Design of a bipolar composite filter by a simulated annealing algorithm

Yin, Shizhuo; Lü, Mingzhe; Chen, Chulung; Yu, Francis T. S.; Hudson, Tracy D.; McMillen, Deanna K.

doi:10.1364/ol.20.001409

Cited by 19 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We have fixed the position of f at the origin so that r = 0. The phase (r'), defined as 4(r,") =2tvr' (10) comes about by translating g relative to f•.…”

Section: Hetero-associative Filtermentioning

confidence: 99%

<title>Different weighting approaches for performing heterogeneous correlation</title>

Khoury

Gianino

Woods

2002

Optical Pattern Recognition XIII

View full text Add to dashboard Cite

In this paper we introduce three weighting algorithms for performing shift-invariant heterogeneous phase-restricted correlation filters that are capable of identifying an object as belonging to a certain class while rejecting any object that is not a member ofthat class. We compare the performance ofthese highly discriminative filters to the performance of the phase-only filter, and the non-discriminative matche4 correlation filter, in similar circumstances. Even when the proposed filters achieved proper classification, the intensities ofthe correlations from heterogeneous targets (hetero-correlations) were much smaller than those from homogeneous targets (autocorrelation). To increase the intensities ofthese hetero-correlation peaks relative to the autocorrelation peaks, we also introduced a fractional power law into the filter's transfer function, thereby controlling the rejection capability of the filter.

show abstract

“…We have fixed the position of f at the origin so that r = 0. The phase (r'), defined as 4(r,") =2tvr' (10) comes about by translating g relative to f•.…”

Section: Hetero-associative Filtermentioning

confidence: 99%

<title>Different weighting approaches for performing heterogeneous correlation</title>

Khoury

Gianino

Woods

2002

Optical Pattern Recognition XIII

View full text Add to dashboard Cite

show abstract

“…To alleviate the dynamic range constraint, we have recently used the simulated annealing ͑SA͒ technique to synthesize a spatial-domain bipolar composite filter ͑BCF͒. 9 We note that SA had been used to design a Fourier-domain composite filter by Kim et al 10,11 In this paper, we shall use SA to design an optimum quantized composite reference function ͑QCRF͒. Since the QCRF is a spatial domain filter, it is very convenient to implement in a joint transform correlator ͑JTC͒.…”

Section: Introductionmentioning

confidence: 99%

Performance of quantized composite filters in a joint transform correlator

Lü

Yin

et al. 1996

Opt. Eng

View full text Add to dashboard Cite

The use of a simulated annealing algorithm to design quantized composite reference function (QCRF) filters is presented. Since the QCRF filters are spatial domain filters using finite quantization levels, they can be implemented at the output spatial light modulator of a joint transform correlator. The performance of the QCRF filters has been tested, in which we have shown that the detectability, accuracy, discriminability, and reliability improve as the quantization of the filter increases.

show abstract