No abstract

Abstract

A proposal for a queried-by-sketch image retrieval system is introduced as an alternative to text-based image search on the Web. The user will create a sketch as a query that will be matched with the edges extracted from natural images. The main challenge regarding edge detection for Content-based Image Retrieval consists in finding edges for larger regions and avoiding the ones corresponding to textures. For this purpose, a combination of selective smoothing and color segmentation is applied prior edge extraction. An evolutionary algorithm is deployed to optimize the image-processing parameters. Similarity between the user´s sketch and the image's edges will be measured regarding two local aspects: spatial proximity and edge orientation. A full architecture for image search on the Web is proposed and preliminary results are reported using a trial database. I.

Collaborative Browsing has experienced an increasing popularity as a topic for both, academic research and commercial sofmare development, due mainly to the promise that it represents as an enabling technologv for distant collaboration. Several areas are adequate for the application of this paradigm.In this paper, we present the results of an overview analysis of diSferent proposals found in the literature, and show their main dflerences from the point of view of the conceptual models they use, and the practical solutions they provide. Based on this overview, we propose a framework for the design of Collaborative Browsing Systems. Finally, we focus on the framework instantiation for the conceptual model and architecture we started to develop.

No abstract