Title :
The application of structure tensor in ddge detection
Author :
Keli, Wen ; Zhaoyu, Pian
Author_Institution :
Changchun Inst. of Technol., Changchun, China
Abstract :
This paper proposes a novel approach for edge detection by first applying the structure tensor. The method firstly presents the definition of scale vector by analyzing the structure tensor, to calculate the weight between two graph-nodes. The nature of structure tensor helps the new features retain more structure information of image, and that makes the detection more accurately. In addition, the paper also presents an anisotropy filter, replacing the Gaussian function, to average the structure tensor. The new filtering function makes structure tensor retain more information of complicated structure. In experiments conducted on various images, the algorithm shows a notable visual improvement.
Keywords :
Gaussian processes; computer vision; edge detection; tensors; Gaussian function; anisotropy filter; complicated structure; edge detection; filtering function; graph node; image information; notable visual improvement; scale vector; structure tensor; Educational institutions; Feature extraction; Lead; Tensile stress; anisotropy filter; anisotropy structure tensor; edge detection; structure tensor;
Conference_Titel :
Computer Application and System Modeling (ICCASM), 2010 International Conference on
Conference_Location :
Taiyuan
Print_ISBN :
978-1-4244-7235-2
Electronic_ISBN :
978-1-4244-7237-6
DOI :
10.1109/ICCASM.2010.5620068