Feature Detection by Color Tensor-Based Photometric Invariants

Abstract:

Article Preview

Although the majority of images are recorded in color format nowadays, computer vision research is still mostly restricted to luminance-based feature detection. In this paper, we combine the features based on the color tensor with photometric invariant derivatives to arrive at photometric invariant features. The combination of the photometric invariance theory and tensor based features allows for detection of a variety of features such as photometric invariant edges, corners. Experiments show that the proposed features are robust to scene incidental events and perform well in real-world scene.

Info:

Periodical:

Advanced Materials Research (Volumes 341-342)

Edited by:

Liu Guiping

Pages:

540-545

DOI:

10.4028/www.scientific.net/AMR.341-342.540

Citation:

X. S. Yuan and Z. Z. Wang, "Feature Detection by Color Tensor-Based Photometric Invariants", Advanced Materials Research, Vols. 341-342, pp. 540-545, 2012

Online since:

September 2011

Export:

Price:

$35.00

In order to see related information, you need to Login.

In order to see related information, you need to Login.