Share Email Print

Optical Engineering

Construction of an image recognition process on the basis of optical Fourier diffractometry: application to degraded bone structure classification
Author(s): Jacek Galas; Marek Daszkiewicz; Andrzej Sawicki; Krzysztof Godwod; Jacek Szawdyn
Format Member Price Non-Member Price
PDF $20.00 $25.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

A hybrid optical and digital image recognition method (based on optical Fourier diffractometry) applied to the detection of disease-induced pathological changes in bones is presented. X-ray bone images are analyzed in a new type of computer-controlled diffractometer. The set of image parameters, extracted from the diffractogram, is evaluated by statistical analysis. The synthetic statistical image descriptors, constructed based on the groups of training images, enable recognition of bone samples with degraded bone structure and then recognition of disease. About 89% of images were classified correctly. After optimization, this method can be applied to a computer-aided medical diagnosis process.

Paper Details

Date Published: 1 April 1994
PDF: 8 pages
Opt. Eng. 33(4) doi: 10.1117/12.163160
Published in: Optical Engineering Volume 33, Issue 4
Show Author Affiliations
Jacek Galas, Institute of Applied Optics (Poland)
Marek Daszkiewicz, Institute of Applied Optics (Poland)
Andrzej Sawicki, National Food & Nutrition Institute (Poland)
Krzysztof Godwod, Institute of Physics (Poland)
Jacek Szawdyn, Bielanski Hospital (Poland)

© SPIE. Terms of Use
Back to Top