RECOGNITION OF DISEASES IN APPLE TREE LEAVES USING BAG OF FEATURES AND SVM WITH VISUAL VOCABULARY VARIATION
DOI:
https://doi.org/10.47820/recima21.v7i2.7212Keywords:
Computer vision. Bag of Features. SVM (Support Vector Machine). Plant diseasesAbstract
Automatic recognition of plant diseases has become a fundamental tool for precision agriculture, especially in crops of high commercial value, such as apple trees (Malus domestica). In this work, a classification approach based on the Bag of Features (BoF) model combined with Support Vector Machines (SVM) is proposed and applied to the Apple Tree Leaf dataset, which contains four pathological classes: Alternaria leaf spot, Brown spot, Gray spot, and Rust. The study is distinguished by a systematic investigation of the impact of visual vocabulary size during the feature quantization stage, evaluating five BoF configurations (100, 300, 700, 1000, and 3000 words). The experiments, conducted in MATLAB R2023b, reveal that intermediate vocabularies—particularly between 700 and 1000 terms—provide the best trade-off between discriminative power and generalization capability, resulting in high accuracy rates for most classes. Nevertheless, the Gray spot class exhibited greater difficulty in recognition, reinforcing the need for complementary strategies for its discrimination. The findings confirm the effectiveness of classical computer vision methods on moderately sized datasets and provide relevant insights for the development of leaf diagnosis systems applied to agricultural contexts.
Downloads
References
ABADE, André; FERREIRA, Paulo Afonso; VIDAL, Flavio de Barros. Plant diseases recognition on images using convolutional neural networks: a systematic review. Computers and Electronics in Agriculture, v. 185, p. 106125, jun. 2021. DOI: 10.1016/j.compag.2021.106125. DOI: https://doi.org/10.1016/j.compag.2021.106125
BARBEDO, J. G. A. A review on the main challenges in automatic plant disease identification based on visible range images. Biosystems Engineering, v. 144, p. 52-60, 2016. DOI: 10.1016/j.biosystemseng.2016.01.017 DOI: https://doi.org/10.1016/j.biosystemseng.2016.01.017
BURGES, Christopher J. C. A tutorial on support vector machines for pattern recognition. Data Mining and Knowledge Discovery, v. 2, p. 121–167, 1998. DOI: 10.1023/A:1009715923555. Disponível em: https://doi.org/10.1023/A:1009715923555. Acesso em: 3 fev. 2026. DOI: https://doi.org/10.1023/A:1009715923555
CORTES, Corinna; VAPNIK, Vladimir. Support-vector networks. Machine Learning, v. 20, n. 3, p. 273–297, 1995. DOI: 10.1007/BF00994018. Disponível em: https://doi.org/10.1007/BF00994018. Acesso em: 3 fev. 2026 DOI: https://doi.org/10.1023/A:1022627411411
CSURKA, Gabriella; DANCE, Christopher R.; FAN, Lixin; WILLAMOWSKI, Jutta; BRAY, Cédric. Visual categorization with bags of keypoints. In: EUROPEAN CONFERENCE ON COMPUTER VISION (ECCV), 8., 2004, Prague. Proceedings… Workshop on Statistical Learning in Computer Vision. Xerox Research Centre Europe (XRCE), 2004. p. 1–22. Disponível em: https://www.cs.cmu.edu/~efros/courses/LBMV07/Papers/csurka-eccv-04.pdf. Acesso em: 1 fev. 2026.
FERENTINOS, K. P. Deep learning models for plant disease detection and diagnosis. Computers and Electronics in Agriculture, v. 145, p. 311–318, 2018. DOI: 10.1016/j.compag.2018.01.009 DOI: https://doi.org/10.1016/j.compag.2018.01.009
HUANG, Yongzhen; WU, Zifeng; WANG, Liang; TAN, Tieniu. Feature coding in image classification: a comprehensive study. IEEE Transactions on Pattern Analysis and Machine Intelligence, v. 36, n. 3, p. 493–506, 2014. DOI: 10.1109/TPAMI.2013.113. Disponível em: https://doi.org/10.1109/TPAMI.2013.113. Acesso em: 2 fev. 2026. DOI: https://doi.org/10.1109/TPAMI.2013.113
LECUN, Y.; BENGIO, Y.; HINTON, G. Deep learning. Nature, v. 521, n. 7553, p. 436–444, 2015. DOI: 10.1038/nature14539. DOI: https://doi.org/10.1038/nature14539
MOHANTY, S. P.; HUGHES, D. P.; SALATHÉ, M. Using deep learning for image-based plant disease detection. Frontiers in Plant Science, v. 7, art. 1419, 2016. DOI: 10.3389/fpls.2016.01419 DOI: https://doi.org/10.3389/fpls.2016.01419
NOWAK, Eric; JURIE, Frédéric; TRIGGS, Bill. Sampling strategies for bag-of-features image classification. In: EUROPEAN CONFERENCE ON COMPUTER VISION (ECCV), 9., 2006. Proceedings… Berlin: Springer, 2006. p. 490–503. (Lecture Notes in Computer Science). DOI: 10.1007/11744085_38. Disponível em: https://doi.org/10.1007/11744085_38. Acesso em: 3 fev. 2026. DOI: https://doi.org/10.1007/11744085_38
PAWARA, Pornntiwa; OKAFOR, Emmanuel; SURINTA, Olarik; SCHOMAKER, Lambertus; WIERING, Marco. Comparing Local Descriptors and Bags of Visual Words to Deep Convolutional Neural Networks for Plant Recognition. In: INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION APPLICATIONS AND METHODS (ICPRAM), 6., 2017, Porto. Proceedings… [S. l.]: SciTePress, 2017. p. 479–486. DOI: 10.5220/0006196204790486. Disponível em: https://www.scitepress.org/papers/2017/61962/61962.pdf. Acesso em: 1 fev. 2026. DOI: https://doi.org/10.5220/0006196204790486
PIRES, Rillian Diello Lucas; GONÇALVES, Diogo Nunes; ORUÊ, Jonatan Patrick Margarido; KANASHIRO, Wesley Eiji Sanches; RODRIGUES JR., Jose F.; MACHADO, Bruno Brandoli; GONÇALVES, Wesley Nunes. Local descriptors for soybean disease recognition. Computers and Electronics in Agriculture, v. 125, p. 48–55, 2016. DOI: 10.1016/j.compag.2016.04.032. DOI: https://doi.org/10.1016/j.compag.2016.04.032
YANG, Jun; JIANG, Yu-Gang; HAUPTMANN, Alexander G.; NGO, Chong-Wah. Evaluating bag-of-visual-words representations in scene classification. In: INTERNATIONAL WORKSHOP ON MULTIMEDIA INFORMATION RETRIEVAL (MIR), 2007. Proceedings… New York: ACM, 2007. p. 197–206. DOI: 10.1145/1290082.1290111. Disponível em: https://doi.org/10.1145/1290082.1290111. Acesso em: 3 fev. 2026. DOI: https://doi.org/10.1145/1290082.1290111
ZHONG, Yong; ZHAO, Ming. Research on deep learning in apple leaf disease recognition. Computers and Electronics in Agriculture, v. 168, art. 105146, 2020. DOI: 10.1016/j.compag.2019.105146. Disponível em: https://doi.org/10.1016/j.compag.2019.105146. Acesso em: 3 fev. 2026. DOI: https://doi.org/10.1016/j.compag.2019.105146
Downloads
Published
Issue
Section
Categories
License
Copyright (c) 2026 RECIMA21 - Revista Científica Multidisciplinar - ISSN 2675-6218
This work is licensed under a Creative Commons Attribution 4.0 International License.
Os direitos autorais dos artigos/resenhas/TCCs publicados pertecem à revista RECIMA21, e seguem o padrão Creative Commons (CC BY 4.0), permitindo a cópia ou reprodução, desde que cite a fonte e respeite os direitos dos autores e contenham menção aos mesmos nos créditos. Toda e qualquer obra publicada na revista, seu conteúdo é de responsabilidade dos autores, cabendo a RECIMA21 apenas ser o veículo de divulgação, seguindo os padrões nacionais e internacionais de publicação.
