DOI 10.17605/OSF.IO/NEX7V 1639 | V18.I05 RESNEXT-BASED IMAGE CLASSIFICATION MODEL FOR PLANT DISEASE IDENTIFICATION SHASHI TANWAR 1 and JASPREET SINGH 2 1, 2 School of Engineering, Computer Science Dept., G D Goenka University, Gurugram India. Abstract Advancement in Automation has brought a revolution in the field of agriculture for various applications. Digital image processing combined with Machine Learning techniques can provide support in the area of agriculture by assisting in the classification and detection of plant diseases. In this paper, the ResNext-50 model is presented for the classification of plant diseases and has proved to be more efficient not only in terms of Image Classification but also in terms of Image Segmentation. The model is developed by making a few modifications to the ResNet- 50 model and adding some layers. A dataset from Kaggle is used having 87867 images for training and validation. ResNet-50 and ResNext-50 are trained on 25 epochs with 80% images and then validation is done with the remaining 20% images. The ResNext-50 model is found to have better training and validation accuracy than the ResNet-50 model. ResNext-50 model is found to have a training accuracy of 99.65% and a validation accuracy of 94.05% after the last epoch, on the other hand, the ResNet-50 model is found to have a training accuracy of 99.32% and a validation accuracy of 93.45% after the last epoch. The accuracy and loss results have proved the efficiency of the ResNext-50 model over the ResNet-50 model. Keywords: CNN, Deep Learning, Machine Learning, Plant Disease Classification, ResNext Model. 1. INTRODUCTION Agriculture is the mainstay of the Indian economy. Various types of plants and crops are being grown as per requirement of society and needs of day to day basic requirements. But the quality and quantity of agriculture is affected by the diseases in plants. The early identification of plants infections is the primary and most crucial activity in agriculture to improvise the quality of plant production for economic growth. Even today, most of the verification is done manually that may not be easy to accurately detect the disease and its type. Advancement in Automation has revolutionized every field and it is also being applied in the field of agriculture for various applications. With the help of artificial intelligence, an automated system can be made able to identify plant diseases with much better accuracy. If the information gathered is proper and accurate, the issue of identification of plant diseases can be solved effectively. Similarly, there are a number of different diseases affecting plants which results in loss of production to a great extent. Thus, it is of utmost importance to detect, analyze and classify diseases. Digital image processing combined with Machine Learning techniques can help in classification and detection of plant diseases [1]–[4] [1] – [3]. Machine Learning is an art of developing algorithms of models that makes a system capable of learning automatically through experience using some training data without being explicitly programmed. These machine learning algorithms are being applied in various different fields such as agriculture, banking [5], customer services, defense services,