Invariant representation and hierarchical network for inspection of nuts from X-ray images
✍ Scribed by A. Sim; B. Parvin; P. Keagy
- Publisher
- John Wiley and Sons
- Year
- 1996
- Tongue
- English
- Weight
- 730 KB
- Volume
- 7
- Category
- Article
- ISSN
- 0899-9457
No coin nor oath required. For personal study only.
✦ Synopsis
An X-ray based system for the inspection of pistachio nuts and wheat kernels for internal insect infestation is presented. The novelty of this system is twofold. First, we construct an invariant representation of infested nuts from X-ray images that is rich, robust, and compact. Insect infestation creates a tunnel, in the X-ray image, with reduced density of the natural material. The tunneling effect is encoded by linking troughs on the image and constructing a joint curvatureproximity distribution table for each nut. The latter step is designed to accentuate separation of those tunneling effects that are due to the natural structure of the nut. Second, since the representation is sparse, we partition the joint distribution table into several regions, where each region is used independently to train a backpropagation (BP) network. The outputs of these subnets are then collectively trained with another BP network. We show that the resulting hierarchical network has the advantage of reduced dimensionality while maintaining a performance similar to the standard BP network. o 1996 John Wiley & Sons, Inc.
1. Introduction
We present a system that has been developed for inspection of pistachio nuts and wheat kernels viewed with an X-ray sensor. The X-ray device reveals internal defects that cannot be otherwise detected by external evidences in the visible domain. Presently, pistachio nuts are inspected for external damages, and a sample of wheat kernels are X-rayed for manual inspection at the mill. In the case of pistachio nuts, we are interested in elimination of aflatoxin contamination [23]. (Aflatoxin is a natural carcinogenic compound, and its concentration is limited by the U.S. and European regulatory agencies.) However, there is a strong correlation between contamination and insect infestation. In the case of wheat kernels, we are interested in rejecting those wheat kernels that are infested with maized weevil.
The main novelty of this article is twofold: First, we derive an invariant representation that captures pertinent information on infested as well as noninfested nuts; second, we show that by partitioning this invariant representation, a classifier with reduced dimensionality can be constructed. From a geometric perspective, infestation can be characterized by a dark tunneling appearance in the X-ray image. The tunnel corresponds to the reduced density of the natural content of the nut and to the replacement of that content