Augustin Lux

Learn More
We propose a method of constructing computer vision systems using a workbench based on a rich extensible toolbox and a general-purpose kernel. The toolbox provides access to an open set of libraries; the kernel provides incremental dynamic system construction and interactivity. This method makes it possible to quickly develop and test new algorithms,(More)
Face recognition is a challenging task due to the large variety of appearance that a face may exhibit under variations in illumination and viewing position as well as variations in facial expression. Many of the more successful approaches use Gabor wavelets as an image descriptor, resulting in relatively high computational cost. In this work, we have(More)
Current methods of object recognition require generally a feature extraction phase. Several feature types have been studied. In this article, we suggest using ridges. Our purpose is to study a simple, but robust method which allows to extract the ridges in an image at several scales. These ridges are used to build object models. The experiments show that(More)
We investigate the use of two visual descriptors: Local Binary Patterns-Three Orthogonal Planes(LBP-TOP) and Dense Trajectories for depression assessment on the AVEC 2014 challenge dataset. We encode the visual information generated by the two descriptors using Fisher Vector encoding which has been shown to be one of the best performing methods to encode(More)
We address the problem of determining if a given image region contains people or not, when environmental conditions such as viewpoint, illumination and distance of people from the camera are changing. We develop three generic approaches to discriminate between visual classes: ridge-based structural models, ridge-normalized gradient histograms, and linear(More)
To compute the Tensorial representation, first we divide each BGn (θ) of each image into non-overlapping rectangular sub-regions with a specific size. A set of histograms is then computed for each sub-region and finally each histogram is organized in four different 3-D tensors, where each tensor corresponds to an specific derivative order of the Binary(More)
Résumé— Cet article présente une méthode pour détecter des caractéristiques de type pic et crête dans une image. Ces caractéristiques seront utilisées pour la modélisation et la reconnaissance d’objets. Un point de type crête ou pic est caractérisé localement par des propriétés géométriques de la conique tangente à la surface-image. Deux critères sont(More)
This paper presents a method for object detection based on a cascade of scale and orientation normalized Gaussian derivative classifiers learnt with Adaboost. Normalized Gaussian derivatives provide a small but powerful feature set for rapid learning using Adaboost. Real time detection is made possible by use of a fast integer coefficient algorithm that(More)