Multi-spectral Texture Segmentation Based on the Spectral Cooccurrence Matrix

Abstract: Multi-spectral images are becoming more common in industrial inspection tasks where the colour is used as a quality measure. In this paper we propose a spectral cooccurrence matrix-based method to analyse multi-spectral texture images, in which every pixel contains a measured colour spectrum. We first quantise the spectral domain of the multi-spectral images using the Self-Organising Map (SOM). Next we label the spectral domain according to the quantised spectra. In the spatial domain, we represent a multi-spectral texture using the spectral cooccurrence matrix, which we calculate from the labelled image. In the experimental part of this paper, we present the results of segmenting natural multi-spectral textures. We compared the k-nearest neighbour (k-NN) classifier and the multilayer perceptron (MLP) neural network-based segmentation results of the multi-spectral and RGB colour textures.

[1]  Aldo Cumani,et al.  Edge detection in multispectral images , 1991, CVGIP Graph. Model. Image Process..

[2]  W. Swanson.  Human Color Vision. 2nd ed. , 1998 .

[3]  Josef Kittler,et al.  A comparison of colour texture attributes selected by statistical feature selection and neural network methods , 1997, Pattern Recognit. Lett..

[4]  A. Casini,et al.  Multispectral Imaging System for the Mapping of Pigments in Works of Art by use of Principal-Component Analysis. , 1998, Applied optics.

[5]  Raimondo Schettini,et al.  A segmentation algorithm for color images , 1993, Pattern Recognit. Lett..

[6]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[7]  John A. Richards,et al.  Remote Sensing Digital Image Analysis: An Introduction , 1999 .

[8]  Glenn Healey,et al.  Use of invariants for recognition of three-dimensional color textures , 1994 .

[9]  Esko Herrala,et al.  Direct sight imaging spectrograph: a unique add-on component brings spectral imaging to industrial applications , 1998, Electronic Imaging.

[10]  Helen C. Shen,et al.  Representing the color aspect of texture images , 1994, Pattern Recognit. Lett..

[11]  Erkki Oja,et al.  Co-occurrence map: Quantizing multidimensional texture histograms , 1996, Pattern Recognit. Lett..

[12]  Kosuke Sato,et al.  An object recognition through continuous spectral images , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[13]  S. M. Ramasamy,et al.  Reflectance spectra of minerals and their discrimination using Thematic Mapper, IRS and SPOT multi-spectral data , 1993 .

[14]  M Adel,et al.  Fast algorithm for texture discrimination by use of a separable orthonormal decomposition of the co-occurrence matrix. , 1997, Applied optics.

[15]  Erkki Oja,et al.  Texture subspaces , 1987 .

[16]  Shoji Tominaga,et al.  MULTICHANNEL VISION SYSTEM FOR ESTIMATING SURFACE AND ILLUMINATION FUNCTIONS , 1996 .

[17]  Bayya Yegnanarayana,et al.  A combined neural network approach for texture classification , 1995, Neural Networks.

[18]  Satoru Toyooka,et al.  Color classification by vector subspace method and its optical implementation using liquid crystal spatial light modulator , 1992 .

[19]  Pi-Fuay Chen,et al.  Hyperspectral imagery classification using a backpropagation neural network , 1994, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).

[20]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[21]  Gunther Wyszecki,et al.  Color Science: Concepts and Methods, Quantitative Data and Formulae, 2nd Edition , 2000 .

[22]  T Troscianko,et al.  Color and luminance information in natural scenes. , 1998, Journal of the Optical Society of America. A, Optics, image science, and vision.

[23]  J. Cohen,et al.  Color Science: Concepts and Methods, Quantitative Data and Formulas , 1968 .

[24]  J. Kittler,et al.  Colour texture analysis using colour histogram , 1994 .

[25]  Keith Phillips,et al.  Applications of Vector Fields to Image Processing , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Glenn Healey,et al.  Markov Random Field Models for Unsupervised Segmentation of Textured Color Images , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Ling-Ling Wang,et al.  Color texture segmentation for clothing in a computer-aided fashion design system , 1996, Image Vis. Comput..

[28]  Mark S. Drew,et al.  Natural metamers , 1992, CVGIP: Image Understanding.

[29]  G. Healey,et al.  Illumination-invariant recognition of texture in color images , 1995 .

[30]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..