The edge detection of hyperspectral image based on its proportion image

Intensity-based edge detectors cannot distinguish whether an edge is caused by material changes. Therefore, our aim is to classify the physical cause of an edge using hyperspectral obtained by a spectrograph. A method is presented to detect edges in hyperspectral images. Analyzing proportion images of a hyperspectral image, we implement edge detection of the hyperspectral image by using its proportion images. In edge part of hyperspectral image, the endmembers proportion of mixed pixels is very small value. Edge detection can be implemented through these the distinctness of endmember proportion in edge part. The method of edge detection is called edge detection based proportion image about hyperspectral images.

[1]  Horst Bunke,et al.  Range Image Segmentation: Adaptive Grouping of Edges into Regions , 1998, ACCV.

[2]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  J. Boardman.  Using dark current data to estimate AVIRIS noise covariance and improve spectral analyses , 1995 .

[4]  Bahram Parvin,et al.  B-rep object description from multiple range views , 1996, International Journal of Computer Vision.

[5]  Peter Meer,et al.  Edge Detection with Embedded Confidence , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Yanjun Gong,et al.  Convex geometry analysis method of hyperspectral data , 2003, SPIE Asia-Pacific Remote Sensing.

[7]  R. Bajcsy,et al.  Color image segmentation with detection of highlights and local illumination induced by inter-reflections , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[8]  Zhensen Wu,et al.  The study of the proportion image of hyperspectral image , 2005, SPIE/COS Photonics Asia.

[9]  Tom Chen,et al.  A real-time high performance edge detector for computer vision applications , 1997, Proceedings of ASP-DAC '97: Asia and South Pacific Design Automation Conference.

[10]  Gudrun Klinker,et al.  A physical approach to color image understanding , 1989, International Journal of Computer Vision.

[11]  Zhensen Wu,et al.  The selection of inherent channels of hyperspectral data with volume method , 2005, SPIE/COS Photonics Asia.