Local Grayvalue Invariants for Image Retrieval
IEEE Transactions on Pattern Analysis and Machine Intelligence
What Is the Set of Images of an Object Under All Possible Illumination Conditions?
International Journal of Computer Vision
Computer Vision: A Modern Approach
Computer Vision: A Modern Approach
Non-uniform sampling for improved appearance-based models
Pattern Recognition Letters
Comparing Images under Variable Illumination
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Illumination Cones for Recognition under Variable Lighting: Faces
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Illumination insensitive recognition using eigenspaces
Computer Vision and Image Understanding
| Hi-index | 0.00 |
The appearance of an object can be greatly affected by the changes in illumination conditions in the scene where that object is seen. In this paper, we propose a novel method for building appearance-based models that are tolerant to lighting variations. This new approach is based on a Non-Uniform Sampling technique, so that we use a very small number of images for generating those models, and this reduces the computing time and storage space required for the modeling stage, with respect to Uniform Sampling techniques. We have tested the proposed algorithm with a comprehensive set of objects with different appearance, and the high recognition rate obtained in these experiments shows the effectiveness of the proposed method. Also, the necessary time to compute the associated manifold in eigenspace is dramatically reduced.