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.