Imaging remains the major application for industrial image analysis. This work presents a system for fabric manufacturing inspection. This environment, like paper and birch wood boards industries, has particular characteristics in which morphological feature extraction for Automated Visual Inspection can not be used. The utilization of Fractal Dimension is investigated for discriminating defective areas. The efficiency of this approach is illustrated in textile images for defect recognition (with overall 96% accuracy). While this may sound complex to some, the method is in fact simple enough to be suitable for PC implementation; on a standard 100 MHz Pentium a 640x480x8 bit grayscale image can be acquired and analyzed in about 10 seconds.

Key Words: textile inspection, quality control, visual inspection, computer vision.