Image Representation in Differential Space

Authors:
Shengzhi Du;Barend Jacobus Wyk;M. Antonie Wyk;Guoyuan Qi;Xinghui Zhang;Chunling Tu
Affiliations:
French South Africa Technical Institute of Electronics (FSATIE), Tshwane University of Technology, Pretoria 0001;French South Africa Technical Institute of Electronics (FSATIE), Tshwane University of Technology, Pretoria 0001;French South Africa Technical Institute of Electronics (FSATIE), Tshwane University of Technology, Pretoria 0001;French South Africa Technical Institute of Electronics (FSATIE), Tshwane University of Technology, Pretoria 0001;Tianjin University of Technology and Education, Tianjin, P.R. China 300222;French South Africa Technical Institute of Electronics (FSATIE), Tshwane University of Technology, Pretoria 0001
Venue:
ISVC '08 Proceedings of the 4th International Symposium on Advances in Visual Computing, Part II
Year:
2008

Citing 4
Cited 0

High-Order Differentiation Filters that Work

IEEE Transactions on Pattern Analysis and Machine Intelligence
Affine Invariant Detection: Edges, Active Contours, and Segments

CVPR '96 Proceedings of the 1996 Conference on Computer Vision and Pattern Recognition (CVPR '96)
An Affine Invariant Region Detector Using the 4th Differential Invariant

ICTAI '07 Proceedings of the 19th IEEE International Conference on Tools with Artificial Intelligence - Volume 01
Combining color and shape information for illumination-viewpoint invariant object recognition

IEEE Transactions on Image Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, a derivative estimator is introduced to obtain differential information of images. Experiments show that differentials obtained by this estimator outperform the traditional Sobel operator and this estimator is practical for extracting differential image information. A new image representation in this differential space is also proposed. Differential sign sequences of images are used as the signature of image patterns. The Hamming distance is used for template matching. The proposed representation is invariant to brightness and contrast and is robust to noise because of the low pass property of the estimator. Template matching is used as an example to exhibit the advantage of this representation. Experiments demonstrate good performance of the proposed method.