Lemon leaves are largely susceptible to citrus-specific conditions that beget significant impact on yield and fruit quality. Traditional opinion involves homemade examination, which is labour-ferocious, prone to crimes, and also not scalable to large citrus orchards. In order to remove these limitations, this work proposes a light-weight Convolutional Neural Network (CNN) model specific to accurate bracket of lemon splint conditions from image inputs. The model as it was proposed was trained on a general dataset of over 18,000 labeled images representing eight classes, including healthy leaves and seven classes of conditions like Citrus Canker, Black Spot, Greening, Scab, Melanosed, Anthracnose, and Powdery Mildew. Through expansive preprocessing and data addition ways, the model achieved enhanced conception under image conditions of different types. Performance measures similar as delicacy (98.2), perfection (98.4), recall (98.1), and F1-score (98.3) show the strength and effectiveness of the model. Compared to state- of-the-art models VGG16, Mobile Net, and InceptionV3, the proposed armature performed more in delicacy and effectiveness. Because of its light-weighted nature, it can be suited for real-time deployment on edge bias with a cost- effective, scalable, and accurate early complaint discovery system for citrus husbandry. Short-term advancements are putting the model in phones and reasoning in order to be suitable to handle multiple citrus species. The agricultural sector is increasingly adopting artificial intelligence and deep learning techniques to improve crop monitoring and disease management. Early and accurate identification of plant diseases plays a crucial role in preventing large-scale crop losses and ensuring better agricultural productivity. In citrus cultivation, diseases affecting lemon leaves often spread rapidly if not detected in their early stages, making automated detection systems highly valuable for farmers and agricultural experts. This study focuses on developing an intelligent image-based disease detection system that can automatically classify lemon leaf diseases using deep learning techniques. The proposed system utilizes a Convolutional Neural Network (CNN) architecture capable of extracting important visual features such as color variations, texture patterns, and lesion structures directly from leaf images. By eliminating the need for manual feature extraction, the model improves both accuracy and efficiency in disease classification. To enhance the robustness of the model, various preprocessing techniques such as image resizing, normalization, and data augmentation methods including rotation, flipping, and scaling were applied. These techniques helped the model generalize better to different lighting conditions, backgrounds, and leaf orientations that may occur in real-world scenarios. The experimental evaluation demonstrates that the proposed model not only provides high classification accuracy but also maintains computational efficiency suitable for deployment on low- resource devices. This makes the system practical for real-time field applications where farmers can capture leaf images using smartphones or portable cameras and obtain instant disease predictions.
Lemon Leaf Disease Detection, Convolutional Neural Network (CNN), Deep Learning, Image Classification, Citrus Disease Identification, Plant Disease Detection, Computer Vision in Agriculture, Data Augmentation, Precision Agriculture, Mobile-based Disease Diagnosis, feature extraction, segmentation, disease diagnosis.
International Journal of Trend in Scientific Research and Development - IJTSRD having
online ISSN 2456-6470. IJTSRD is a leading Open Access, Peer-Reviewed International
Journal which provides rapid publication of your research articles and aims to promote
the theory and practice along with knowledge sharing between researchers, developers,
engineers, students, and practitioners working in and around the world in many areas
like Sciences, Technology, Innovation, Engineering, Agriculture, Management and
many more and it is recommended by all Universities, review articles and short communications
in all subjects. IJTSRD running an International Journal who are proving quality
publication of peer reviewed and refereed international journals from diverse fields
that emphasizes new research, development and their applications. IJTSRD provides
an online access to exchange your research work, technical notes & surveying results
among professionals throughout the world in e-journals. IJTSRD is a fastest growing
and dynamic professional organization. The aim of this organization is to provide
access not only to world class research resources, but through its professionals
aim to bring in a significant transformation in the real of open access journals
and online publishing.