Binary filters for pattern classification

被引：0

作者：

Venkatesh, Santosh S. ^{[1
]}

Psaltis, Demetri ^{[1
]}

机构：

[1] California Inst of Technology, Dep, of Electrical Engineering, Pasadena,, CA, USA

来源：

IEEE Transactions on Acoustics, Speech, and Signal Processing | 1992年 / v卷 / 0n期

关键词：

Electric Filters; Digital - Mathematical Techniques--Integral Equations - Mathematical Transformations--Fourier Transforms - Pattern Recognition - Signal Processing--Correlation Detectors;

D O I：

暂无

中图分类号：

学科分类号：

摘要：

Generalized Fourier correlators imposing finite system space-bandwidth products are described, and a class of binary filters is proposed. In pattern classification and signal registration applications, it is shown that for a particular class of signals, the binary filters yield the same asymptotic performance as the matched filter. It is hence adduced that a dynamic range of a single bit in the filter suffices for classification purposes. The effects of statistical sidelobe fluctuations and a finite system space-bandwidth product are included in the analysis. It is demonstrated that performance improves in a natural fashion with increase in the space-bandwidth product for both the binary filter and the matched filter.

引用

页码：604 / 611