Optimal Gabor filter-based edge detection of high spatial resolution remotely sensed images

Haohao Zhao; Pengfeng Xiao; Xuezhi Feng

doi:10.1117/1.JRS.11.015019

9 March 2017 Optimal Gabor filter-based edge detection of high spatial resolution remotely sensed images

Haohao Zhao, Pengfeng Xiao, Xuezhi Feng

Author Affiliations +

Journal of Applied Remote Sensing, Vol. 11, Issue 1, 015019 (March 2017). https://doi.org/10.1117/1.JRS.11.015019

Abstract

Edge extraction from high spatial resolution (HSR) remotely sensed images is one of the essential tasks for image segmentation and object identification. We present an optimal Gabor-based edge detection method which mainly focuses on selecting optimal parameters, including central frequency and spectrum scale, for Gabor filter. The central frequency is automatically optimized by phase randomization and the human visual system-based structure similarity index. Next, the optimal spectrum scale is determined based on two-dimensional power spectrum density. The edge detection method is comprehensively discussed in the analysis of parameter sensitivity, overall performance, and comparative tests with several widely used methods. Qualitative and quantitative experimental studies, performed on six test images with various spatial resolution, show that the proposed method provides a promising solution to edge detection from HSR remotely sensed images.

Citation Download Citation

Haohao Zhao, Pengfeng Xiao, and Xuezhi Feng "Optimal Gabor filter-based edge detection of high spatial resolution remotely sensed images," Journal of Applied Remote Sensing 11(1), 015019 (9 March 2017). https://doi.org/10.1117/1.JRS.11.015019

Received: 18 October 2016; Accepted: 22 February 2017; Published: 9 March 2017

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