Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geometric relationships among the local features are ignored. This paper presents new features, called pairwise features (PWF), which encode both the appearance and the spatio-temporal relations of the local features for action recognition. First STIPs are extracted, then PWFs are constructed by grouping pairs of STIPs which are both close in space and close in time. We propose a combination of two codebooks for video representation. Experiments on two standard human action datasets: the KTH dataset and the Weizmann dataset show that the proposed approach outperforms most existing methods.

GMM based algorithms have become the de facto standard for background subtraction in video sequences, mainly because of their ability to track multiple background distributions, which allows them to handle complex scenes including moving trees, flags moving in the wind etc. However, it is not always easy to determine which distributions of the mixture belong to the background and which distributions belong to the foreground, which disturbs the results of the labeling process for each pixel. In this work we tackle this problem by taking the labeling decision together for all pixels of several consecutive frames minimizing a global energy function taking into account spatial and temporal relationships. A discrete approximative optical-flow like motion model is integrated into the energy function and solved with Ishikawa's convex graph cuts algorithm.

We propose in this paper a definition of the normal law on the space of strings. This definition allows generations of sets of strings that have controlled statistical features. Moreover, we apply with success a method of estimation of the mean and standard deviation of a normal string distribution.

In this paper, we present a novel approach for face recognition, using a new subspace method called bilinear discriminant analysis (BDA) and normalized radial basis function networks (NRBFNs). In a first step, BDA extracts the features that enhance separation between classes by using a generalized bilinear projection-based Fisher criterion, computed from image matrices directly. In a second step, the features are fed into a NRBFN that learns class conditional probabilities. This results in an efficient and computationally simple open-world identification process. Experimental results assess the performance and robustness of the proposed algorithm compared to other subspace methods combined with NRBFNs, in the presence of variations in head poses, facial expressions, and partial occlusions.

The use of interest points in content-based image retrieval allows the image index to represent local properties of the image. Classic corner detectors can be used for this purpose. However, they have drawbacks when applied to various natural images for image retrieval, because visual features need not be corners and corners may gather in small regions. We present a salient point detector that extract points where variations occur in the image, whether they are corner-like or not. The detector is based on the wavelet transform to detect global variations as well as local ones. The wavelet-based salient points are evaluated for image retrieval with a retrieval system using texture features. In this experiment our method provides better retrieval performance compared with other point detectors.

Content based image retrieval is the task of searching images from a database, which are visually similar to a given example image. We present methods for content based image retrieval based on texture similarity using interest points and Gabor features. Interest point detectors are used in computer vision to detect image points with special properties, which can be geometric (corners) or non-geometric (contrast etc.). Gabor functions and Gabor filters are regarded as excellent tools for feature extraction and texture segmentation. The article combines these methods and generates a textural description of images. Special emphasis is devoted to distance measures on texture descriptions. Experimental results of a query system are given.

This paper presents the overall scheme of an indexation system for broadcast video designed for very large databases. We discuss features which can possibly be extracted from a video sequence so as to be used for "queries by example". We present examples of semantic features (query by content) like text reading, face localisation and classification. As this study is still at its infancy, we point out the key features and temporary achievements and present some temporary results.

We present a system to automatically select images in an image database in order to be used as an illustration of an image processing or analysis process. This question is related to the teleteaching of image processing using already implemented libraries of algorithms, in the context of a teleteaching European project. We first give a Bayesian approach of the problem, with the use of image basis. Then we present how to use the Haar transform for this purpose. Finally, we give examples and discuss our approach.

The matching of an object, a region of an image segmentation, to a template is a heavy computation process and is not very robust. We represent an object by a region adjacency graph (RAG) on the top of which a pyramid (a decreasing sequence of RAG) is built according to a set of rules, which verify some uniqueness and uniformity properties. The contraction process preserves the structure of the RAG across the pyramid's levels, and the rules are chosen according to the characteristics of the template. By building such a pyramid and then by a top-down process to match all the sub-graphs we have a linear parallel complexity time, with a robust match and a partial match relative to the given set of rules.

We propose to study the relationship between the hierarchical Hough transform and classical algorithms for partitioning curves into segments. We show that the set of segments found by classical algorithms is a subset of the segments found by the hierarchical Hough transform. This new relationship allows us to have a better understanding of the behavior of some parameters of the hierarchical Hough transform.

A clustering algorithm based on the minimum volume ellipsoid (MVE) robust estimator is proposed. The MVE estimator identifies the least volume region containing h percent of the data points. The clustering algorithm iteratively partitions the space into clusters without prior information about their number. At each iteration, the MVE estimator is applied several times with values of h decreasing from 0.5. A cluster is hypothesized for each ellipsoid. The shapes of these clusters are compared with shapes corresponding to a known unimodal distribution by the Kolmogorov-Smirnov test. The best fitting cluster is then removed from the space, and a new iteration starts. Constrained random sampling keeps the computation low. The clustering algorithm was successfully applied to several computer vision problems formulated in the feature space paradigm: multithresholding of gray level images, analysis of the Hough space, and range image segmentation.>

A blind noise variance algorithm that recovers the variance of noise in two steps is proposed. The sample variances are computed for square cells tessellating the noise image. Several tessellations are applied with the size of the cells increasing fourfold for consecutive tessellations. The four smallest sample variance values are retained for each tessellation and combined through an outlier analysis into one estimate. The different tessellations thus yield a variance estimate sequence. The value of the noise variance is determined from this variance estimate sequence. The blind noise variance algorithm is applied to 500 noisy 256*256 images. In 98% of the cases, the relative estimation error was less than 0.2 with an average error of 0.06. Application of the algorithm to differently sized images is also discussed.>