Penggunaan Histogram dari Koefisien Aproksimasi Wavelet untuk Deteksi Cacat Tekstil

Generally, textile defect inspection at textile industry is still conducted manually by human. This approach is susceptible to errors and tends to be inconsistent due to fatigue and inattentiveness. To guarantee the consistency and inspection quality, an automatic defect detection system is required. This research proposes the use of histograms generated from two-level wavelet’s approximation coefficients as features to detect textile defects. The Euclidian distance that is calculated between feature of reference textile (non-defective textile) and feature of defective one is used as an evaluation parameter. If the Euclidian distances of the features of textile images are higher than a predetermined threshold, the textiles are determined as defective ones, and vice versa. Simulations are conducted using four groups of textile defects. It turns out that the proposed method can achieve 100% detection rate for textile group with ink-spot and textile group with holes