Abstract
Invariant moments can be used to describe the basic characteristics of visual pattern.1 Thus they can be employed as a criterion in measuring the performance of different neural networks. Numerical analysis of the convergence of several neural network models based on invariant moment measurement has been conducted. Moment invariant image descriptors are used to develop a shift, scale, and rotation invariant neural network.
© 1989 Optical Society of America
PDF ArticleMore Like This
Morris Lee
MA1 Image Understanding and Machine Vision (IUMV) 1989
Margaret E. Sereno
WJ5 OSA Annual Meeting (FIO) 1989
Yuri Owechko
MD4 Optical Computing (IP) 1989