The IRIM group is a consortium of French teams working on Multimedia Indexing and Retrieval. This paper describes our participation to the TRECVID 2008 High Level Features detection task. We evaluated several fusion strategies and especially rank fusion. Results show that including as many low-level and intermediate features as possible is the best strategy, that SIFT features are very importan...

...somewhat. We extracted, partitioned and described contours, histogrammed their geometric parameters and concatenated the histograms to form a single image vector with which we classified the plant images using a Linear Discriminant Analysis (LDA); that is, no segmentation or saliency selection was performed. Despite the obvious simplicity of the LDA classification we reached the middle of th...

In this paper, we describe a method of shape-based 3D model retrieval that employs a set of 3D, local, multi-scale features extracted from a voxel representation of a 3D model to be compared. The method first convert a surface based 3D model into a voxel model. Then, a novel 3D extension of the popular 2D image feature, the Scale Invariant Feature Transform by David Lowe, is applied to extract ...

India, having less awareness towards the deaf and dumb peoples leads to increase the communication gap between deaf and hard hearing community. Sign language is commonly developed for deaf and hard hearing peoples to convey their message by generating the different sign pattern. The scale invariant feature transform has been used to perform reliable matching between different images of the same...

This paper applies statistical design principles to a simple biological model of human vision so that we can more clearly interpret the apparent role of eye saccades. In doing so we show that many structural features of the biological system (such as the optical geometry of the retina) are strategies for minimising the resources required to construct a working image recognition system. The idea...

In this paper we present a stereo feature-based method using SIFT (Scale-invariant feature transform) descriptors. We use automatic feature extractors, matching algorithms between images and techniques of robust estimation to produce a DTM (Digital Terrain Model) using convergent shots of a rock glacier.The geomorphologic structure observed in this study is the Veleta rock glacier (Sierra Nevad...

This paper focuses on the hand gesture recognition using the various feature extraction techniques and SVM as a classifier. Her we have proposed the hybrid approach using SIFT and HoG combined as a feature extraction technique and gestures classification done using SVM linear kernel function.The accumulative multi class SVM method is employed in order to obtain a classification of the multiple ...

Introduction Building robust low-level image representations, beyond edge primitives, is a long-standing goal in vision. In its most basic form, an image is a matrix of intensities. How we should progress from this matrix to stable mid-level representations, useful for high-level vision tasks, remains unclear. Popular feature representations such as SIFT or HOG spatially pool edge information t...

An intuitive three-dimensional task-oriented coverage model for 3D multi-camera networks based on fuzzy sets is presented. The model captures the vagueness inherent in the concept of visual coverage, with a specific target of the feature detection and matching task. The coverage degree predicted by the model is validated against various multi-camera network configurations using the SIFT feature...

Local feature matching has become a commonly used method to compare images. For mobile robots, a reliable method for comparing images can constitute a key component for localization and loop closing tasks. In this paper, we address the issues of outdoor appearance-based topological localization for a mobile robot over time. Our data sets, each consisting of a large number of panoramic images, h...