Narsaiah Battu, Arathi Chitla

DOI: https://doi.org/10.5281/zenodo.24199252

Most image-based plant disease studies train deep networks on large laboratory datasets, yet many practical projects have only a few hundred field photographs and no GPU. This paper evaluates eight standard machine learning classifiers on a small field image dataset of 1,532 leaf photographs labelled Healthy, Powdery (powdery mildew) and Rust, using 129 hand-crafted colour, texture and shape features. Classifiers were compared by nested, repeated stratified cross-validation on the 1,382 training and validation images, and the best model was tested once on the untouched official 150-image test set. Gradient boosting achieved the highest cross-validated accuracy (92.04% ± 1.41%) and significantly outperformed random forest (89.87%; corrected resampled t-test, p = 0.021). On the official test set it reached 89.33% accuracy (95% CI 83.4–93.3%), a macro F1-score of 89.37% and Cohen’s κ = 0.84, within four points of a published DenseNet121 result on the same data. Colour and texture features were the most informative; adding shape features reduced k-nearest-neighbour accuracy from 87.37% to 66.79%. Random forest was the most data-efficient model, reaching 68.4% test accuracy with only five training images per class. The commonest error was a diseased leaf predicted as healthy (10 of 100 diseased test leaves). A bias control using only eight border pixels per image reached 58.1% in cross-validation but 38.7% on the test set (chance: 33.3%), revealing that capture conditions shared within the training split inflate cross-validated estimates. Classical machine learning is therefore a strong, low-cost baseline for field disease recognition, provided performance is reported on an independent test set.

plant disease recognition, powdery mildew, rust, field images, machine learning, hand-crafted features, gradient boosting, random forest, dataset bias

Eight standard machine learning classifiers were evaluated on a small field dataset of 1,532 leaf photographs labelled Healthy, Powdery and Rust. Gradient boosting on 129 hand-crafted features achieved 92.04% in nested cross-validation and 89.33% (κ = 0.84) on the untouched official test set, close to published deep-learning results and without a GPU. Colour and texture features carried most of the information, random forest was the most data-efficient model, and the main error was missed disease (sensitivity 90%, specificity 94%). A background-pixel control showed that shared capture conditions inflate cross-validated accuracy on this dataset, so independent test sets are essential for honest reporting.

K. G. Liakos, P. Busato, D. Moshou, S. Pearson, and D. Bochtis, “Machine learning in agriculture: A review,” Sensors, vol. 18, no. 8, Art. no. 2674, 2018.
[2] A. Kamilaris and F. X. Prenafeta-Boldú, “Deep learning in agriculture: A survey,” Comput. Electron. Agric., vol. 147, pp. 70–90, 2018.
[3] S. P. Mohanty, D. P. Hughes, and M. Salathé, “Using deep learning for image-based plant disease detection,” Front. Plant Sci., vol. 7, Art. no. 1419, 2016, doi: 10.3389/fpls.2016.01419.
[4] D. P. Hughes and M. Salathé, “An open access repository of images on plant health to enable the development of mobile disease diagnostics,” 2015, arXiv:1511.08060.
[5] J. G. A. Barbedo, “Factors influencing the use of deep learning for plant disease recognition,” Biosyst. Eng., vol. 172, pp. 84–91, 2018.
[6] R. Thapa, K. Zhang, N. Snavely, S. Belongie, and A. Khan, “The Plant Pathology Challenge 2020 data set to classify foliar disease of apples,” Appl. Plant Sci., vol. 8, no. 9, Art. no. e11390, 2020.
[7] M. A. Noyan, “Uncovering bias in the PlantVillage dataset,” 2022, arXiv:2206.04374.
[8] R. Rahman, “Plant disease recognition dataset,” Kaggle. [Online]. Available: https://www.kaggle.com/datasets/rashikrahmanpritom/plant-disease-recognition-dataset (accessed Nov. 2026).
[9] M. Purba, “Plant disease recognition based on leaf images using sequential-based DenseNet architecture,” J. Sci. Appl. Informatics (JSAI), vol. 9, no. 1, pp. 153–159, 2026, doi: 10.36085/jsai.v9i1.9988.
[10] A. A. Al-Zubi, “CNN-based detection of powdery mildew and rust in apple orchards for optimizing crop management,” J. Anim. Plant Sci., vol. 35, no. 2, pp. 381–389, 2025.
[11] S. Arivazhagan, R. Newlin Shebiah, S. Ananthi, and S. Vishnu Varthini, “Detection of unhealthy region of plant leaves and classification of plant leaf diseases using texture features,” Agric. Eng. Int.: CIGR J., vol. 15, no. 1, pp. 211–217, 2013.
[12] K. P. Ferentinos, “Deep learning models for plant disease detection and diagnosis,” Comput. Electron. Agric., vol. 145, pp. 311–318, 2018.
[13] E. C. Too, L. Yujian, S. Njuki, and L. Yingchun, “A comparative study of fine-tuning deep learning models for plant disease identification,” Comput. Electron. Agric., vol. 161, pp. 272–279, 2019.
[14] J. G. A. Barbedo, “Impact of dataset size and variety on the effectiveness of deep learning and transfer learning for plant disease classification,” Comput. Electron. Agric., vol. 153, pp. 46–53, 2018.
[15] T. Ojala, M. Pietikäinen, and T. Mäenpää, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 7, pp. 971–987, Jul. 2002.
[16] R. M. Haralick, K. Shanmugam, and I. Dinstein, “Textural features for image classification,” IEEE Trans. Syst., Man, Cybern., vol. SMC-3, no. 6, pp. 610–621, Nov. 1973.
[17] M.-K. Hu, “Visual pattern recognition by moment invariants,” IRE Trans. Inf. Theory, vol. 8, no. 2, pp. 179–187, Feb. 1962.
[18] N. Dalal and B. Triggs, “Histograms of oriented gradients for human detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2005, vol. 1, pp. 886–893.
[19] F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011.
[20] L. Breiman, “Random forests,” Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001.
[21] J. H. Friedman, “Greedy function approximation: A gradient boosting machine,” Ann. Statist., vol. 29, no. 5, pp. 1189–1232, 2001.
[22] G. Ke et al., “LightGBM: A highly efficient gradient boosting decision tree,” in Adv. Neural Inf. Process. Syst. (NeurIPS), vol. 30, 2017, pp. 3146–3154.
[23] C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.
[24] S. Varma and R. Simon, “Bias in error estimation when using cross-validation for model selection,” BMC Bioinformatics, vol. 7, Art. no. 91, 2006.
[25] J. Demšar, “Statistical comparisons of classifiers over multiple data sets,” J. Mach. Learn. Res., vol. 7, pp. 1–30, 2006.
[26] C. Nadeau and Y. Bengio, “Inference for the generalization error,” Mach. Learn., vol. 52, no. 3, pp. 239–281, 2003.
[27] S. van der Walt et al., “scikit-image: Image processing in Python,” PeerJ, vol. 2, Art. no. e453, 2014.

Narsaiah Battu, Arathi Chitla (2026). Evaluation of Standard Machine Learning for Plant Leaf Disease Recognition on a Small Field Image Dataset. International Journal of Computer Science Engineering Techniques, 10(6), 428–433. ISSN: 2455-135X. DOI: https://doi.org/10.5281/zenodo.24199252