In recent years the use of local characteristics has become one of the dominant approaches to content based object recognition. The detection of interest points is the first step in the process of matching or recognition. A local approach significantly improves and accelerates image retrieval from databases. Therefore a reliable algorithm for feature detection is crucial for many applications. In this thesis we propose a novel approach for detecting characteristic points in an image. Our approach is invariant to geometric and photometric transformations, which frequently appear between scenes viewed in different conditions.We emphasize the problem of invariance to affine transformations. This transformation is particularly important as it c...
International audienceIn this paper we summarize recent progress on local photometric invariants. Th...
The main advantage of using local invariant features is their local character which yields robustnes...
The main advantage of using local invariant features is their local character which yields robustnes...
In recent years the use of local characteristics has become one of the dominant approaches to conten...
In recent years the use of local characteristics has become one of the dominant approaches to conten...
Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our m...
This paper approaches the problem of finding correspondences between images in which there are large...
International audienceThis paper presents a novel approach for detecting affine invariant interest p...
While the understanding of the image content is relatively easy for most humans, an automatic analys...
Abstract — This paper is concerned with the problem of feature point registration and scene recognit...
In this research report we propose a novel approach to build interest points and descriptors which a...
We present a new method to perform reliable matching between different images. This method exploits ...
National audienceThis paper presents a new method for image matching in the presence of large scale ...
We present a new method to perform reliable matching between different images. This method finds com...
Abstract. In this paper we propose a novel approach for detecting interest points invariant to scale...
International audienceIn this paper we summarize recent progress on local photometric invariants. Th...
The main advantage of using local invariant features is their local character which yields robustnes...
The main advantage of using local invariant features is their local character which yields robustnes...
In recent years the use of local characteristics has become one of the dominant approaches to conten...
In recent years the use of local characteristics has become one of the dominant approaches to conten...
Abstract. This paper presents a novel approach for detecting affine invariant interest points. Our m...
This paper approaches the problem of finding correspondences between images in which there are large...
International audienceThis paper presents a novel approach for detecting affine invariant interest p...
While the understanding of the image content is relatively easy for most humans, an automatic analys...
Abstract — This paper is concerned with the problem of feature point registration and scene recognit...
In this research report we propose a novel approach to build interest points and descriptors which a...
We present a new method to perform reliable matching between different images. This method exploits ...
National audienceThis paper presents a new method for image matching in the presence of large scale ...
We present a new method to perform reliable matching between different images. This method finds com...
Abstract. In this paper we propose a novel approach for detecting interest points invariant to scale...
International audienceIn this paper we summarize recent progress on local photometric invariants. Th...
The main advantage of using local invariant features is their local character which yields robustnes...
The main advantage of using local invariant features is their local character which yields robustnes...