Share Email Print

Proceedings Paper

Nonlint material identification using computer vision and pattern recognition
Author(s): Michael A. Lieberman; Rajendra B. Patil
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper discusses methods used to evaluate a feature space for identification of non-lint material (trash) in cotton samples. A main criterion for accepting any feature in the identification task was invariance under translation, rotation, and, in most cases, scale. In subsequent processing, most features were normalized. Classical grouping was performed in an n-dimensional feature space using divisive hierarchical clustering based on the Euclidian distance metric. The best results for identifying bark, stick, and leaf/pepper trash in the sample data set was 92%. By category, bark was identified correctly 88%, stick 84%, and leaf/pepper 94% of the time. Identification between leaf and pepper could be handled by defining an area cutoff in the pepper-leaf continuum.

Paper Details

Date Published: 12 May 1993
PDF: 11 pages
Proc. SPIE 1836, Optics in Agriculture and Forestry, (12 May 1993); doi: 10.1117/12.144023
Show Author Affiliations
Michael A. Lieberman, USDA Agricultual Research Service (United States)
Rajendra B. Patil, New Mexico State Univ. (United States)

Published in SPIE Proceedings Vol. 1836:
Optics in Agriculture and Forestry
James A. DeShazer; George E. Meyer, Editor(s)

© SPIE. Terms of Use
Back to Top