Natural shape detection based on principal component analysis

Ashok Samal; Prasana A. Iyengar

doi:10.1117/12.148220

1 July 1993 Natural shape detection based on principal component analysis

Ashok Samal, Prasana A. Iyengar

Author Affiliations +

Journal of Electronic Imaging, Vol. 2, Issue 3, (July 1993). https://doi.org/10.1117/12.148220

Abstract

The classical Hough transform, the generalized Hough transforms, and their extensions are quite robust for detection of a large class of objects that can be categorized as industrial parts. These objects are rigid and have fixed shapes, i.e., different instances of the same object are more or less identical. These techniques, and indeed most current techniques, however, do not adequately handle shapes that are more flexible. These shapes are widely found in nature and are characterized by the fact that different instances of the same shape are similar, but not identical, e.g., leaves and flowers. We present a new technique to recognize natural shapes, based on principal component analysis. A set of basis shapes are obtained using principal component analysis. A Hough-like technique is used to detect the basis shapes. The results are then combined to locate the shape in the image. Experimental results show that the approach is robust, accurate, and fast.

Citation Download Citation

Ashok Samal and Prasana A. Iyengar "Natural shape detection based on principal component analysis," Journal of Electronic Imaging 2(3), (1 July 1993). https://doi.org/10.1117/12.148220

Published: 1 July 1993

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