HTF: a novel feature for general crack detection

Recent years, image-based crack detection has attracted more and more attentions for its potential applications on the inspection, diagnosis, and maintenance of various products, e.g. metal workpiece, concrete structure, asphalt road and etc. Generally, the applications are inevitably confronted with noises such as non-uniform illuminated conditions, shadings, stains and nature textures. To ease the problem, traditional methods usually focused on a special application and are carried out with strictly controlled image acquisition environments or an adhoc preprocessing procedure. In this paper, we propose a general crack detection method which can deal with various products as well as the noises in a unified fashion, and even with the same parameters. The method partitions an image into overlapped small grid cells and determines whether the cells contain cracks using a well designed feature descriptor. Experiments using real images of various products show the effectiveness of the proposed feature as well as the method.