Catálogo de publicaciones - libros

This paper surveys some of the existing techniques and systems for content-based indexing and retrieval of two main types of multimedia data – images and videos. Furthermore, some of our recent work are reported. Specifically, in content-based image retrieval, we have proposed multi-scale color histograms by incorporating color and spatial information. In content-based video retrieval, we have proposed a new level of program between story/event and video sequence levels. Video summarization results are given based on the scene clustering results.

Matching techniques are part-and-parcel of shape recognition. A coarse-to-fine method is presented which finds point correspondence between open or closed curves and is invariant to various image deformations, including affine transformation, perspective distortion, non-rigid motion and so forth. The method is inspired by the idea to use point correspondences established at one level to generate a priori information, which is either topological or geometric, to match features at finer levels. This has all been achieved through an analysis of the curve topology and a synthesis of the B-spline interpolation techniques. This is in contrast to existing multi-scale methods for curve matching that use pure feature correlation or 3D structure recovery at a fixed scale. The presented method proves to be robust and accurate and can serve as a powerful aid to measure similarity of shape, as demonstrated in various experiments on real images.

P2P computing is gaining more and more attention from both academia and industrial communities for its potential to reconstruct current distributed applications on the Internet. However, the basic DHT-based P2P systems support only queries. Ranked queries produce results that are ordered by certain computed scores, which have become widely used in many applications relying on relational databases, where users do not expect exact answers to their queries, but instead a ranked set of the objects that best match their preferences. By combing P2P computing and ranked query processing, this paper addresses the problem of providing ranked queries support in Peer-to-Peer (P2P) networks, and introduces efficient algorithms to solve this problem. Considering that the existing algorithms for ranked queries consume an excessive amount of bandwidth when they are applied directly into the scenario of P2P networks, we propose two new algorithms: for ranked selection queries and for ranked join queries. and reduce bandwidth cost by pruning irrelevant tuples before query processing. Performance of the proposed algorithms are validated by extensive experiments.