Optimised filters for texture defect detection

Abstract

This paper presents a new approach to texture defect detection based on a set of optimised filters. Each filter is applied to one wavelet sub-band and its size and shape are tuned for a defect type. The wavelet transform provides a very efficient way to decompose a complex texture into a set of base components (wavelet sub-bands), which are then analysed by each filter to detect a kind of defect. The proposed methodology has been successfully applied to leather inspection, achieving the detection rate of highly trained human operators. The process is also fast enough to be used for in-line inspection.