Improving Classification Accuracy of High Spatial Resolution Images by Using Texture Quantization and Genetic Feature Selection

Ashoori, H.

doi:10.22061/jrsgr.2024.10880.1065

Document Type : Original Research Paper

Author

H. Ashoori

Department of Geomatics Engineering, Qazvin Branch, Islamic Azad University, Qazvin, Iran

https://doi.org/10.22061/jrsgr.2024.10880.1065

Abstract

Background and Objectives: Texture quantization is a useful method for extracting spatial relevance between pixels, which is used in the human brain for image interpretation. Aside from spectral bands, textural features of high spatial resolution image can be used to improve classification accuracy. Finding proper textural features among available features is important for special case studies.
Methods: In this paper, two methods based on genetic algorithm (GA) are introduced to choose efficient features. The first is binary GA, which improves classification accuracies through selecting the best textural features. The second one is GA with a variable number of selected features in a refined and full feature space. Results show that the best combination does not necessarily consist of features with improved individual accuracy.
Findings: The proposed methods have better accuracy, less number of features, and less computational time when comparing with the simple GA. They could be used based on the number of spectral bands, number of generated features, and train and check pixel number. Second method needs more prerequisite time and could be used for images with fewer bands, train and check pixels, and generated features, because increasing these items increase computational time very much. Second method could be used in large images with more train and check pixels but led to more selected features.
Conclusion: Results obtained on three datasets indicate 7.7 to 50.48 percent improvement in mean accuracy.

Keywords

Main Subjects

Remote Sensing

COPYRIGHTS
© 2024 The Author(s). This is an open-access article distributed under the terms and conditions of the Creative Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) (https://creativecommons.org/licenses/by-nc/4.0/)

References

[1] Fauvel M, Benediktsson JóA, Chanussot J, Sveinsson JR. Spectral and Spatial Classification of Hyperspectral Data Using SVMs and Morphological Profiles. IEEE Transactions on Geoscience and Remote Sensing. 2008 Nov;46(11):3804–14.

[2] Gaetano R, Scarpa G, Poggi G. Hierarchical Texture-Based Segmentation of Multiresolution Remote-Sensing Images. IEEE Transactions on Geoscience and Remote Sensing. 2009 Jul;47(7):2129–41.

[3] Puig D, Angel Garcia M. Automatic texture feature selection for image pixel classification. Pattern Recognition. 2006 Nov;39(11):1996–2009.

[4] Lin CH, Chen HY, Wu YS. Study of image retrieval and classification based on adaptive features using genetic algorithm feature selection. Expert Systems with Applications. 2014 Nov;41(15):6611–21.

[5] Welikala RA, Fraz MM, Dehmeshki J, Hoppe A, Tah V, Mann S, et al. Genetic algorithm-based feature selection combined with dual classification for the automated detection of proliferative diabetic retinopathy. Computerized Medical Imaging and Graphics. 2015 Jul; 43:64–77.

[6] Ruiz LA, Fdez-Sarría A, Recio JA. Texture feature extraction for classification of remote sensing data using wavelet decomposition: a comparative study. 20th ISPRS Congress. 2004; Vol. 35. No. part B.

[7] Castleman KR. Digital Image Processing. Pearson; 1996.

[8] Theodoridis S, Konstantinos Koutroumbas. Pattern recognition. Amsterdam Elsevier/Acad. Press [20]11.

[9] Haralick RM, Shanmugam K, Dinstein I. Textural Features for Image Classification. IEEE Transactions on Systems, 1973 Nov; SMC-3(6):610–21.

[10] Laws, K. Textured Iage Segmentation. 1980; Ph.D Dissertation, University of South California.

[11] Pratt WK. Digital image processing: PIKS Scientific inside. Hoboken, N.J.: Wiley-Interscience; 2007.

[12] Yu S, De Backer S, Scheunders P. Genetic feature selection combined with composite fuzzy nearest neighbor classifiers for hyperspectral satellite imagery. Pattern Recognition Letters. 2002 Jan;23(1-3):183–90.

[13] Feature selection using genetic algorithm for classification of schizophrenia using fMRI data. Journal of Artificial Intelligence and Data Mining. 2015;3(1).

[14] Singh DAAG, Leavline EJ, Priyanka R, Priya PP. Dimensionality Reduction using Genetic Algorithm for Improving Accuracy in Medical Diagnosis. International Journal of Intelligent Systems and Applications. 2016 Jan 8;8(1):67–73.

[15] Liang Y, Zhang M, Browne WN. Image feature selection using genetic programming for ﬁgure-ground segmentation. 2017; Engineering Applications of Artificial Intelligence, Volume 62: 96-108.

[16] http://www.grss-ieee.org/community/technical-committees/data-fusion/, 2014 IEEE GRSS Data Fusion Contest. Online.

[17] Boyd DS, Foody GM, Ripple WJ. Evaluation of approaches for forest cover estimation in the Pacific Northwest, USA, using remote sensing. Applied Geography. 2002 Oct;22(4):375–92.

[18] Joshi C, Leeuw JD, Skidmore AK, Duren IC van, van Oosten H. Remotely sensed estimation of forest canopy density: A comparison of the performance of four methods. International Journal of Applied Earth Observation and Geoinformation. 2006 Jun;8(2):84–95.

[19] Cross A, Settle JJ, Drake N, R. Päivinen. Subpixel measurement of tropical forest cover using AVHRR data. International Journal of Remote Sensing. 1991 May 1;12(5):1119–29.

[20] Souza C. Mapping Forest degradation in the Eastern Amazon from SPOT 4 through spectral mixture models. Remote Sensing of Environment. 2003 Nov 15;87(4):494–506.

[21] Lévesque J, King DJ. Spatial analysis of radiometric fractions from high-resolution multispectral imagery for modelling individual tree crown and forest canopy structure and health. Remote Sensing of Environment. 2003 Apr;84(4):589–602.

[22] Akbari D, Akbari V. Object‑based classification of hyperspectral images based on weighted genetic algorithm and deep learning model. Applied Geomatics. 2023; 15, 227–238.

[23] Akbari D, Rokni K. Spectral-spatial classification of hyperspectral images based on nonlinear principal component analysis and deep learning models. International Journal of Remote Sensing. 2023; Volume 23.

[24] Zhu W, Yang X, Liu R, Zhao C. A new feature extraction algorithm for measuring the spatial arrangement of texture Primitives: Distance coding diversity. International journal of applied earth observation and geoinformation. 2024 Mar 1; 127:103698–8.

Journal of Remote Sensing and Geoinformation Research

Improving Classification Accuracy of High Spatial Resolution Images by Using Texture Quantization and Genetic Feature Selection

References

References

Volume 2, Issue 1 - Serial Number 3
January 2024
Pages 155-168

Improving Classification Accuracy of High Spatial Resolution Images by Using Texture Quantization and Genetic Feature Selection

References

References

Volume 2, Issue 1 - Serial Number 3January 2024Pages 155-168

Volume 2, Issue 1 - Serial Number 3
January 2024
Pages 155-168