Abstract
Texture classification plays an important role in different domains of healthcare, agriculture, and industry. In this contribution, we propose an interpretable and efficient texture classification framework that considers colour or channel information and does not require much data to produce accurate results. Therefore, such a classifier can be suitable for medical applications and resource-limited hardware. We base our work on a Generalized Matrix Learning Vector Quantization (GMLVQ) and introduce a special matrix format for multi-channel images. We compare the performance of different model designs on two data sets emphasising the role of the dissimilarity measure used. We demonstrate that our extension of parametrized angle dissimilarity measure leads to better model generalization and improved robustness against varying lighting conditions than its Euclidean counterpart.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
Notes
- 1.
Our dissimilarity measures are not required to satisfy the triangle inequality and hence are not necessarily proper metrics. We still refer to these pseudo-metrics as “distances” and “dissimilarities” throughout this paper for improved readability.
References
Bunte, K., Giotis, I., Petkov, N., Biehl, M.: Adaptive matrices for color texture classification. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds.) CAIP 2011. LNCS, vol. 6855, pp. 489–497. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23678-5_58
Burghouts, G.J., Geusebroek, J.M.: Material-specific adaptation of color invariant features. Pattern Recog. Lett. 30, 306–313 (2009)
Castellano, G., Bonilha, L., Li, L., Cendes, F.: Texture analysis of medical images. Clin. Radiol. 59(12), 1061–1069 (2004)
Fogel, I.Y., Sagi, D.: Gabor filters as texture discriminator. Biol. Cybern. 61, 103–113 (1989)
Gavhale, K.R., Gawande, U., et al.: An overview of the research on plant leaves disease detection using image processing techniques. IOSR J. Comput. Eng. (IOSR-JCE) 16(1), 10–16 (2014)
Ghosh, S., Tiño, P., Bunte, K.: Visualization and knowledge discovery from interpretable models. In: International Joint Conference on Neural Networks (IJCNN), Glasgow, UK, pp. 1–8. IEEE (2020)
Giotis, I., Bunte, K., Petkov, N., Biehl, M.: Adaptive matrices and filters for color texture classification (vol 47, pg 79, 2013). J. Math. Image Vision 48, 202 (2014)
Hammer, B., Villmann, T.: Generalized relevance learning vector quantization. Neural Netw.: Off. J. Int. Neural Netw. Soc. 15, 1059–68 (2002)
Haralick, R.M., Shanmugam, K., Dinstein, I.H.: Textural features for image classification. IEEE Trans. Syst. Man Cybern. SMC-3(6), 610–621 (1973)
Kohonen, T.: Learning vector quantization. In: Kohonen, T. (ed.) Self-Organizing Maps. Springer Series in Information Sciences, vol. 30, pp. 175–189. Springer, Heidelberg (1995). https://doi.org/10.1007/978-3-642-97610-0_6
Kumar, A., Pang, G.: Fabric defect segmentation using multichannel blob detectors. Opt. Eng. - OPT ENG 39, 3176–3190 (2000)
Kumar, S., Gupta, A.: Comparative review of machine learning and deep learning techniques for texture classification. In: Proceedings of the International Conference on Artificial Intelligent Techniques for Electrical Engineering Systems (AITEES 2022), pp. 95–112. Atlantis Press (2022)
Kupidura, P.: The comparison of different methods of texture analysis for their efficacy for land use classification in satellite imagery. Remote Sens. 11(10), 1233 (2019)
Luimstra, G., Bunte, K.: Adaptive Gabor filters for interpretable color texture classification. In: European Symposium on Artificial Neural Networks (ESANN), pp. 61–66. ESANN (2022)
MIT Vision and Modeling Group. Database vistex of color textures from MIT. https://vismod.media.mit.edu/vismod/imagery/VisionTexture/vistex.html
Nailon, W.: Texture analysis methods for medical image characterisation, pp. 75–100. IntechOpen (2010)
Sato, A., Yamada, K.: Generalized learning vector quantization. In: Touretzky, D., Mozer, M., Hasselmo, M. (eds.) NeuIPS, vol. 8. MIT Press (1995)
Schneider, P., Biehl, M., Hammer, B.: Adaptive relevance matrices in learning vector quantization. Neural Comput. 21(12), 3532–3561 (2009)
Schneider, P., Bunte, K., Stiekema, H., Hammer, B., Villmann, T., Biehl, M.: Regularization in matrix relevance learning. IEEE Trans. on Neural Netw. 21(5), 831–840 (2010)
Zhu, C., Byrd, R.H., Lu, P., Nocedal, J.: Algorithm 778: L-BFGS-B. ACM Trans. Math. Softw. 23(4), 550–560 (1997)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Shumska, M., Bunte, K. (2023). Towards Robust Colour Texture Classification with Limited Training Data. In: Tsapatsoulis, N., et al. Computer Analysis of Images and Patterns. CAIP 2023. Lecture Notes in Computer Science, vol 14184. Springer, Cham. https://doi.org/10.1007/978-3-031-44237-7_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-44237-7_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44236-0
Online ISBN: 978-3-031-44237-7
eBook Packages: Computer ScienceComputer Science (R0)