The general topic of this dissertation is the comparison of images, which is treated both as a local and a global issue via several applications. We are first interested in object recognition task based on local descriptors. We propose a complete, robust and automatic system for multiple object recognition, which relies on two methodological approaches: the “a contrario” detection theory and the optimal mass transport theory of Monge-Kantorovich. In the latter framework, a dissimilarity measure is introduced for the comparison of SIFT-like descriptors relying on the optimal transportation cost between circular histograms (Circular Earth Mover's Distance). A matching criterion of local descriptors based on the a contrario methodology is then...
This report addresses precise image search based on local descriptors. Our approach extends a k-NN v...
This dissertation focuses on designing image recognition systems which are robust to geometric varia...
Nowadays computer vision algorithms can be found abundantly in applications relatedto video surveill...
The general topic of this dissertation is the comparison of images, which is treated both as a local...
Sets of local features that are invariant to common image transformations are an effective represent...
International audienceIn this paper we propose a comprehensive framework that allows existing local ...
International audienceMany computer vision algorithms make use of local features, and rely on a syst...
Many applications, as in computer vision or medicine, aim at identifying the similarities between se...
Abstract. We investigate the properties of a metric between two distributions, the Earth Mover’s Dis...
Object recognition is one of the most active fields of computer vision. In this thesis we consider t...
We introduce a metric between two distributions that we call the Earth Mover's Distance (EMD). ...
In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feat...
In this thesis, we first present a contribution to overcome this problem of robustness for the recog...
International audienceThe Earth Mover's Distance (EMD) is a metric based on the theory of optimal tr...
This report addresses precise image search based on local descriptors. Our approach extends a k-NN v...
This dissertation focuses on designing image recognition systems which are robust to geometric varia...
Nowadays computer vision algorithms can be found abundantly in applications relatedto video surveill...
The general topic of this dissertation is the comparison of images, which is treated both as a local...
Sets of local features that are invariant to common image transformations are an effective represent...
International audienceIn this paper we propose a comprehensive framework that allows existing local ...
International audienceMany computer vision algorithms make use of local features, and rely on a syst...
Many applications, as in computer vision or medicine, aim at identifying the similarities between se...
Abstract. We investigate the properties of a metric between two distributions, the Earth Mover’s Dis...
Object recognition is one of the most active fields of computer vision. In this thesis we consider t...
We introduce a metric between two distributions that we call the Earth Mover's Distance (EMD). ...
In this paper, we present a new approach for matching local descriptors such as Scale Invariant Feat...
In this thesis, we first present a contribution to overcome this problem of robustness for the recog...
International audienceThe Earth Mover's Distance (EMD) is a metric based on the theory of optimal tr...
This report addresses precise image search based on local descriptors. Our approach extends a k-NN v...
This dissertation focuses on designing image recognition systems which are robust to geometric varia...
Nowadays computer vision algorithms can be found abundantly in applications relatedto video surveill...