Real-time surface grading of profiled wooden boards

Abstract

This paper describes the design of a prototype system for real-time classification of wooden profiled boards. An overview is given of the algorithms and hardware developed to classify in real-time at a data rate of 4 Mpixel/s. The system achieves its performance by a hierarchical processing strategy that transforms the intensity information contained in the digital image into a symbolic description of small texture elements. Based on this symbolic representation, a syntactic segmentation scheme is applied that produces a list of objects that are present on the board surface. The objects are described by feature vectors containing both numeric, structural, texture- and shape-related properties. A graph-like decision network is then used to identify the various defects. Classification procedures were extensively tested for spruce boards on a large data set containing 500 boards randomly taken from the production line. The overall rate of correct classification was 95 percent, as opposed to a reproducible correct classification rate of 55 percent achieved by human graders. The structure of these algorithms is reflected in the hardware design. A multiprocessor system is used in which each processor is specialized to solve a specific task in the recognition hierarchy.