论文信息 - Industrial inspection using Gaussian functions in a colour space

Industrial inspection using Gaussian functions in a colour space

Abstract This paper presents an original method of modelling the colour distributions of images using 2D Gaussian functions and its application to flaw detection in industrial inspection. 2D Gaussian functions are used to model the colours that appear in the non-flawed images in an unsupervised manner. Pixels 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 wide range of applications for detecting colour separable objects in images. It also has great potential in industrial inspection due to its speed, accuracy and unsupervised training.

Gerard Lacey | Manuel Mazo | Luis Miguel Bergasa | Nicola Duffy

[1] Manuel Graña,et al. An analysis of the GLVQ algorithm , 1995, IEEE Trans. Neural Networks.

[2] James C. Bezdek,et al. Repairs to GLVQ: a new family of competitive learning schemes , 1996, IEEE Trans. Neural Networks.

[3] Yihong Gong,et al. Detection of Regions Matching Specified Chromatic Features , 1995, Comput. Vis. Image Underst..

[4] Gerard Lacey,et al. Colour Profiling Using Multiple Colour Spaces , 1998, BMVC.

[5] Teuvo Kohonen,et al. Self-Organizing Maps , 2010 .

[6] Helge J. Ritter,et al. Adaptive color segmentation-a comparison of neural and statistical methods , 1997, IEEE Trans. Neural Networks.

[7] JANDER M OREIRA,et al. Neural-based color image segmentation and classification using self-organizing maps , 1996 .

[8] Alex Waibel,et al. Tracking Human Faces in Real-Time, , 1995 .

[9] Neill W. Campbell,et al. Automatic Segmentation and Classification of Outdoor Images Using Neural Networks , 1997, Int. J. Neural Syst..