Efficient texture analysis for industrial inspection |
| |
Authors: | T. A. Mitchell R. Bowden M. Sarhadi |
| |
Affiliation: | 1. Integrated Manufacturing Technologies Institute , National Research Council , London, ON, Canada N6G 4X8 Zhuming.Bi@nrc.gc.ca;3. Integrated Manufacturing Technologies Institute , National Research Council , London, ON, Canada N6G 4X8 |
| |
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 demonstrated. Near frame-rate performance on low-cost hardware is possible, since only convolution with small kernels is used. A new algorithm to optimize convolution kernels for the required texture analysis task is presented. A key feature of the paper is the industrial readiness of the techniques described. |
| |
Keywords: | Reconfigurable Manufacturing Systems (RMS) System architecture System configuration Open Architecture Control (OAC) Reconfigurability Modularity |
|
|