A physical approach to color image understanding
International Journal of Computer Vision
Separation of Reflection Components Using Color and Polarization
International Journal of Computer Vision
Topographic Maps and Local Contrast Changes in Natural Images
International Journal of Computer Vision
Edge Detection by Helmholtz Principle
Journal of Mathematical Imaging and Vision
Geometry and Color in Natural Images
Journal of Mathematical Imaging and Vision
Solving for Colour Constancy using a Constrained Dichromatic Reflection Model
International Journal of Computer Vision
Optimal Level Curves and Global Minimizers of Cost Functionals in Image Segmentation
Journal of Mathematical Imaging and Vision
Topographic Maps of Color Images
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Extracting Meaningful Curves from Images
Journal of Mathematical Imaging and Vision
Image Analysis and Mathematical Morphology
Image Analysis and Mathematical Morphology
Level Lines Selection with Variational Models for Segmentation and Encoding
Journal of Mathematical Imaging and Vision
Efficient cumulative matching for image registration
Image and Vision Computing
Fast computation of a contrast-invariant image representation
IEEE Transactions on Image Processing
Light speed labeling for Risc architectures
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Body color sets: A compact and reliable representation of images
Journal of Visual Communication and Image Representation
Mixed color/level lines and their stereo- matching with a modified Hausdorff distance
Integrated Computer-Aided Engineering
Light speed labeling: efficient connected component labeling on RISC architectures
Journal of Real-Time Image Processing
Detecting pedestrians on a Movement Feature Space
Pattern Recognition
Enhancing a disparity map by color segmentation
Integrated Computer-Aided Engineering
Hi-index | 0.00 |
Topographic maps are an interesting alternative to edge-based techniques common in computer vision applications. Indeed, unlike edges, level lines are closed and less sensitive to external parameters. They provide a compact geometrical representation of images and they are, to some extent, robust to contrast changes. The aim of this paper is to propose a novel and vectorial representation of color topographic maps. In contrast with existing color topographic maps, it does not require any color conversion. For this purpose, our technique refers to the dichromatic reflectance model, which explains the distribution of colors as the mixture of two reflectance components, related either to the body or to the specular reflection. Thus, instead of defining the topographic map along the sole luminance direction in the RGB space, we propose to design color lines along each dominant color vector, from the body reflection. Experimental results show that this approach provides a better tradeoff between the compactness and the quality of a topographic map.