Distance-based separability criterion of ROI in classification of farmland hyper-spectral images

Tang Jinglei, Miao Ronghui, Zhang Zhiyong, Xin Jing, Wang Dong

Abstract


The hyper-spectral image contains spectral and spatial information, which increases the ability and precision of objects classification. Despite the classification value of hyper-spectral imaging technology within various applications, users often find it difficult to effectively apply in practice because of the effect of light, temperature and wind in outdoor environment. This research presented a new classification model for outdoor farmland objects based on near-infrared (NIR) hyper-spectral images. It involves two steps including region of interest (ROI) acquisition and establishment of classifiers. A distance-based method for quantitative analysis was proposed to optimize the reference pixels in ROI acquisition firstly. Then maximum likelihood (ML) and support vector machine (SVM) were used for farmland objects classification. The performance of the proposed method showed that the total classification accuracy based on the reference pixels was over 97.5%, of which the SVM-M model could reach 99.5%. The research provided an effective method for outdoor farmland image classification.
Keywords: distance-based separability criterion, near-infrared hyper-spectral image, ROI, farmland image classification
DOI: 10.25165/j.ijabe.20171005.2264

Citation: Tang J L, Miao R H, Zhang Z Y, Xin J, Wang D. Distance-based separability criterion of ROI in classification of farmland hyper-spectral images. Int J Agric & Biol Eng, 2017; 10(5): 177–185.

Keywords


distance-based separability criterion, near-infrared hyper-spectral image, ROI, farmland image classification

References


Zhu J, Wang Y, Yu H, Xu H. Mobile robot autonomous perceiving slope terrain under unknown environment. Chinese Journal of Scientific Instrument, 2010; 31(8): 1916–1920. (in Chinese)

Zhang R B, Yi L L, Gu H W. Environment perception for AUV in uncertain ocean environment. Journal of Computer Research and Development, 2013; 50(9): 1981–1991.

Dan J J, Peng Y K, Wang W, Li Y Y, Wu J H, Zhang L L. Simultaneous detection of external and internal quality parameters of apples using hyperspectral technology. Transactions of the CSAM, 2011; 42(3): 140–144. (in Chinese)

Wang C. Study on compression algorithm of hyper-spectral image. Master’s thesis. Nanjing University of Science and Technology, 2014.

ElMasry G, Wang N, Vigneault C. Detecting chilling injury in red delicious apple using hyper-spectral imaging and neutral networks. Postharvest Biology and Technology, 2009; 52: 1–8.

Cai J R, Wang J H, Huang X Y, Chen Q S. Detection of rust in citrus with hyperspectral imaging technology. OPTO-Electronic Engineering, 2009; 36(6): 26–30.

Cheng G S, Guo J X, Atimu R, Kang Y, Shi Z. The size detection of apple using hyperspectral imaging technology. Journal of Agricultural Mechanization Research, 2012; 34(6): 108–112.

Ghamisi P, Benediktsson J, Ulfarsson M. Spectralcspatial classification of hyperspectral images based on hidden markov random fields. IEEE Transactions on Geoscience and Remote Sensing, 2013; 52(5): 2565–2574.

Liao W Z, Pizurica A, Scheunders P, Philips W, Pi Y. Semisupervised local discriminant analysis for feature extraction in hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 2012; 51(1): 184–198.

Tarabalka Y, Fauvel M, Chanussot J, Benediktsson J A. SVM and MRF-based method for accurate classification of hyperspectral images. IEEE Transactions on Geoscience and Remote Sensing, 2010; 7(4): 736–740.

Tarabalka Y, Chanussot J, Benediktsson J A. Benediktsson. Segmentation and classification of hyperspectral images using watershed transformation. Pattern Recognition, 2010;

(7): 2367–2379.

Luo G, Chen G, Tian L, Qin K, Qian S E. Minimum noise fraction versus principal component analysis as a preprocessing step for hyperspectral imagery denoising. Canadian Journal of Remote Sensing, 2016; 42(2): 106–116.

Dong L F. Research on hyper-spectral preprocessing. Master’s thesis. Changan University, 2007.

Boardman J, Kruse F. Automated spectral analysis: a geological example using AVIRIS data, north grapevine mountains, Nevada. Surgical Endoscopy, 1994; 1(1): 407–418.

Si B L. An image retrieval method based on regions of interest. Master’s thesis. Institute of Computing Technology, Chinese Academy of Sciences, 2002.

Zhou J L., Khawaja M A, Li Z D, Sun J J, Wang Y, Chen F. Making machine learning useable by revealing internal states update: A transparent approach. International Journal of Computational Science and Engineering, 2016; 4(13): 378–389.

Brendel B, Teuffenbach M Von, Noël P B, Pfeiffer F, Koehler T. Penalized maximum likelihood reconstruction for X-ray differential phase-contrast tomography. Medical Physics, 2016; 43(1): 188–194.

Varma M K S, Rao N K K, Raju K K, Varma G P S. Pixel-based classification using support vector machine classifier. International Conference on Advanced Computing. IEEE, 2016.

Liu H P, An H J. Maximum likelihood in identifying Huhhot greening tree species. Journal of Northeast Forestry University, 2014; 42(7): 157–160.

Zhang H Y, Peng Y K, Wang W, Zhao S W, Liu Q Q. Rapid nondestructive detection of water content in fresh pork based on spectroscopy technique combined with support vector machine. Spectroscopy and Spectral Analysis, 2012; 32(10): 2794–2798.

Li W, Hu B, Wang M W. Discrimination of varieties of borneol using terahertz spectra based on principal component analysis and support vector machine. Spectroscopy and Spectral Analysis, 2014; 34(12): 3235–3240.

Ma X, Zhang Y, Wang Y. Performance evaluation of kernel functions based on grid search for support vector regression. International Conference on Cybernetics and Intelligent Systems, 2015; pp.283–288.

Liu Z, Zuo M J, Zhao X, Xu H. An analytical approach to fast parameter selection of Gaussian RBF Kernel for support vector machine. Journal of Information Science & Engineering, 2015; 31(2): 691–710.

Wong T T. Performance evaluation of classification algorithms by k-fold and leave-one-out cross validation. Pattern Recognition, 2015; 48(9): 2839–2846.


Full Text: PDF

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.