Research projects | Description |
|
Compact multi-cue vocabularies We propose a novel approach for constructing multi-cue Portmanteau vocabularies for image classification. |
|
Object Recoloring based on Intrinsic Image Estimation In this research we decompose the image into its intrinsic reflectance components with the aim to recolor scenes. |
|
Color Constancy On this website links to color constancy research, available code, and data bases can be found. |
|
Discriminative Pyramids for Object and Scene Recognition (+code) In this research we address the high dimenssionality of spatial pyramids, which is generally considered to be its most serious disadvantage. |
|
Physics-based color image segmentation (+code) Based on an analysis of the bi-directional reflection model we propose a method which is particularly suited for segmentation in the presence of shadow and highlight edges. |
|
Color attention for object recognition (+code) We propose a novel image representation where color attention is used to sample the shape description of the image. |
|
Color Feature Detection for Object Recognition (+code) Luminance edges are still the main source of information in the state-of-the-art methods for feature detection. We propose to exploit the statistical structure of luminance and color in natural images to extract the most discriminative features from the viewpoint of information theory for object recognition. |
|
VOC PASCAL 2009 image classification challenge The CVC obtained the second position in the classification challenge, and obtained the best score on 2 out of the 20 classes. |
|
VOC PASCAL 2009 image segmentation challenge The CVC obtained the second position in the segmenation challenge, winning 6 out of 20 classes. |
|
||
|
Contact
webmaster | Last updated: Monday 11
May 2009
|
