6533b85dfe1ef96bd12bdc70

RESEARCH PRODUCT

Intelligent eye

subject

description

This paper describes Intelligent Eye, a mobile phone interactive leisure guide that offers location-based multimedia information. The information offered is related to the user's position, so the main goal of this work is the development of an efficient system to detect where the user is pointing his/her camera at by means of a content-based image retrieval algorithm (CBIR). The CBIR procedure uses color histograms in the HS color space extracted from images, and employs Kullback-Leibler divergence as the similarity measure. Intelligent Eye can be used in a wide range of camera-equipped mobile phones; however, efficiency is improved if GPS data is available. In order to outperform other systems we have made use of a video stream in the classification process instead of using still images. Moreover, the image database can be populated dynamically by means of a feedback procedure with images taken by users. We report preliminary results of the prototype working with real images obtaining a hit classification rate of 96%.