In this work we present a methodology to obtain invariant pattern recognition when the input scene is degraded by a defect of focus. When the image is blurred the discrimination capacity (DC) diminishes and the pattern recognition process is worse. This method is based in the selection of ring frequency bands and in the design of trade-off filters. Then several information channels are obtained. The information of all the channels is fused by means of the addition of all the channels and the geometric mean of them. Also individual channel analysis is shown. The influence on the DC and on the SNR of the added white noise in the input image is presented.
Multichannel analysis to obtain invariant pattern recognition with defocused images
19th Congress of the International Commission for Optics: Optics for the Quality of Life ; 2002 ; Florence,Italy
Proc. SPIE ; 4829
2003-11-19
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Multichannel analysis to obtain invariant pattern recognition with defocused images [4829-130]
British Library Conference Proceedings | 2003
|Observing Shape from Defocused Images
British Library Online Contents | 2003
|On Observing Shape from Defocused Images
British Library Conference Proceedings | 1999
|Multichannel pattern recognition of color images (Invited Paper) [3904-25]
British Library Conference Proceedings | 1999
|