Automatic measurement of garment dimensions using machine vision

In view of the existing situation of manual measurement of garment dimensions, machine vision has been used widely in automatic measurement of garment dimensions. In this paper, adaptive median filter algorithm is adopted to eliminate the garment image noise; a fast fuzzy edge-detection algorithm is used to detect the edge of garment image; and a new corner-detection algorithm based on Freeman code is invoked to locate the corner points. The experiment results show that the proposed method can successfully remove impulsive noise and non-impulsive noise from garment image, and can detect the edge and corners of garment image exactly, the measured dimensions approach to the actual ones. Furthermore, the method is simple, robust, and has fast processing speed.