Pierre Buyssens

Learn More
We present a Multiscale Convolutional Neural Network (MCNN) approach for vision–based classification of cells. Based on several deep Convolutional Neural Networks (CNN) acting at different resolutions, the proposed architecture avoid the classical handcrafted features extraction step, by processing features extraction and classification as a whole. The(More)
In this paper, we propose two major improvements to the exemplar-based image inpainting algorithm, initially formulated by Criminisi et al. [1]. First, we introduce a structure-tensor-based data-term for a better selection of pixel candidates to fill in based on priority. Then, we propose a new lookup heuristic in order to locate the best source patches to(More)
We present a low resolution face recognition technique based on a special type of convolutional neural network which is trained to extract facial features from face images and project them onto a low–dimensional space. The network is trained to reconstruct a reference image chosen beforehand, and it has been applied in visible and infrared light. Since the(More)
We describe an Eikonal-based algorithm for computing dense oversegmentation of an image, often called superpixels. This oversegmentation respect local image boundaries while limiting undersegmentation. The proposed algorithm relies on a region growing scheme, where the potential map used is not xed and evolves during the di usion. Re nement steps are also(More)
A previous study of the effect of zinc deprivation on Mycobacterium bovis BCG pointed out the potential importance of an alcohol dehydrogenase for maintaining the hydrophobic character of the cell envelope. In this report, the effect of the overexpression of the M. bovis BCG alcohol dehydrogenase (ADH) in Mycobacterium smegmatis and M. bovis BCG is(More)
This paper proposes a technical review of exemplar-based inpainting approaches with a particular focus on greedy methods. Several comparative and illustrative experiments are provided to deeply explore and enlighten these methods, and to have a better understanding on the state-of-the-art improvements of these approaches. From this analysis, three(More)
Heat-shock proteins (Hsps) from various origins are known to share a conserved structure and are assumed to be key partners in the biogenesis of proteins. Fractionation of the mycobacterial Hsp60, a 65 kDa protein also called Cpn60, from Mycobacterium bovis BCG zinc-deficient culture filtrate on phenyl-Sepharose followed by Western blotting revealed the(More)
We present a study on different levels of visible and infrared modalities fusion for face recognition. While visible modality is the most natural way to recognize someone, infrared presents thermal distribution that can be useful for face recognition. We compare the well-known eigenfaces method as a baseline to an approach based on sparsity for the feature(More)
In this paper we propose an approach to inpaint holes in depth maps that appear when synthesizing virtual views from a RGB-D scenes. Based on a superpixel oversegmentation of both the original and synthesized views, the proposed approach efficiently deals with many occlusion situations where most of previous approaches fail. The use of superpixels makes the(More)
We propose to tackle the problem of RGB-D image disocclusion inpainting when synthesizing new views of a scene by changing its viewpoint. Indeed, such a process creates holes both in depth and color images. First, we propose a novel algorithm to perform depth-map disocclusion inpainting. Our intuitive approach works particularly well for recovering the lost(More)