Evaluation of edge detection for panchromatic remote sensing image based on ROC curve

Man Peng; Shanshan Li

doi:10.1117/12.750499

14 November 2007 Evaluation of edge detection for panchromatic remote sensing image based on ROC curve

Man Peng, Shanshan Li

Proceedings Volume 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications; 67902B (2007) https://doi.org/10.1117/12.750499
Event: International Symposium on Multispectral Image Processing and Pattern Recognition, 2007, Wuhan, China

Abstract

ROC (Receiver Operating Characteristic) analysis has been widely used to evaluate detection performance. It solves binary hypothesis testing problems. It is difficult to get real edge of remote sensing image. As a result, they are not directly looked as hypothesis testing problem. In this paper, we first introduce a method to generate reference edge map (REM). Using two sets of synthetic image to test its robustness. Edge detectors are tested on three panchromatic remote sensing images, and then we generate test ROC curves based on REM and compute the area under the curves. Quantitative results are discussed.

Citation Download Citation

Man Peng and Shanshan Li "Evaluation of edge detection for panchromatic remote sensing image based on ROC curve", Proc. SPIE 6790, MIPPR 2007: Remote Sensing and GIS Data Processing and Applications; and Innovative Multispectral Technology and Applications, 67902B (14 November 2007); https://doi.org/10.1117/12.750499

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available