High Speed Implementation Of Linear Feature Extraction Algorithms

Hassan Mostafavi; Mukesh Shah

doi:10.1117/12.936657

9 January 1984 High Speed Implementation Of Linear Feature Extraction Algorithms

Hassan Mostafavi, Mukesh Shah

Proceedings Volume 0432, Applications of Digital Image Processing VI; (1984) https://doi.org/10.1117/12.936657
Event: 27th Annual Technical Symposium, 1983, San Diego, United States

Abstract

This paper describes a novel digital implementation of the Hough Transform for high speed extraction of linear features from images of complex scenes. In addition to detection, the Hough Transform estimates both location and orientation of a linear feature. The implementation is based on using the image intensity histogram generator that is available as a high speed hardware feature on some commercial digital image display and processors. It is shown that linear feature extraction is reduced to detection of peaks in a number of onedimensional histogram arrays. The number of histogram generation operations is equal to the number of angles into which the 0°-18° range is quantized. Using this method, the processing time for extraction of a linear feature using 16 angles is on the order of 0.5 second. Unlike regular implementations of the Hough Transform, the amount of computation is completely independent of the number of detected pixels (pixels with value 1) in the binary input image to the Rough Transform.

Citation Download Citation

Hassan Mostafavi and Mukesh Shah "High Speed Implementation Of Linear Feature Extraction Algorithms", Proc. SPIE 0432, Applications of Digital Image Processing VI, (9 January 1984); https://doi.org/10.1117/12.936657

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