Prospects for Classifying Complex Imagery Using a Self-Organizing Neural Network
Abstract
The objective of this study is to evaluate the performance of Fukushima's Neocognitron model when it is applied to complex imagery. This system could discriminate between simple alphabetical characters represented in fields of 16 by 16 pixels, and that shift invariance can be achieved through a proper choice of design parameters. This work describes results for expanded Neocognitron architectures operating on complex images of 128 by 128 pixels. These neural network systems were simulated on a VAX-8600 minicomputer. Wire frame models of three different vehicles were used to test the properties which Fukushima had demonstrated. The expanded Neocognitron systems were able to classify these objects and to identify their critical features. After training, each object was placed at different positions in the plane, and the Neocognitron's shift invariance property was tested. With complex (128 X 128) imagery, it was difficult to achieve proper classification and maintain shift invariance using only a few levels. In another experiment, the Neocognitron trained on polar transforms of objects in the training set. Objects in the training set were rotated, and polar transforms of the rotated images were submitted as input. In this manner, the Neocognitron's shift invariance was exploited to recognize rotated imagery. These investigations gave insight into the role of various model parameters and their proper values, as well as demonstrating the model's applicability to complex images. Keywords: Neural network; Shift invariance; Rotation invariance; Image classification; Unsupervised learning; Multilayer architecture; Parallel computing.
Document Details
- Document Type
- Technical Report
- Publication Date
- Jan 11, 1989
- Accession Number
- ADA206208
Entities
People
- K. G. Heinemann
- M. M. Menon
Organizations
- Massachusetts Institute of Technology