All Issue

2025 Vol.34, Issue 4 Preview Page

Original Articles

Non-Destructive Estimation of Leaf Area, Fresh Weight, and Dry Weight in Leafy Vegetables Using Image Analysis

이미지 분석을 이용한 엽채류의 엽면적, 생체중 및 건물중의 비파괴적 추정

Min Hyeok Baek1†
,
In Seon Kim1†
,
Jung Su Jo23*
백 민혁1†
,
김 인선1†
,
조 정수23*
1Graduate Student, Department of Horticulture, College of Agriculture and Life Sciences, Chonnam National University, Gwangju 61186, Korea
2Professor, Department of Horticulture, College of Agriculture and Life Sciences, Chonnam National University, Gwangju 61186, Korea
3Professor, Interdisciplinary Program in IT-Bio convergence System, Chonnam National University, Gwangju 61186, Republic of Korea
1전남대학교 농업생명과학대학 원예학과 대학원생
2전남대학교 농업생명과학대학 원예학과 교수
3전남대학교 IT-Bio 융합시스템 농업 교육 연구단 교수
*Corresponding Author
†These authors contributed equally to this work.
31 October 2025. pp. 485-495
PDF XML Citation
Abstract

This study was conducted to develop a non-destructive biomass prediction model for the efficient management of crop growth. Top view and side view images of kale and lettuce were captured, and data such as leaf area, width, and height were extracted using ImageJ. A regression model was constructed using these as independent variables and the measured fresh and dry weight as dependent variables, with performance evaluated by the coefficient of determination (R2) and root mean square error (RMSE). For leaf area estimation, the rosette-structured lettuce showed a strong correlation from both top view (R2 = 0.964) and side view (R2 = 0.95) images. In contrast, the upright-structured kale showed a high correlation only from the side view (R2 = 0.876), demonstrating that the crop’s morphology determines the optimal viewing angle. For fresh and dry weight prediction, kale showed high predictive accuracy with the side view image model (DW: R2 = 0.859－0.941, FW: R2 = 0.860－0.946), whereas lettuce showed significantly more stable and higher accuracy with the top-view image model (DW: R2 = 0.920－0.968, FW: R2 = 0.870－0.953). A model combining top view and side view images greatly improved the accuracy for kale, which had weak predictability, but had little effect on the accuracy for lettuce, which was already well-predicted from a single direction. Ultimately, the combined side and top view model for kale and the top view only model for lettuce were selected as the optimal models for biomass prediction, proving the importance of a non-destructive prediction method tailored to the structural characteristics of the crop.

Keywords
image processing
kale
lettuce
regression model

본 연구는 작물 생육을 효율적으로 관리하기 위한 비파괴적 바이오매스 예측 모델을 개발하고자 수행되었다. 케일과 상추의 상단면 및 측면 이미지를 촬영하여 ImageJ로 엽면적, 가로폭, 세로폭 등의 데이터를 추출하였다. 이를 독립변수, 실측 생체중과 건물중을 종속변수로 하여 회귀 모델을 구축하고, 결정계수(R2)와 평균 제곱근 오차(RMSE)로 성능을 평가하였다. 엽면적 추정 시, 로제트형 구조의 상추는 상단면과 측면 이미지 모두에서 강한 상관관계(TV: R2 = 0.964, SV: R2 = 0.95)를 보였던 반면, 직립형 구조의 케일은 측면 이미지에서만 높은 상관관계(R2 = 0.876)를 보여 작물의 형태가 최적의 촬영 각도를 결정함을 보여주었다. 생체중 및 건물중 예측 시, 케일은 측면 이미지 모델이 예측 정확도가 높았던(DW: R2 = 0.859－0.941, FW: R2 = 0.860－0.946) 반면, 상추는 상단면 이미지 모델이 월등히 안정적이고 높은 예측 정확도(DW: R2 = 0.920－0.968, FW: R2 = 0.870－0.953)를 보였다. 상단면과 측면 이미지를 결합한 모델은 예측력이 약했던 케일의 정확도를 크게 향상시킨 반면, 단일 촬영 방향으로도 예측이 잘 되었던 상추의 정확도에는 거의 영향을 미치지 않았다. 최종적으로 케일은 상·측면 결합(SV+TV) 모델이, 상추는 상면(TV) 단독 모델이 바이오매스 예측을 위한 최적 모델로 선정되어, 작물의 구조적 특성에 맞는 비파괴적 예측 방법이 중요함을 입증했다.

키워드
상단 이미지
상추
측면 이미지
케일
회귀 모델
References
1

Antunes W.C., M.F. Pompelli, D.M. Carretero, and F.M. DaMatta 2008, Allometric models for non‐destructive leaf area estimation in coffee (Coffea arabica and Coffea canephora). Ann Appl Biol 153:33-40. doi:10.1111/j.1744-7348.2008.00235.x

10.1111/j.1744-7348.2008.00235.x
2

Blanco F.F., and M.V. Folegatti 2005, Estimation of leaf area for greenhouse cucumber by linear measurements under salinity and grafting. Sci Agric 62:305-309. doi:10.1590/S0103-90162005000400001

10.1590/S0103-90162005000400001
3

Bukharov A.F., A.Y. Fedosov, and M.I. Ivanova 2023, Impacts of climate change on vegetable production and ways to overcome them. Vegetable crops of Russia 3:41-49. doi:10.18619/2072-9146-2023-3-41-49

10.18619/2072-9146-2023-3-41-49
4

Cardenas-Gallegos, J.S., L.N. Lacerda, P.M. Severns, A. Peduzzi, P. Klimeš, and R. S. Ferrarezi 2025, Advancing biomass estimation in hydroponic lettuce using RGB-depth imaging and morphometric descriptors with machine learning. Comput Electron Agric 234:110299 doi:10.1016/j.compag.2025.110299

10.1016/j.compag.2025.110299
5

Gowda P.T., S.A. Satyareddi, and S.B. Manjunath 2013, Crop Growth Modeling: A Review. Research & Reviews: J Agric & AlliedGuan, Z., A. Abd-Elrahman, Z. Fan, V.M. Whitaker, and B. Wilkinson 2020, Sc 2:1-11.

6

Guan, Z., A. Abd-Elrahman, Z. Fan, V.M. Whitaker, and B. Wilkinson 2020, Modeling strawberry biomass and leaf area using object-based analysis of high-resolution images. ISPRS J Photogramm Remote Sens 163:171-186

10.1016/j.isprsjprs.2020.02.021
7

Hatfield J.L., and C. Dold 2019, Water-use efficiency: advances and challenges in a changing climate. Front Plant Sci 10:103. doi:10.3389/fpls.2019.00103

10.3389/fpls.2019.0010330838006PMC6390371
8

Heo J.H., M.K. Lee, C.H. Rhew, and S.H. Woo 2018, Analysis of influential factors on sustainable agricultural development. Korea J Agric Manag Policy 45:721-741.

10.30805/KJAMP.2018.45.4.721
9

Hitzler P., K. Janowicz, A. Sharda, and C. Shimizu 2021, Advancing agriculture through semantic data management. Semantic Web 12:543-545. doi:10.3233/SW-210433

10.3233/SW-210433
10

Hu Yang, H.Y., W.L. Wang Le, X.L. Xiang LiRong, W.Q. Wu Qian, and J.H. Jiang HuanYu 2018, Automatic non-destructive growth measurement of leafy vegetables based on kinect. Sensors 18:806.

10.3390/s1803080629518958PMC5876734
11

Jang S.W., E.H. Lee, and W.B. Kim 2007, Analysis of Research and Development Papers of Lettuce in Korea. Korean J Hortic Sci Technol 25:295-303.

12

Karatassiou M., A. Ragkos, P. Markidis, and T. Stavrou 2015, A Comparative Study of Methods for the Estimation of the Leaf Area in forage Species. International Conference on Information and Communication Technologies for Sustainable Agri-production and Environment, 326-332.

13

Khan F.A., F.A. Banday, S. Narayan, F.U. Khan, and S.A. Bhat 2016, Use of models as non-destructive method for leaf area estimation in horticultural crops. IRA-Int J Appl Sci 4:162-180. doi:10.21013/jas.v4.n1.p19

10.21013/jas.v4.n1.p19
14

Korean Statistical Information on Service (KOSIS) 2024, Domestic production of kale. https://kosis.kr/ Accessed 25 September 2025.

15

Lati R.N., S. Filin, and H. Eizenberg 2013, Estimation of Plants' Growth Parameters via Image Based Reconstruction of Their Three Dimensional Shape. Agron J 105:191-198. doi:10.2134/agronj2012.0305

10.2134/agronj2012.0305
16

Liu S., S. Marden, and M. Whitty 2013, Towards automated yield estimation in viticulture. Proceedings of the Australasian Conference on Robotics and Automation. 24:2-6.

17

Lordan J., M. Pascual, F. Fonseca, V. Montilla, J. Papió, J. Rufat, and J.M. Villar 2015, An Image-based Method to Study the Fruit Tree Canopy and the Pruning Biomass Production in a Peach Orchard. HortScience 50:1809-1817. doi:10.21273/HORTSCI.50.12.1809

10.21273/HORTSCI.50.12.1809
18

Lu H.Y., C.T. Lu, M.L. Wei, and L.F. Chan 2004, Comparison of different models for nondestructive leaf area estimation in taro. Agron J 96:448-453. doi:10.2134/agronj2004.4480

10.2134/agronj2004.4480
19

Lu N., J. Zhou, Z. Han, D. Li, Q. Cao, X. Yao, and T. Cheng 2019, Improved estimation of aboveground biomass in wheat from RGB imagery and point cloud data acquired with a low-cost unmanned aerial vehicle system. Plant Methods 15:17. doi:10.1186/s13007-019-0402-3

10.1186/s13007-019-0402-330828356PMC6381699
20

National Institute of Biology Rescources (NIBR) 2016, Detail of Biology Species. https://species.nibr.go.kr/home/mainHome.do?cont_link=009&subMenu=009002&contCd=009002&pageMode=view&ktsn=120000063969 Accessed 29 September 2025.

21

NongNet 2024, Production by year. https://www.nongnet.or.kr/front/M000000006/stats/totSearch2.do?keyword=1005 Accessed 29 September 2025.

22

Poorter H., K.J. Niklas, P. B. Reich, J. Oleksyn, P. Poot, and L. Mommer 2012, Biomass allocation to leaves, stems and roots: meta‐analyses of interspecific variation and environmental control. New Phytol 193:30-50. doi:10.1111/j.1469-8137.2011.03952.x

10.1111/j.1469-8137.2011.03952.x
23

Rezaei E.E., H. Webber, S. Asseng, K. Boote, J.L. Durand, F. Ewert, P. Martre, and D.S. MacCarthy 2023, Climate change impacts on crop yields. Nat Rev Earth Environ 4:831-846. doi:10.1038/s43017-023-00491-0

10.1038/s43017-023-00491-0
24

Satheesh N., and S. Workneh Fanta 2020, Kale: Review on nutritional composition, bio-active compounds, anti-nutritional factors, health beneficial properties and value-added products. Cogent Food Agric 6 doi:10.1080/23311932.2020.1811048

10.1080/23311932.2020.1811048
25

Serdar Ü., and H. Demirsoy 2006, Non-destructive leaf area estimation in chestnut. Sci Hortic 108:227-230. doi:10.1016/j.scienta.2006.01.025

10.1016/j.scienta.2006.01.025
26

Yue J., G. Yang, C. Li, Z. Li, Y. Wang, H. Feng, and B. Xu 2017, Estimation of winter wheat above-ground biomass using unmanned aerial vehicle-based snapshot hyperspectral sensor and crop height improved models. Remote Sens 9:708. doi:10.3390/rs9070708

10.3390/rs9070708
Information
  • Publisher :The Korean Society for Bio-Environment Control
  • Publisher(Ko) :(사)한국생물환경조절학회
  • Journal Title :Journal of Bio-Environment Control
  • Journal Title(Ko) :생물환경조절학회지
  • Volume : 34
  • No :4
  • Pages :485-495
  • Received Date : 2025-10-02
  • Revised Date : 2025-10-19
  • Accepted Date : 2025-10-21
  • DOI :https://doi.org/10.12791/KSBEC.2025.34.4.485
Journal Informaiton Journal of Bio-Environment Control Journal of Bio-Environment Control
Online Submission
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crossref funder-registry
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close