into meaningful regions remains unsolved. New and emerging techniques are constantly being applied with reduced Success. The design of each of these new segmentation algorithms requires spending careful attention judging the effectiveness of the technique. This paper demonstrates how the proposed methodology is well suited to perform a quantitative comparison between image segmentation algorithms using I ground-truth segmentation. It consists of a general framework already partially proposed in the literature, but dispersed over several works. The framework is based on the principle of eliminating the minimum number of elements Such that a specified condition is met. This rule translates directly into a global optimization procedure and the intersection-graph between two partitions emerges as the natural tool to solve it. The objective of this paper is to summarize, aggregate and extend the dispersed work. The principle is clarified, presented striped of unnecessary supports and extended to sequences of images. Our Study shows that the proposed framework for segmentation performance evaluation is simple, general and mathematically sound.

Abstract
Object detection and tracking is an essential preliminary task in event analysis systems (e.g. visual surveillance). Typically objects are extracted and tagged, forming representative tracks of their activity. Tagging is Usually performed by probabilistic data association, however, in systems capturing disjoint areas it is often not possible to establish such associations, as data may have been collected at different times OF in different locations. In this case, appearance matching is a valuable aid. We propose using bag-of-visterms, i.e. an histogram of quantized local feature descriptors, to represent and match tracked objects. This method has proven to be effective for object matching and classification in image retrieval applications, where descriptors can be extracted a priori. An important difference in event analysis systems is that relevant information is typically restricted to the foreground. Descriptors can, therefore, be extracted faster, approaching real-time requirements. Also, unlike image retrieval, objects can change over time and therefore their model needs to be updated Continuously. Incremental or adaptive learning is used to tackle this problem. Using independent tracks of 30 different persons, we show that the bag-of-visterms representation effectively discriminates visual object tracks and that it presents high resilience to incorrect object segmentation. Additionally, this methodology allows the construction of scalable object models that can be used to match tracks across independent views.

Abstract

Abstract
Automatic biometric identification based on fingerprints is still one of the most reliable identification method in criminal and forensic applications. A critical step in fingerprint analysis without human intervention is to automatically and reliably extract singular points from the input fingerprint images. These singular points (cores and deltas) not only represent the characteristics of local ridge patterns but also determine the topological structure (i.e., fingerprint type) and largely influence the orientation field. Poincaré Index-based methods are one of the most common for singular points detection. However, these methods usually result in many spurious detections. Therefore, we propose an enhanced version of the method presented by Zhou et al. [13] that introduced a feature called DORIC to improve the detection. Our principal contribution lies in the adoption of a smoothed orientation field and in the formulation of a new algorithm to analyze the DORIC feature. Experimental results show that the proposed algorithm is accurate and robust, giving better results than the best reported results so far, with improvements in the range of 5% to 7%. © 2009 IEEE.

Abstract
Biased photorefractive media are known to admit bright and dark solitons. The bright solitons in these media are always stable, but their dark counterparts are unstable above a certain background intensity and below a critical velocity. We use the stability criterion and the Vakhitov-Kolokolov function to precisely determine the unstable-parameter region. We also predict the strength of the instability by determining the unstable eigenvalues and eigenmodes using the Evans function method. Numerical simulation of the full evolution equation confirms the results.