A Comparative Hybrid CNN-SVM Framework for Multi-Crop Nutrient Deficiency Classification Using Leaf Pattern Analysis
Keywords:
Nutrient deficiency; Deep learning; CNN; SVM; EfficientNetB0; DenseNet121; leaf pattern analysis; vegetable crops; precision agricultureAbstract
Early and accurate identification of nutrient deficiency in vegetable crops is essential for improving cropproductivity, reducing yield loss, and supporting precision agriculture. Visual symptoms of nutrient deficiencycommonly appear on leaves in the form of chlorosis, necrosis, marginal yellowing, interveinal discoloration, andstructural deformation. However, manual identification is difficult because deficiency symptoms vary across crop species and may overlap among single and combined nutrient stress conditions.
References
[1] S. P. Mohanty, D. P. Hughes, and M. Salathe, "Using deep learning for image-based plant disease detection," Frontiers in Plant Science, vol. 7, Article 1419, 2016.
[2] K. P. Ferentinos, "Deep learning models for plant disease detection and diagnosis," Computers and Electronics in Agriculture, vol. 145, pp. 311-318, 2018.
