The Conformal Monogenic Signal
Proceedings of the 30th DAGM symposium on Pattern Recognition
Computing Isophotes on Free-Form Surfaces Based on Support Function Approximation
Proceedings of the 13th IMA International Conference on Mathematics of Surfaces XIII
Webcam-Based Visual Gaze Estimation
ICIAP '09 Proceedings of the 15th International Conference on Image Analysis and Processing
Isocentric color saliency in images
ICIP'09 Proceedings of the 16th IEEE international conference on Image processing
Image Analysis by Conformal Embedding
Journal of Mathematical Imaging and Vision
Hi-index | 0.00 |
Usually, object detection is performed directly on (normalized) gray values or gray primitives like gradients or Haar-like features. In that case the learning of relationships between gray primitives, that describe the structure of the object, is the complete responsibility of theclassifier. We propose to apply more knowledge about the image structure in the preprocessing step, by computing local isophote directions and curvatures, in order to supply the classifier with much more informative image structure features. However, a periodic feature space, like orientation, is unsuited for common classification methods. Therefore, we split orientation into two more suitable components. Experiments show that the isophote features result in better detection performance than intensities, gradients or Haar-like features.