All Issue

2025 Vol.70, Issue 2 Preview Page

Original Research Article

Rice Leaf Area Index Evaluation Using RGB-based Vegetation Indices and Machine Learning Models

RGB 기반 생육지수와 기계학습 모델을 활용한 벼 엽면적지수 평가

Eun-ji Kim1†
,
Hyeok-jin Bak2†
,
Dongwon Kwon3
,
Sungyul Chang3
,
Woo-jin Im3
,
Nam-jin Chung4
,
Jae-Ki Chang5
,
Woon-Ha Hwang5
,
Wan-Gyu Sang3*
김 은지1†
,
박 혁진2†
,
권 동원3
,
장 성율3
,
임 우진3
,
정 남진4
,
장 재기5
,
황 운하5
,
상 완규3*
1Student, National Institute of Crop and Food Science, Rural Development Administration, RDA, Wanju 55365, Korea
2Professional Researcher, National Institute of Crop and Food Science, Rural Development Administration, RDA, Wanju 55365, Korea
3Junior Scientist, National Institute of Crop and Food Science, Rural Development Administration, RDA, Wanju 55365, Korea
4Professor, Jeonbuk National University, Department of Crop Science and Biotechnology, Jeonju 54896, Korea
5Senior Scientist, National Institute of Crop and Food Science, Rural Development Administration, RDA, Wanju 55365, Korea
1국립식량과학원 산학연학생
2국립식량과학원 전문연구원
3국립식량과학원 농업연구사
4전북대학교 작물생명과학과 교수
5국립식량과학원 농업연구관
*Corresponding Author
†Theses authors contributed equally to this work.
1 June 2025. pp. 57-67
PDF XML Citation
Abstract

Recently, the agricultural sector has embraced digital technologies to improve crop growth monitoring, aiming to boost efficiency and reduce labor. In rice, leaf area is closely related to photosynthesis and yield. However, traditional measurements tend to be destructive and LAI-based methods could be costly or constrained by environmental factors. To address this problem, two medium-late rice cultivars were grown, and nadir RGB images were acquired from tillering to panicle initiation. Seven vegetation indices were derived from the R, G, and B channels, and Otsu’s algorithm was used to segment rice from the background. Various machine learning models (e.g., Random Forest and eXtreme Gradient Boosting), followed by the predicted leaf area index, validated by destructive (LI-3100) and LAI measurements. During tillering, both index-based and machine learning methods surpassed 0.98 classification accuracy, with ExG, MExG, and CIVE strongly correlating with the measured leaf area. However, leaf morphology changes and shading after panicle initiation reduced accuracy, although the actual leaf area comparisons remained more reliable than LAI. Taken together, this study demonstrates the usefulness of RGB imagery for rapid and non-destructive rice growth assessment and highlights its potential for real-time field monitoring and automated precision agriculture.

Keywords
leaf area index
leaf area
machine learning
rice
vegetation indices
References
1

Bréda, N. J. J. 2003. Ground-based measurements of leaf area index: A review of methods, instruments and current controversies. J. Exp. Bot. 54(392) : 2403-2417.

10.1093/jxb/erg26314565947
2

Breiman, L. 2001. Random forests. Mach. Learn. 45(1) : 5-32.

10.1023/A:1010933404324
3

Burgos-Artizzu, J. P., A. Ribeiro, M. Guijarro, and G. Pajares. 2011. Real-time image processing for crop/weed discrimination in maize fields. Comput. Electron. Agric. 75(3) : 337-346. https://doi.org/10.1016/j.compag.2010.12.011

10.1016/j.compag.2010.12.011
4

Chen, T. and C. Guestrin. 2016. XGBoost: A scalable tree boosting system. Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (KDD 2016) : 785-794. https://doi.org/10.1145/2939672.2939785

10.1145/2939672.2939785
5

Das Choudhury, S., A. Samal, and T. Awada. 2019. Leveraging image analysis for high-throughput plant phenotyping. Front. Plant Sci. 10 : 508.

10.3389/fpls.2019.0050831068958PMC6491831
6

Friedman, J. H. 2001. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29(5) : 1189-1232.

10.1214/aos/1013203450
7

Gitelson, A. A., Y. J. Kaufman, R. Stark, and D. Rundquist. 2002. Novel algorithms for remote estimation of vegetation fraction. Remote Sens. Environ. 80(1) : 76-87. https://doi.org/10.1016/S0034-4257(01)00289-9

10.1016/S0034-4257(01)00289-9
8

Hamuda, E., M. Glavin, and E. Jones. 2016. A survey of image processing techniques for plant extraction and segmentation in the field. Comput. Electron. Agric. 125 : 184-199.

10.1016/j.compag.2016.04.024
9

Hashimoto, N., Y. Saito, S. Yamamoto, T. Ishibashi, R. Ito, M. Maki, and K. Homma. 2023. Relationship between leaf area index and yield components in farmers' paddy fields. AgriEngineering 5(4) : 1754-1765. https://doi.org/10.3390/agriengineering5040108

10.3390/agriengineering5040108
10

Hicks, S. I. K. and R. J. Lascano. 1995. Estimation of leaf area index for cotton canopies using the LI-COR LAI-2000 plant canopy analyzer. Agron. J. 87(3) : 300-311.

10.2134/agronj1995.00021962008700030011x
11

Huete, A. R. 1988. A soil-adjusted vegetation index (SAVI). Remote Sens. Environ. 25(3) : 295-309.

10.1016/0034-4257(88)90106-X
12

Hunt, E. R. Jr., P. C. Doraiswamy, J. E. McMurtrey, C. S. T. Daughtry, E. M. Perry, and B. Akhmedova. 2013. A visible band index for remote sensing leaf chlorophyll content at the canopy scale. Int. J. Appl. Earth Obs. Geoinf. 21 : 103-112.

10.1016/j.jag.2012.07.020
13

Karunathilake, E. M. B. M., A. T. Le, S. Heo, Y. S. Chung, and S. Mansoor. 2023. The path to smart farming: Innovations and opportunities in precision agriculture. Agriculture 13 : 1593. https://doi.org/10.3390/agriculture13081593

10.3390/agriculture13081593
14

Kataoka, T., T. Kaneko, H. Okamoto, and S. Hata. 2003. Crop growth estimation system using machine vision. Proc. IEEE/ ASME Int. Conf. Adv. Intell. Mechatron. (AIM 2003) 1079-1083.

10.1109/AIM.2003.1225492
15

Ke, G., Q. Meng, T. Finley, T. Wang, W. Chen, W. Ma, Q. Ye, and T.-Y. Liu. 2017. LightGBM: A highly efficient gradient boosting decision tree. Proc. 31st Conf. Neural Inf. Process. Syst. (NIPS 2017).

16

Knops, J. M. and K. Reinhart. (2000). Specific leaf area along a nitrogen fertilization gradient. The American Midland Naturalist, 144(2) : 265-272.

10.1674/0003-0031(2000)144[0265:SLAAAN]2.0.CO;2
17

Lee, Y. H., W. G. Sang, J. K. Baek, J. H. Kim, J. I. Cho, and M. C. Seo. 2020. Low-cost assessment of canopy light interception and leaf area in soybean canopy cover using RGB color images. Korean J. Agric. For. Meteorol. 22(1) : 13-19.

18

Li, X., X. Xu, S. Xiang, M. Chen, S. He, W. Wang, M. Xu, C. Liu, L. Yu, W. Liu, and W. Yang. 2023. Soybean leaf estimation based on RGB images and machine learning methods. Plant Methods 19 : 59. https://doi.org/10.1186/s13007-023-01023-z

10.1186/s13007-023-01023-z37330499PMC10276400
19

Liu, J. and E. Pattey. 2010. Retrieval of leaf area index from top-of-canopy digital photography over agricultural crops. Agric. For. Meteorol. 150(11) : 1485-1490.

10.1016/j.agrformet.2010.08.002
20

Louhaichi, M., M. M. Borman, and D. E. Johnson. 2001. Spatially located platform and aerial photography for documentation of grazing impacts on wheat. Geocarto Int. 16(1) : 65-70.

10.1080/10106040108542184
21

Malone, S., D. A. Herbert Jr., and D. L. Holshouser. 2002. Evaluation of the LAI-2000 Plant Canopy Analyzer to estimate leaf area in manually defoliated soybean. Agron. J. 94(5) : 1012-1019.

10.2134/agronj2002.1012
22

Netto, A. F. A., R. N. Martins, G. S. A. Souza, G. M. Araújo, S. L. H. Almeida, and V. A. Capelini. 2018. Segmentation of RGB images using different vegetation indices and thresholding methods. Nativa 6(4): 389-394. https://doi.org/10.31413/nativa.v6i4.5405

10.31413/nativa.v6i4.5405
23

Okyere, F. G., D. Cudjoe, P. Sadeghi-Tehran, N. Virlet, A. B. Riche, M. Castle, L. Greche, F. Mohareb, D. Simms, M. Mhada, and M. J. Hawkesford. 2023. Machine learning methods for automatic segmentation of images of field- and glasshouse-based plants for high-throughput phenotyping. Plants 12(2035) : 1-22. https://doi.org/10.3390/plants12102035

10.3390/plants1210203537653952PMC10224253
24

Otsu, N. 1979. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybern. 9(1) : 62-66.

10.1109/TSMC.1979.4310076
25

Rural Development Administration (RDA). 2014. Fertilizer recommendation for crop production. RDA, Suwon, Korea.

26

Shafi, U., R. Mumtaz, J. García-Nieto, S. A. Hassan, S. A. R. Zaidi, and N. Iqbal. 2019. Precision agriculture techniques and practices: From considerations to applications. Sensors 19(17) : 3796. https://doi.org/10.3390/s19173796

10.3390/s1917379631480709PMC6749385
27

Song, K. E., J. G. Jung, S. Cho, J. Y. Kim, and S. Shim. 2022. Development of Smart Digital Agriculture Technology for Food Crop Production in Korea-The Path Forward Based on Expert Feedback. Korean J. Crop Sci. 67(1) : 27-40.

28

Tang, Y. 2013. Deep learning using linear support vector machines. Proc. Int. Conf. Mach. Learn. (ICML 2013).

29

Taylor, N., K. E. Brown, and J. Smith. 2005. Classification and verification through the combination of the multi-layer perceptron and auto-association neural networks. Proc. Int. Joint Conf. Neural Netw. (IJCNN 2005). https://doi.org/10.1109/IJCNN.2005.1556018

30

Woebbecke, D. M., G. E. Meyer, K. Von Bargen, and D. A. Mortensen. 1995. Color indices for weed identification under various soil, residue, and lighting conditions. Trans. ASAE 38(1) : 259-269.

10.13031/2013.27838
Information
  • Publisher :The Korean Society of Crop Science
  • Publisher(Ko) :한국작물학회
  • Journal Title :The Korean Journal of Crop Science
  • Journal Title(Ko) :한국작물학회지
  • Volume : 70
  • No :2
  • Pages :57-67
  • Received Date : 2025-02-06
  • Revised Date : 2025-03-28
  • Accepted Date : 2025-05-07
  • An Erratum to this article was published on 1 September 2025.
    This article has been updated.
  • DOI :https://doi.org/10.7740/kjcs.2025.70.2.057
Journal Informaiton The Korean Journal of Crop Science The Korean Journal of Crop Science
Online Submission
  • NRF
  • KOFST
  • KISTI Current Status
  • KISTI Cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close