ABSTRACT
The spatial information in a remotely sensed image is often characterized by the texture features, which have been regarded as an important visual primitive to search through large collections of natural visually similar patterns in the image. This paper presents an automated process of extract and classify the texture patterns observed in the remote sensing images such as Landsat TM multispectral images. After the principal component analysis, the first component image, which preserves the largest percentage of the variance, is divided into sub regions. The feature vectors representing the textures of each region are computed by Gabor wavelets and classified using a Bayes Point Machine classifier. The preliminary results show the effectiveness of the process and its potentials in practical remote sensing applications.
- Myint, S. W. A robust texture analysis and classification approach for urban land-use and land-cover feature discrimination, Geocarto International, 16, 4, (Dec. 2001), 27--38.Google ScholarCross Ref
- Franklin, S. E., Hall, R. J., Moskal, L. M., Maudie, A. J., and Lavigne, M. B. Incorporating texture into classification of forest species composition from airborne multispectral images, International Journal of Remote Sensing, 21, 1 (2000), 61--79.Google ScholarCross Ref
- Turner, M. R. Texture transformation by Gabor function, Biology Cybernation, 55, (1986), 71--82. Google ScholarDigital Library
- Ma, W. Y. and Manjunath, B. S. A texture thesaurus for browsing large aerial photographs, J. of the American Society for Information Science, 49, 7, (May 1998), 633--648. Google ScholarDigital Library
- Cristianini, N. and Shawe-Taylor, J. 2000. An Introduction to Support Vector Machines, The Cambridge University Press, Cambridge, UK. Google ScholarDigital Library
- Herbrich, R., Graepel, T., and Campbell, C., Bayes point machines. J. Machine Learning Research, 1, (2001) 245--279. Google ScholarDigital Library
- Li, J. and Narayanan, R. M. Integrated spectral and spatial information mining in remote sensing imagery. IEEE Trans Geosci. Rem. Sens. 42, 3 (Mar. 2004), 673--685.Google ScholarCross Ref
- Mantero, P., Moser, G., and Serpico, S. B. Partially supervised classification of remote sensing images through SVM-based probability density estimation. IEEE Trans Geosci. Rem. Sens., 43, 3 (Mar. 2005), 559--570.Google ScholarCross Ref
- Cao, W. and Meng S. Image classification based on Bayes point machines. IEEE International Workshop on Imaging Systems and Techniques, (2009), 164--167.Google Scholar
- Wu, G., Chang, E., and Chung-Sheng L. 2002. BPMs versus SVMs for image classification. IEEE International Conference on Multimedia and Expo, (2002), 505--508.Google Scholar
- Celik, T. and Tjahjadi, T. Bayesian texture classification and retrieval based on multiscale feature vector. Pattern Recognition Letters, 32, 2 (2011), 159--167. Google ScholarDigital Library
- Chang, E., Goh, K., Sychay, G., and Wu, G. CBSA: Content-based soft annotation for multimodal image retrieval using Bayes point machines. IEEE Transactions on Circuits and Systems for Video Technology, 13, 1 (2003), 26--38. Google ScholarDigital Library
- Gorte, B. and Stein, A. Bayesian classification and class area estimation of satellite images using stratification. IEEE Trans Geosci. Rem. Sens. 36, 3 (May 1998), 803--812.Google ScholarCross Ref
- Rodarmel, C. and Shan, J. Principal component analysis for hyperspectral image classification, Surveying and Land Information Science, 62, 2, (June 2002), 115--122.Google Scholar
- Gonzales, R. C., Woods, R. E., 1993. Digital Image Processing. Addison-Wesley, Reading, Massachusetts. Google ScholarDigital Library
- Manjunath, B. S., Wu, P., Newsam, S., and Shin, H. D. A texture descriptor for browsing and similarity retrieval, J. of Signal Processing: Image Communication, 16, 1--2, (Sep. 2000), 33--43.Google ScholarCross Ref
- Manjunath, B. S. and Ma, W. Y. Texture features for browsing and retrieval of image data, IEEE Transactions on Pattern Analysis and Machine Intelligence, 18, 8, (Aug. 1996), 837--842. Google ScholarDigital Library
- Herbrich, R., Graepel, T., and Campbell, C., 1999. Bayes point machines: Estimating the Bayes point in kernel space. Proc. Int. Joint Conf. Artificial Intelligence Workshop on Support Vector Machines, (Stockholm, Sweden, Aug. 1999), 23--27.Google Scholar
- Minka, T., Winn, J., Guiver, J., and Knowles, D. Infer.NET 2.5. Microsoft Research Cambridge. 2012. http://research.microsoft.com/infernet.Google Scholar
Index Terms
- Texture classification of landsat TM imagery using Bayes point machine
Recommendations
Maximally Stable Texture Regions
ICPR '10: Proceedings of the 2010 20th International Conference on Pattern RecognitionIn this study, we propose to detect interest regions based on texture information of images. For this purpose, Maximally Stable Extremal Regions (MSER) approach is extended using the high dimensional texture features of image pixels. The regions with ...
Research on Texture Images Retrieval Based on the Gabor Wavelet Transform
ICIE '09: Proceedings of the 2009 WASE International Conference on Information Engineering - Volume 01A technique of texture images retrieval based on Gabor wavelet transform is presented in this paper.A group of filters of different directions and different scales, generated from the basic wavelet of Gabor function are used for the wavelet ...
Texture classification and discrimination for region-based image retrieval
Display Omitted The fusion of the Gabor and curvelet filters is used for texture representation.Rotation invariant texture features are obtained by rearranging the sub-bands.Encoding the sub-bands' information by polynomial makes unique vectors.The ...
Comments