---

Texture models characterize local spatial information in an image. Texture is a useful property for recognition especially in natural scenes, but observed image texture depends on factors such as scene geometry and illumination conditions. An important focus of our research is to develop texture recognition methods that are invariant to such factors. In reference [1] we derive invariants of a color correlation texture model that can be used for recognition independent of the distance and orientation of a surface. The same model is used in [3] by a recognition technique that is invariant to the scene illumination. A method is presented in reference [5] that is invariant to both geometry and illumination. A combination of these methods is applied to recognition in multispectral satellite images in [6]. In references [2] and [4] we explore random field models for color images with application to image segmentation. In references [7] and [8] we examine limitations of random field models and present a more comprehensive model which allows the interaction parameters defining the random field to be random themselves.

[1] R. Kondepudy and G. Healey

``Use of invariants for recognition of three-dimensional color textures,'' Journal of the Optical Society of America A, 11(11):3037-3049, November 1994. abstract

[2] D. Panjwani and G. Healey

``Selecting neighbors in random field models for color images'', Proceedings of the First IEEE International Conference on Image Processing (1994). abstract

[3] G. Healey and L. Wang

``Illumination-Invariant Recognition of Texture in Color Images,'' Journal of the Optical Society of America A, 12(9):1877-1883, September 1995. abstract

[4] D. Panjwani and G. Healey

``Markov Random Field Models for Unsupervised Segmentation of Textured Color Images,'' IEEE Transactions on Pattern Analysis and Machine Intelligence, 17(10):939-954, October, 1995. abstract

[5] A. Speis and G. Healey

``An Analytical and Experimental Study of the Performance of Markov Random Fields Applied to Textured Images using Small Samples,'' IEEE Transactions on Image Processing, 5(3):447-458, March 1996. abstract

[6] A. Speis and G. Healey

``Feature Extraction for Texture Discrimination via Random Field Models with Random Spatial Interaction,'' IEEE Transactions on Image Processing, 5(4):635-645, April 1996. abstract

[7] G. Healey and A. Jain

``Retrieving Multispectral Satellite Images using Physics-based Invariant Representations,'' IEEE Transactions on Pattern Analysis and Machine Intelligence, 18(8):842-848, August 1996. abstract

[8] P. Suen and G. Healey

``A New Spatial Interaction Model for Color Texture,'' Proceedings of the IEEE International Conference on Image Processing, vol. 2, pp. 867-870, October 1997. abstract

[9] A. Jain and G. Healey

``A Multiscale Representation Including Opponent Color Features for Texture Recognition,'' IEEE Transactions on Image Processing, 7(1):124-128, January 1998. abstract

[10] L. Wang and G. Healey

``Using Zernike Moments for the Illumination and Geometry Invariant Classification of Multispectral Texture,'' IEEE Transactions on Image Processing, 7(2):196-203, 1998. abstract

[11] P. Suen and G. Healey

``Analyzing the Bidirectional Texture Function,'' Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 753-758, June 1998. abstract

[12] L. Wang and G. Healey

``Using Multiband Filtered Energy Matrices for Recognition and Illumination Correction,'' Optical Engineering, 37(10), October 1998. abstract

[13] B. Thai and G. Healey

``Modeling and Classifying Symmetries using a Multiscale Opponent Color Representation,'' IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(11), 1224-1235, 1998. abstract

[14] B. Thai and G. Healey

``Spatial Filter Selection for Illumination-Invariant Color Texture Discrimination,'' Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Vol. II, 154-159, June 1999. abstract

Back to the ICVL homepage

Last modified: 29 August 1999