23 March 1998 Classification of product inspection items using nonlinear features
Author Affiliations +
Abstract
Automated processing and classification of real-time x-ray images of randomly oriented touching pistachio nuts is discussed. The ultimate objective is the development of a system for automated non-invasive detection of defective product items on a conveyor belt. This approach involves two main steps: preprocessing and classification. Preprocessing locates individual items and segments ones that touch using a modified watershed algorithm. The second stage involves extraction of features that allow discrimination between damaged and clean items (pistachio nuts). This feature extraction and classification stage is the new aspect of this paper. We use a new nonlinear feature extraction scheme called the maximum representation and discriminating feature (MRDF) extraction method to compute nonlinear features that are used as inputs to a classifier. The MRDF is shown to provide better classification and a better ROC (receiver operating characteristic) curve than other methods.
© (1998) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ashit Talukder, Ashit Talukder, David P. Casasent, David P. Casasent, H.-W. Lee, H.-W. Lee, } "Classification of product inspection items using nonlinear features", Proc. SPIE 3386, Optical Pattern Recognition IX, (23 March 1998); doi: 10.1117/12.304761; https://doi.org/10.1117/12.304761
PROCEEDINGS
12 PAGES


SHARE
Back to Top