Feature extraction of hyperspectral images for detecting immature green citrus fruit

doi:10.15302/J-FASE-2018241

Front. Agr. Sci. Eng.

2018, Vol. 5

Issue (4) : 475-484 https://doi.org/10.15302/J-FASE-2018241

RESEARCH ARTICLE

Feature extraction of hyperspectral images for detecting immature green citrus fruit

Yongjun DING¹(

), Won Suk LEE², Minzan LI³

¹. School of Electronic and Information Engineering, Lanzhou City University, Lanzhou 730070, China
². Agricultural and Biological Engineering, University of Florida, Gainesville, FL 32611, USA
³. Key Laboratory of Modern Precision Agriculture System Integration Research of Ministry of Education, China Agricultural University, Beijing 100083, China

Download: PDF(2814 KB) HTML
Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks

Abstract

At an early immature growth stage of citrus, a hyperspectral camera of 369–1042 nm was employed to acquire 30 hyperspectral images in order to detect immature green fruit within citrus trees under natural illumination conditions. First, successive projections algorithm (SPA) were implemented to select 677, 804, 563, 962, and 405 nm wavebands and to construct multispectral images from the original hyperspectral images for further processing. Then, histogram threshold segmentation using NDVI of 804 and 677 nm was implemented to remove image backgrounds. Three slope parameters, calculated from the pairs 405 and 563 nm, 563 and 677 nm, and 804 and 962 nm were used to construct a classifier to identify the potential citrus fruit. Then, a marker-controlled watershed segmentation based on wavelet transform was applied to obtain potential fruit areas. Finally, a green fruit detection model was constructed according to Grey Level Co-occurrence Matrix (GLCM) texture features of the independent areas. Three supervised classifiers, logistic regression, random forest and support vector machine (SVM) were developed using texture features. The detection accuracies were 79%, 75%, and 86% for the logistic regression, random forest, and SVM models, respectively. The developed algorithm showed a great potential for identifying immature green citrus for an early yield estimation.

Keywords hyperspectral green citrus image processing fruit detection precision agriculture yield mapping

Corresponding Author(s): Yongjun DING

Just Accepted Date: 21 September 2018 Online First Date: 02 November 2018 Issue Date: 19 November 2018

Cite this article:

Yongjun DING,Won Suk LEE,Minzan LI. Feature extraction of hyperspectral images for detecting immature green citrus fruit[J]. Front. Agr. Sci. Eng. , 2018, 5(4): 475-484.

URL:

https://academic.hep.com.cn/fase/EN/10.15302/J-FASE-2018241
https://academic.hep.com.cn/fase/EN/Y2018/V5/I4/475

Fig.1 Comparison of the different spectra under different illumination conditions. (a) Regions of interest from the same fruit and leaf (I) in the normal brightness area of the fruit; (II) light area of the fruit; (III) dark area of the fruit; (IV) normal brightness on the left; and (V) dark area on the left; (b) spectrum of each region of interest.

Fig.2 Flowchart for the proposed algorithm

Fig.3 Example of SPA with J = 5, Xcal= 3 and k(0) = 3. Result of first iteration: k(1) = 1.

Fig.4 The influence of varying illumination conditions on reflectance. (a) Color image composed of three components at 405, 563 and 677 nm with ROIs; (b) the reflectance of each ROIs.

Fig.5 2D-DWT pyramid decomposition

Tab.1 Difference in texture features between fruit and leaves under varying illumination conditions.

Fig.12 Comparison of PCA Mahalanobis distance classification and SPA Mahalanobis distance classification. (a) Five regions of interest; (b) the result of PCA Mahalanobis distance classification with ROIs. The result of Mahalanobis distance classification (c) using 754, 397, 962, 563, 501 nm wavelengths; (d) using 677, 804, 563, 962, 405 nm wavelengths; (e) using 606, 955, 402, 768, 466 nm wavelengths; (f) using 489, 955, 563, 399, 767 nm wavelengths; (g) using 549, 955, 440, 768, 987 nm wavelengths.

Fig.13 Example of background removal. (a) RGB image composed of 405nm, 563nm and 677nm as B, G and R components; (b) the gray image of NDVI_{804, 677}; (c) the histogram of the gray image of NDVI_{804, 677}; (d) the result after background removal.

Fig.14 The distribution of fruit and leaves in the feature space structured by three slope parameters

Tab.2 Results of the three classification models to detection potential fruit

Fig.15 The execution process of the marker-controlled watershed segmentation based on two-dimensional discrete wavelet transform. (a) The image of potential fruit regions; (b) the reconstruction result of approximation coefficient with Daubechies db4 function at level four decomposition; (c) the result of regional maxima; (d, e) the result of marker-controlled watershed segmentation.

Tab.3 Results of the three classification models for detection of potential fruit

1	Bulanon D M, Burks T F, Alchanatis V, Noguchi N. A multispectral imaging analysis for enhancing citrus fruit detection. Environment Control in Biology, 2010, 48(2): 81–91 https://doi.org/10.2525/ecb.48.81
2	Bulanon D M, Burks T F, Alchanatis V. Study on temporal variation in citrus canopy using thermal imaging for citrus fruit detection. Biosystems Engineering, 2008, 101(2): 161–171 https://doi.org/10.1016/j.biosystemseng.2008.08.002
3	Xu H R, Ye Z Z, Ying Y B. Identification of citrus fruit in a tree canopy using color information. Transactions of the Chinese Society of Agricultural Engineering, 2005, 21(5): 98–101 (in Chinese)
4	Cai J R, Zhou X J, Li Y L, Fan J. Recognition of mature oranges in natural scene based on machine vision. Transactions of the Chinese Society of Agricultural Engineering, 2008, 24(1): 175–178 (in Chinese)
5	Kane K E, Lee W S. Multispectral imaging for in-field green citrus identification. In: ASAE Annual Meeting 2007, Minneapolis. St. Joseph: American Society of Agricultural and Biological Engineers, 2007, 1–11
6	Kurtulmus F, Lee W S, Vardar A. Green citrus detection using ‘eigenfruit’ color and circular Gabor texture features under natural outdoor conditions. Computers and Electronics in Agriculture, 2011, 78(2): 140–149 https://doi.org/10.1016/j.compag.2011.07.001
7	Sengupta S, Lee W S. Identification and determination of the number of immature green citrus fruit in a canopy under different ambient light conditions. Biosystems Engineering, 2014, 117(1): 51–61 https://doi.org/10.1016/j.biosystemseng.2013.07.007
8	Zhao C, Lee W S, He D. Immature green citrus detection based on colour feature and sum of absolute transformed difference (SATD) using colour images in the citrus grove. Computers and Electronics in Agriculture, 2016, 124(C): 243–253 https://doi.org/10.1016/j.compag.2016.04.009
9	Li H, Lee W S, Wang K. Immature green citrus fruit detection and counting based on fast normalized cross correlation (FNCC) using natural outdoor colour images. Precision Agriculture, 2016, 17(6): 678–697 https://doi.org/10.1007/s11119-016-9443-z
10	Okamoto H, Lee W S. Green citrus detection using hyperspectral imaging. Computers and Electronics in Agriculture, 2009, 66(2): 201–208 https://doi.org/10.1016/j.compag.2009.02.004
11	Kim M S, Chen Y R, Mehl P M. Hyperspectral reflectance and fluorescence imaging system for food quality and safety. Transactions of the ASAE (American Society of Agricultural Engineers), 2001, 44(3): 721–729
12	Araújo M C U, Saldanha T C B, Galvao R K H, Yoneyama T, Chame H C, Visani V. The successive projections algorithm for variable selection in spectroscopic multicomponent analysis. Chemometrics and Intelligent Laboratory Systems, 2001, 57(2): 65–73 https://doi.org/10.1016/S0169-7439(01)00119-8
13	Wu P C, Chen L G. An efficient architecture for two-dimensional discrete wavelet transform. IEEE Transactions on Circuits and Systems for Video Technology, 2001, 11(4): 536–545 https://doi.org/10.1109/76.915359
14	Kim J B, Kim H J. Multiresolution-based watersheds for efficient image segmentation. Pattern Recognition Letters, 2003, 24(1): 473–488 https://doi.org/10.1016/S0167-8655(02)00270-2
15	Yang X, Li H, Zhou X. Nuclei segmentation using marker-controlled watershed, tracking using mean-shift, and Kalman filter in time-lapse microscopy. IEEE Transactions on Circuits and Systems. I, Regular Papers, 2006, 53(11): 2405–2414 https://doi.org/10.1109/TCSI.2006.884469
16	Yazdi M, Gheysari K. A new approach for the fingerprint classification based on gray-level co-occurrence matrix. International Journal of Computer and Information Science and Engineering, 2008, 2(3): 171–174
17	Yan J, Lee J. Degradation assessment and fault modes classification using logistic regression. Journal of Manufacturing Science and Engineering, 2005, 127(4): 912–914 https://doi.org/10.1115/1.1962019
18	Guo L, Ma Y, Cukic B, Singh H. Robust prediction of fault-proneness by random forests. In: 15th International Symposium on Software Reliability Engineering 2004, Bretagne. USA: IEEE, 2004, 417–428
19	Cherkassky V, Ma Y. Practical selection of SVM parameters and noise estimation for SVM regression. Neural Networks, 2004, 17(1): 113–126 https://doi.org/10.1016/S0893-6080(03)00169-2 pmid: 14690712
20	Brereton R G, Lloyd G R. Support vector machines for classification and regression. Analyst, 2010, 135(2): 230–267 https://doi.org/10.1039/B918972F pmid: 20098757

[1]	Kejian WANG, Dongmei GUO, Yao ZHANG, Lie DENG, Rangjin XIE, Qiang LV, Shilai YI, Yongqiang ZHENG, Yanyan MA, Shaolan HE. Detection of Huanglongbing (citrus greening) based on hyperspectral image analysis and PCR[J]. Front. Agr. Sci. Eng. , 2019, 6(2): 172-180.
[2]	Beth CLARK, Glyn D. JONES, Helen KENDALL, James TAYLOR, Yiying CAO, Wenjing LI, Chunjiang ZHAO, Jing CHEN, Guijun YANG, Liping CHEN, Zhenhong LI, Rachel GAULTON, Lynn J. FREWER. A proposed framework for accelerating technology trajectories in agriculture: a case study in China[J]. Front. Agr. Sci. Eng. , 2018, 5(4): 485-498.
[3]	Chenghai YANG. High resolution satellite imaging sensors for precision agriculture[J]. Front. Agr. Sci. Eng. , 2018, 5(4): 393-405.

Viewed

Full text

Abstract

Cited

Shared

Discussed