Online First

 Preview Page

Research Article

Assessing the Discriminatory Power of Leaf Morphometric Traits in Capsicum annuum by means of a Linear Discriminant Analysis
E.M.B.M. Karunathilake1†
,
Jinhyun Ahn2†
,
Piya Kittipadakul3
,
Supachai Vuttipongchaikij4
,
Hyun Jo5*
1Department of Plant Resources and Environment, Jeju National University, Jeju 63243, Korea
2Department of Management Information Systems, Jeju National University, Jeju 63243, Korea
3Department of Agronomy, Faculty of Agriculture, Kasetsart University, 50 Ngam Wong Wan road, Chatuchak, Bangkok 10900, Thailand
4Department of Genetics, Faculty of Science, Kasetsart University, 50 Ngam Wong Wan road, Chatuchak, Bangkok 10900, Thailand
5Department of Applied Biosciences, Kyungpook National University, Daegu 41566, Korea
*Corresponding Author
†These authors contributed equally to this work.
PDF XML Citation
Abstract

Leaf morphometric traits are widely utilized to identify plants, yet their effectiveness when used to discriminate large Capsicum collections remains unclear. This study assessed whether eight leaf size and shape traits could reliably classify 371 and 352 C. annuum accessions collected in 2021 and 2022. Comprehensive diagnostic testing revealed major violations of the assumptions required for linear discriminant analysis (LDA), including non-normal trait distributions, unequal covariance matrices, and severe multicollinearity among predictors. Shape descriptors further exhibited nonlinear dependencies incompatible with LDA. As a result, LDA models produced unstable discriminant functions and extremely low agreement between predicted and true accession labels. Given these limitations, unsupervised methods were employed. K-means clustering identified eight phenotypic groups in 2021 and three in 2022, and a principal component analysis (PCA) supported these patterns, with the first two components capturing the primary axes of the leaf size and shape variation. However, strong overlap among accessions in the PCA space indicated weak morphological differentiation, likely reflecting strong environmental influence and limited genetic divergence with regard to the leaf form. These findings indicate that basic leaf morphometric traits alone are insufficient for accession-level classification in C. annuum. Robust discrimination will require integrative phenotyping frameworks that combine geometric, physiological, biochemical, and genomic traits, supported by measurement technologies.

Keywords
chili pepper
genetic resources
k-mean cluster
leaf imagery
leaf morphology
principal component analysis
References
1

Al Hiary H, Bani Ahmad S, Reyalat M, Braik M, ALRahamneh Z (2011) Fast and accurate detection and classification of plant diseases. Int J Comput Appl 17:31-38. https://doi.org/10.5120/2183-2754

10.5120/2183-2754
2

Ali S, Hassan M, Kim JY, Farid MI, Sanaullah M, Mufti H (2022) FF-PCA-LDA: Intelligent feature fusion based PCA-LDA classification system for plant leaf diseases. Appl Sci 12:3514. https://doi.org/10.3390/app12073514

10.3390/app12073514
3

Alvares Bianchi P, Renata Almeida Da Silva L, André Da Silva Alencar A, Henrique Araújo Diniz Santos P, Pimenta S, Pombo Sudré C, Erpen-Dalla Corte L, Simões Azeredo Gonçalves L, Rodrigues R (2020) Biomorphological characterization of brazilian capsicum chinense Jacq. germplasm. Agronomy 10:447. https://doi.org/10.3390/agronomy10030447

10.3390/agronomy10030447
4

Baloch FS, Lee SM, Mansoor S, Morales A, Karunathilake EMBM, Nadeem MA, Cavagnaro PF, Chung YS (2025) GBS-derived SNP and SilicoDArT markers reveals the genetic variation and population structure of Korean buckwheat (Fagopyrum esculentum) an underutilised crop. BMC Plant Biol 25:1479. https://doi.org/10.1186/s12870-025-07633-0

10.1186/s12870-025-07633-041168792PMC12574297
5

Bankhead P (2025) Pixel size & dimensions. Introd. Bioimage Anal. URL https://bioimagebook.github.io/chapters/1-concepts/5-pixel_size/pixel_size.html (accessed 11.30.25).

6

Baumgartner A, Donahoo M, Chitwood DH, Peppe DJ (2020) The influences of environmental change and development on leaf shape in Vitis. Am J Bot 107:676-688. https://doi.org/10.1002/ajb2.1460

10.1002/ajb2.146032270876PMC7217169
7

Breiman L (2001) Random Forests. Mach Learn 45:5-32. https://doi.org/10.1023/A:1010933404324

10.1023/A:1010933404324
8

Chitwood DH, Ranjan A, Martinez CC, Headland LR, Thiem T, Kumar R, Covington MF, Hatcher T, Naylor DT, et al. (2014) A Modern Ampelography: A genetic basis for leaf shape and venation patterning in grape. PLANT Physiol 164:259-272. https://doi.org/10.1104/pp.113.229708

10.1104/pp.113.22970824285849PMC3875807
9

Cornelissen JHC, Lavorel S, Garnier E, Díaz S, Buchmann N, Gurvich DE, Reich PB, Steege HT, Morgan HD, et al. (2003) A handbook of protocols for standardised and easy measurement of plant functional traits worldwide. Aust J Bot 51:335-380. https://doi.org/10.1071/BT02124

10.1071/BT02124
10

De Luna-Bonilla OÁ, Valencia-Á S, Ibarra-Manríquez G, Morales-Saldaña S, Tovar-Sánchez E, González-Rodríguez A (2024) Leaf morphometric analysis and potential distribution modelling contribute to taxonomic differentiation in the Quercus microphylla complex. J Plant Res 137:3-19. https://doi.org/10.1007/s10265-023-01495-z

10.1007/s10265-023-01495-z37740854PMC10764464
11

Dong N, Prentice IC, Wright IJ, Evans BJ, Togashi HF, Caddy‐Retalic S, McInerney FA, Sparrow B, Leitch E, et al. (2020) Components of leaf‐trait variation along environmental gradients. New Phytol 228:82-94. https://doi.org/10.1111/nph.16558

10.1111/nph.16558
12

El‐Hendawy SE, Hu Y, Schmidhalter U (2007) Assessing the Suitability of Various Physiological Traits to Screen Wheat Genotypes for Salt Tolerance. J Integr Plant Biol 49:1352-1360. https://doi.org/10.1111/j.1744-7909.2007.00533.x

10.1111/j.1744-7909.2007.00533.x
13

Fanourakis D, Kazakos F, Nektarios PA (2021) Allometric Individual Leaf Area Estimation in Chrysanthemum. Agronomy 11:795. https://doi.org/10.3390/agronomy11040795

10.3390/agronomy11040795
14

Gardner-Lubbe S (2021) Linear discriminant analysis for multiple functional data analysis. J Appl Stat 48:1917-1933. https://doi.org/10.1080/02664763.2020.1780569

10.1080/02664763.2020.178056935706433PMC9042036
15

Graf R, Zeldovich M, Friedrich S (2024) Comparing linear discriminant analysis and supervised learning algorithms for binary classification—A method comparison study. Biom J 66:2200098. https://doi.org/10.1002/bimj.202200098

10.1002/bimj.202200098
16

Hong JP, Ro N, Lee HY, Kim GW, Kwon JK, Yamamoto E, Kang BC (2020) Genomic Selection for Prediction of Fruit-Related Traits in Pepper (Capsicum spp.). Front Plant Sci 11:570871. https://doi.org/10.3389/fpls.2020.570871

10.3389/fpls.2020.57087133193503PMC7655793
17

Idrees S, Hanif MA, Ayub MA, Hanif A, Ansari TM (2020) Chili Pepper, in: Medicinal Plants of South Asia. Elsevier, pp 113-124. https://doi.org/10.1016/B978-0-08-102659-5.00009-4

10.1016/B978-0-08-102659-5.00009-4
18

Jameson J (2024) What is Linear Discriminant Analysis (LDA)? Jacob C Jameson. URL https://jacobjameson.com/posts/2024-02-15-LDA/2024-02-15-LDA.html#:~:text=Assumptions%20of%20LDA,-LDA%20makes%20a&text=Normal%20Distribution:%20It%20assumes%20that,move%20away%20from%20the%20center. (accessed 10.20.25).

19

Jensen G (2018) AI: Weak AI vs Strong AI. Gravitron. URL https://www.gavinjensen.com/blog/2018/ai-weak-strong

20

Jones AMP, Ragone D, Aiona K, Lane WA, Murch SJ (2011) Nutritional and morphological diversity of breadfruit (Artocarpus, Moraceae): Identification of elite cultivars for food security. J Food Compos Anal 24:1091-1102. https://doi.org/10.1016/j.jfca.2011.04.002

10.1016/j.jfca.2011.04.002
21

Lapanowski AF, Gaynanova I (2020) Compressing Large Sample Data for Discriminant Analysis. https://doi.org/10.1109/BigData52589.2021.9671676

10.1109/BigData52589.2021.9671676
22

Lozada DN, Sandhu KS, Bhatta M (2023) Ridge regression and deep learning models for genome-wide selection of complex traits in New Mexican Chile peppers. BMC Genomic Data 24:80. https://doi.org/10.1186/s12863-023-01179-6

10.1186/s12863-023-01179-638110866PMC10726521
23

Mansoor S, Karunathilake EMBM, Tuan TT, Chung YS (2024) Genomics, phenomics, and machine learning in transforming plant research: Advancements and challenges. Hortic Plant J S2468014124000098. https://doi.org/10.1016/j.hpj.2023.09.005

10.1016/j.hpj.2023.09.005
24

Marron N, Dillen SY, Ceulemans R (2007) Evaluation of leaf traits for indirect selection of high yielding poplar hybrids. Environ Exp Bot 61:103-116. https://doi.org/10.1016/j.envexpbot.2007.04.002

10.1016/j.envexpbot.2007.04.002
25

Nishani YAR, Shyamalee HAPA, Ranawake AL (2025) Characterization and diversity analysis of underutilized Capsicum chinense L. accessions in sri lanka. Trop Agric Res Ext 28:73-91. https://doi.org/10.4038/tare.v28i2.5754

10.4038/tare.v28i2.5754
26

Park JE, Mansoor S, Ku K, Le AT, Tuan TT, Ko HC, Min OSS, Baloch FS, Chung YS (2025) Cost effective image-based phenotyping in Capsicum annuum germplasm for rapid assessment of traits. Plant Biotechnol Rep 19:181-196. https://doi.org/10.1007/s11816-025-00968-y

10.1007/s11816-025-00968-y
27

Poljak I, Vidaković A, Benić L, Tumpa K, Idžojtić M, Šatović Z (2024) Patterns of leaf and fruit morphological variation in marginal populations of Acer tataricum L. subsp. tataricum. Plants 13:320. https://doi.org/10.3390/plants13020320

10.3390/plants1302032038276777PMC10818317
28

Qu L, Pei Y (2024) A comprehensive review on discriminant analysis for addressing challenges of class-level limitations, small sample size, and robustness. Processes 12:1382. https://doi.org/10.3390/pr12071382

10.3390/pr12071382
29

Romero-Higareda CE, Hernández-Verdugo S, Pacheco-Olvera A, Núñez-Farfán J, Retes-Manjarrez E, López-Orona C, Osuna-Enciso T (2022) ttADAPTIVE PHNEOTYPIC plasticity of wild Capsicum annuum (Solanaceae) to variable environments of water-light availability. Acta Oecol 114:103807. https://doi.org/10.1016/j.actao.2021.103807

10.1016/j.actao.2021.103807
30

Royer DL (2012) Climate reconstruction from leaf size and shape: new developments and challenges. Paleontol Soc Pap 18:195-212. https://doi.org/10.1017/S1089332600002618

10.1017/S1089332600002618
31

Thai TT, Mansoor S, Van HT, Vu VG, Karunathilake EMBM, Le AT, Baloch FS, Chung YS, Kim J (2025) Advanced phenotyping features utilizing deep learning techniques for automated analysis of stomatal guard cell orientation. Sci Rep 15:38578. https://doi.org/10.1038/s41598-025-22412-5

10.1038/s41598-025-22412-541188350PMC12586445
32

Tomaszewski L, Kołakowski R (2023) Mobile services for smart agriculture and forestry, biodiversity monitoring, and water management: challenges for 5G/6G networks. Telecom 4:67-99. https://doi.org/10.3390/telecom4010006

10.3390/telecom4010006
33

Toprak S, Coşkun ÖF (2025) Characterization of pepper (Capsicum annuum L.) genotypes for zinc stress tolerance based on morphological traits. Harran Tarım Ve Gıda Bilim Derg 29:477-486. https://doi.org/10.29050/harranziraat.1700013

10.29050/harranziraat.1700013
34

Tripodi P, Greco B (2018) Large scale phenotyping provides insight into the diversity of vegetative and reproductive organs in a wide collection of wild and domesticated peppers (Capsicum spp.). Plants 7:103. https://doi.org/10.3390/plants7040103

10.3390/plants704010330463212PMC6313902
35

Uniyal M (2024) Linear Discriminant Analysis in Machine Learning. Appl. Roots. URL https://www.appliedaicourse.com/blog/linear-discriminant-analysis-in-machine-learning/#:~:text=Key%20Assumptions:&text=Equal%20Covariance%20Matrices:%20It%20assumes,be%20independent%20of%20each%20other. (accessed 10.20.25)

36

Viáfara-Vega RA, Granada-Agudelo M, Cárdenas-Henao H (2025) Characterization and discrimination of Colombian Capsicum accessions using elliptic fourier analysis. Genet Resour Crop Evol 72:8973-8984. https://doi.org/10.1007/s10722-025-02482-0

10.1007/s10722-025-02482-0
37

Wen W, Li Z, Shao J, Tang Y, Zhao Z, Yang J, Ding M, Zhu X, Zhou M (2021) The distribution and sustainable utilization of buckwheat resources under climate change in China. Plants 10:2081. https://doi.org/10.3390/plants10102081

10.3390/plants1010208134685889PMC8538749
38

Yang Z, Dai G, Qin K, Wu J, Wang Z, Wang C (2025) Comprehensive evaluation of germplasm resources in various goji cultivars based on leaf anatomical traits. Forests 16:187. https://doi.org/10.3390/f16010187

10.3390/f16010187
39

Zhao W, Wang L, Song Y, Jiang H, Guo X (2026) Leaf-fruit trait decoupling along environmental gradients in tropical cryptocaryeae (Lauraceae). Plants 15:126. https://doi.org/10.3390/plants15010126

10.3390/plants1501012641515071PMC12787473
Information
  • Publisher :KOREAN SOCIETY FOR HORTICULTURAL SCIENCE
  • Publisher(Ko) :한국원예학회
  • Journal Title :Horticultural Science and Technology
  • Journal Title(Ko) :원예과학기술지
  • Received Date : 2026-03-16
  • Revised Date : 2026-03-30
  • Accepted Date : 2026-04-03
  • DOI :https://doi.org/10.7235/HORT.20260011
Journal Informaiton Horticultural Science and Technology Horticultural Science and Technology
Online Submission
  • scopus
  • NRF
  • KOFST
  • crossref crossmark
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close