This paper reports about an implementation of a search engine for visual information content, which has been developed in the context of the forthcoming MPEG-7 standard. The system supports similarity-based retrieval of visual (image and video) data along feature axes like color, texture, shape and geometry. The descriptors for these features have been developed in a way such that invariance ag...

This paper introduces a visual language for active database systems. We present a new approach to database programming based on visual active language that allows us to describe active rules in a graphical way. The resulting visual language can be transformed into a textual one. In addition, an active system can be represented with several diierent graphs showing the interactions of rules and t...

This report describes continued work on the intelligibility of the stimuli contained in the Hoosier Audiovisual Multi-Talker Database (Sheffert, Lachs, & Hernandez, 1997). All the stimuli in the database have now been tested using three different presentation conditions: audio-visual, audio-only, and visual only. A re-analysis of the audio-visual data, together with new analyses of the data obt...

ImageNet is a large scale and publicly available image database. It currently offers more than 14 millions of images, organised according to the WordNet hierarchy. One of the main objective of the creators is to provide to the research community a relevant database for visual recognition applications such as object recognition, image classification or object localisation. However, only a few vi...

Searching and managing large archives of visual data, such as images and video, is made hard by the lack of proper integration between the visual aspects of the problem (image processing, motion estimation, feature extraction...) and its database aspects (defining visual data as data types in a database). In this paper, we argue that image database languages can be built based on feature algebr...

This paper describes the audio-visual database collected at AT&T Labs{Research for the study of bimodal speech recognition. To date, this database consists of two multiple speaker parts, namely isolated confusable words and connected letters, thus allowing the study of some popular and relatively simple speaker independent audio-visual recognition tasks. In addition, a single speaker connected ...

This paper describes simple designing methods of corpus-based visual speech synthesis. Our approach needs only a synchronous real image and speech database. Visual speech is synthesized by concatenating real image segments and speech segments selected from the database. In order to automatically perform all processes, e.g. feature extraction, segment selection and segment concatenation, we simp...