Segmentation and classification of hyperspectral images using CHV pattern extraction grid
- 90 Downloads
Recently, most critical challenge tasks in remote sensing applications are the segmentation and classification of hyperspectral images (HSI). Data dependency and relation among the frequency bands are the major drawbacks in the traditional HSI segmentation and classification techniques for large-size images. To segment and classify the regions in HSI, the clear description of the edge information is necessary. The presence of noise needs to be removed prior to the clear edge information extraction. To alleviate such issues, the new way of pattern extraction is proposed in this paper. Initially, the fuzzy-based adaptive median filtering removes the noise present in the image which is the prior step for clear information extraction. The integration of circular local binary pattern with the sorted local horizontal vector (CHV) patterns extracts the clear edge information necessary for classification. The intensity values from the color-based feature extraction and the CHV pattern are used to construct the relevance vector machine kernel with the limits. The comparative analysis between the proposed CHV-based pattern extraction grid with the existing techniques regarding the various metrics such as accuracy, sensitivity, specificity, rate variations and coefficient variations assures the effectiveness of proposed work in remote sensing applications.
KeywordsHyperspectral image (HSI) Color-based features Fuzzy-based adaptive median filter (FAMF) Circular local binary pattern (CLBP) Sorted local horizontal–vertical (SLHV) Relevance vector machine (RVM)
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Akbari D, Homayouni S, Safari A, Khazai S (2014) An efficient framework for spectral–spatial classification of hyperspectral images in urban areas. In: IEEE international geoscience and remote sensing symposium (IGARSS) 2014: 2886–2889Google Scholar
- Gu B, Sheng VS, Li S (2015a) Bi-parameter space partition for cost-sensitive SVM. In: IJCAI, pp 3532–3539Google Scholar
- Hyperspectral remote sensing scenes (2014). Available: http://www.ehu.eus/ccwintco/index.php?title=Hyperspectral_Remote_Sensing_Scenes
- Li J, Bioucas-Dias JM, Plaza A (2010) Semisupervised hyperspectral image segmentation using multinomial logistic regression with active learning. IEEE Trans Geosci Remote Sens 48:4085–4098Google Scholar
- Menon V, Prasad S, Fowler JE (2015) Hyperspectral classification using a composite kernel driven by nearest-neighbor spatial features. In: IEEE international conference on image processing (ICIP), pp 2100–2104Google Scholar
- Rafi M, Shaikh MS (2013) A comparison of SVM and RVM for document classification. arXiv preprint arXiv:1301.2785
- Salmon BP, Kleynhans W, van den Bergh F, Olivier JC, Marais WJ, Grobler TL et al (2012) A search algorithm to meta-optimize the parameters for an extended Kalman filter to improve classification on hyper-temporal images. In: 2012 IEEE international geoscience and remote sensing symposium (IGARSS), pp 4974–4977Google Scholar
- VeeraSenthilKumar G, Dhivya M, Sivasangari R, Suganya V (2014) Fuzzy based hyperspectral image segmentation using sub-pixel detection. Int J Inf 4:179–188Google Scholar
- Wang J, Li T, Shi Y-Q, Lian S, Ye J (2016) Forensics feature analysis in quaternion wavelet domain for distinguishing photographic images and computer graphics. Multimed Tools Appl. doi: 10.1007/s11042-016-4153-0
- Zheng Y, Jeon B, Xu D, Wu Q, Zhang H (2015) Image segmentation by generalized hierarchical fuzzy C-means algorithm. J Intell Fuzzy Syst 28:961–973Google Scholar
- Zhili Z, Ching-Nung Y, Xingming S, Qi L, WU QJ (2016) Effective and efficient image copy detection with resistance to arbitrary rotation. IEICE Trans Inf Syst 99:1531–1540Google Scholar