VGGMobiNet: A Unified VGG16-MobileNetV2 Model for Brinjal Leaf Disease Analysis and Management

View at publisher Summarise with VIRAT
Authors: Gogineni Manju Sri, Akavarapu Kavya Sri, Palaparthi Samarpan, Vangalla Veera Babu
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study describes a complete, automated, deep learning-based approach for diagnosing and recommending treatments for brinjal (eggplant) leaf diseases. A carefully designed hybrid architecture using VGG16 for feature extraction and MobileNetV2 for classification is employed as the backbone of the present method. The model has been trained using a dataset containing brinjal leaf images of both healthy and diseased categories, and it can detect with precision six diseases along with the healthy state: Insect Pest, Small Leaf, Leaf Spot, Mosaic Virus, White Mold, and Wilt Leaf. The system exhibits remarkable classification accuracy by making use of transfer learning and data augmentation techniques and at the same time reducing the requirement of manual feature engineering and computation overhead to a great extent, the model achieves a classification accuracy of 97 %. The small size of the hybrid model provides the advantage of fast inference and easy deployment in terms of resources, thereby making it suitable for real-time field applications and mobile-based agricultural systems. The entire agricultural sector, in general, and the smart agriculture sub-sector, in particular, will benefit from the proposed system through supporting early disease diagnosis, sustainable crop management, and increased agricultural productivity.

Fields of Study & Subjects

Smart Agriculture and AI Advanced Neural Network Applications Industrial Vision Systems and Defect Detection

Publication details

Journal / source
International Conference on Communication, Computing and Electronics Systems (ICCCES)
Pages
1631–1636
Publication date
21 January 2026
Language
EN