Patrick Hède

Learn More
Pattern recognition and image recognition methods are commonly developed and tested using testbeds, which contain known responses to a query set. Until now, testbeds available for image analysis and content-based image retrieval (CBIR) have been scarce and small-scale. Here we present the one million images CEAList Image Collection (CLIC) testbed that we(More)
As well as words in text processing, image regions are polysemic and need some disambiguation. If the set of representations of two different objects are close or intersecting, a region that is in the intersection will be recognized as being possibly both objects. We propose here a way to disambiguate regions using some knowledge on relative spatial(More)
We describe building a large-scale image ontology using the WordNet lexical resources. This ontology is based on English words identifying portrayable objects. We reviewed the upper structure and interconnections of WordNet and selected only the branches leading to portrayable objects. This article explains our pruning approach to WordNet. The words, which(More)
Shared evaluation tasks have become popular over the last decades as ways of making communities of researchers advance together. This paper presents the organization of five new shared task evaluation campaigns for image indexing and retrieval. We have designed these campaigns based on our previous experience of participating in or organizing various text(More)
In our effort to contribute to the closing of the "semantic gap" between images and their semantic description, we are building a large-scale ontology of images of objects. This visual catalog will contain a large number of images of objects, structured in a hierarchical catalog, allowing image processing researchers to derive signatures for wide classes of(More)
Image annotation is frequently used in image base management. Unfortunately, manual keyword indexing is costly and not exempt of errors for large image bases. In this article, we present a method for automatic image description in natural language for images without problems of occlusion. This method relies on a double expertise in image indexation and(More)
When building an e-learning system, we need a way of organizing the information to be presented to the user. Formal ontologies are one way of resolving this knowledge structuring task. The main use of ontologies in e-learning systems concerns the modelling of the domain of interest and this is equally our approach. Here we present a technique for(More)