Efficient texture analysis for industrial inspection

Citation
Ta. Mitchell et al., Efficient texture analysis for industrial inspection, INT J PROD, 38(4), 2000, pp. 967-984
Citations number
21
Categorie Soggetti
Engineering Management /General
Journal title
INTERNATIONAL JOURNAL OF PRODUCTION RESEARCH
ISSN journal
00207543 → ACNP
Volume
38
Issue
4
Year of publication
2000
Pages
967 - 984
Database
ISI
SICI code
0020-7543(20000310)38:4<967:ETAFII>2.0.ZU;2-N
Abstract
This paper describes a convolution-based approach to the analysis of images containing few texture classes. Segmentation of foreground and background textures, or detection of boundaries between similarly textured objects, is demonstrated. The application to industrial inspection applications is dem onstrated. Near frame-rate performance on low-cost hardware is possible, si nce only convolution with small kernels is used. A new algorithm to optimiz e convolution kernels for the required texture analysis task is presented. A key feature of the paper is the industrial readiness of the techniques de scribed.