Industrial inspection using Gaussian functions in a colour space

This paper presents an original method of modelling the colour distribution s of images using 2D Gaussian functions and its application to flaw detecti on in industrial inspection. 2D Gaussian functions are used to model the co lours that appear in the non-flawed images in an unsupervised manner. Pixel s under test are compared to the colour distribution from training images. 140 images have been tested and the results are given. This method has a wi de range of applications for detecting colour separable objects in images. It also has great potential in industrial inspection due to its speed, accu racy and unsupervised training. (C) 2000 Elsevier Science B.V. All rights r eserved.