This thesis addresses the use of color in image processing and computer vision. Two problems are studied: - illuminant estimation, - local descriptors matching for color images comparison. Achromatic surfaces are defined as surfaces reflecting a spectrum with the same frequency dsitribution than the illuminant. Consequently, revovering these surfaces allows to estimate the illuminant. Assuming that the range of colors taken by an illuminant is limited (Planck equation), it is possible to select the pixels belonging to a potentially gray surface. A voting procedure is then applied to select one or more illuminants. The proposed algorithm has many advantages: it is effective, intuitive, does not rely on a learning phase and requires only few ...
The PhD thesis objective is to study a colour’s correct and complete processing, respecting metrolog...
AbstractAre surfaces’ colours judged from weighted averages of the light that they reflect to the ey...
Color features are the key-elements widely used in content-analysis and retrieval. However, most of ...
This thesis addresses the use of color in image processing and computer vision. Two problems are stu...
Cette thèse traite de l’utilisation de la couleur en vision par ordinateur. Deux problèmes sont étud...
International audienceAlthough color is commonly experienced as an indispensable quality in describi...
[[abstract]]In computer vision, color has always played an important role. Color can provide critica...
Image matching is a key step for many computer vision applications. Among all the approaches existin...
In this paper, we compare local colour descriptors to grey-value descriptors. We adopt the evaluatio...
Color is the main source of information particularly for content-analysis and retrieval. Most of the...
This work deals with stereo-vision and more precisely matching of pixels using correlation measures....
This work deals with stereo-vision and more precisely matching of pixels using correlation measures....
International audienceColor description is a challenging task because of large variations in RGB val...
Scale invariance and color invariance are two critical characters of robust local descriptors. For s...
International audienceColor description is a challenging task because of large variations in RGB val...
The PhD thesis objective is to study a colour’s correct and complete processing, respecting metrolog...
AbstractAre surfaces’ colours judged from weighted averages of the light that they reflect to the ey...
Color features are the key-elements widely used in content-analysis and retrieval. However, most of ...
This thesis addresses the use of color in image processing and computer vision. Two problems are stu...
Cette thèse traite de l’utilisation de la couleur en vision par ordinateur. Deux problèmes sont étud...
International audienceAlthough color is commonly experienced as an indispensable quality in describi...
[[abstract]]In computer vision, color has always played an important role. Color can provide critica...
Image matching is a key step for many computer vision applications. Among all the approaches existin...
In this paper, we compare local colour descriptors to grey-value descriptors. We adopt the evaluatio...
Color is the main source of information particularly for content-analysis and retrieval. Most of the...
This work deals with stereo-vision and more precisely matching of pixels using correlation measures....
This work deals with stereo-vision and more precisely matching of pixels using correlation measures....
International audienceColor description is a challenging task because of large variations in RGB val...
Scale invariance and color invariance are two critical characters of robust local descriptors. For s...
International audienceColor description is a challenging task because of large variations in RGB val...
The PhD thesis objective is to study a colour’s correct and complete processing, respecting metrolog...
AbstractAre surfaces’ colours judged from weighted averages of the light that they reflect to the ey...
Color features are the key-elements widely used in content-analysis and retrieval. However, most of ...