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.