Sakshi Pandey et al, International Journal of Advanced Trends in Computer Science and Engineering, 13(3), May - June 2024, 148 - 160 148 Disease Detection In Rice And Wheat Leaves: A Comparative Study On Various Deep Learning Techniques Sakshi Pandey 1 , Kuldeep Yogi 2 , Ayush Ranjan 3 1 Department of Computer Science, Banasthali Vidyapith, Rajasthan, INDIA, pandey.sakshi16@gmail.com 2 Department of Computer Science, Banasthali Vidyapith, Rajasthan, INDIA, ykuldeep@banasthali.in 3 Department of Computer Science, Rajasthan University, Rajasthan, INDIA, aayushranjanpathak@gmail.com Received Date : April 11, 2024 Accepted Date: May 21, 2024 Published Date: June 06, 2024 ABSTRACT Rice and wheat are considered as the most significant foods in agriculture all over the globe. Around 50% of all calories consumed in the human diet are rendered by both rice and wheat. Rice is a rich source of carbohydrates that is the main energy source of the human body. Wheat, which comprises vitamins and minerals, is a staple food source. Also, wheat is extensively used as flour to make a variety of food products. However, the disease that occurs in the leaves of rice and wheat could decelerate the production of these two food sources. Thus, timely detection of disease that occurs within the rice and wheat leaves is very significant. To detect Rice Leaf Diseases (RLD) and Wheat Leaf Diseases (WLD), numerous conventional methods are established. Specifically, You Only Look Once (YOLO), Faster Region- based Convolutional Neural Network (FRCNN), and Single Shot Detector (SSD) are extensively implemented in various works to detect diverse leaf diseases in rice and wheat plants. Therefore, in this review, the merits and demerits of the traditional Object Detection (OD) models in RLD and WLD detection are provided systematically. The robustness of the Deep learning (DL) techniques in detecting various kinds of leaf diseases in rice and wheat plants with a classification accuracy of 99% and a precision of 98% is proved by the analysis outcomes. Key words: Rice Leaf Diseases (RLD), Wheat Leaf Diseases (WLD), Leaf disease detection, Comparative study, Classification models, Deep learning techniques, and Object detection. 1. INTRODUCTION Agriculture is the backbone and vital source of income for many people in India and numerous global countries; also, the global food systems are highly interconnected among those countries [1]. The major food sources of the global food systems for human survival are plants and crops. Hence, taking care of plants and crops is very significant [2]. The most important factor of the global food system is Food Security (FS), which also states that “all people have physical, social, and economic access to sufficient and nutritious food to meet their dietary needs for an active and healthy life at all times” [3]. More than half of the global population consumes rice as the primary food source. Rice is a major staple food. Moreover, wheat, which is utilized as a raw material for numerous food industries worldwide, is another major staple food [4]. Wheat is enriched with vitamins and minerals and rice is enriched with carbohydrates that are crucial for the human body [5]. Nevertheless, rice and wheat plants are easily susceptible to several diseases and pests. A significant factor that also affects the growth of the paddy and wheat crops is climatic changes, namely unseasonal rainfall and temperature variations. To protect healthy plants from diseased plants, quick detection of diseased plants is very important [6]. For sustainable and correct agriculture, the timely detection of plant disease is significant. Majority of the plant diseases display visible symptoms; some plant diseases do not have any visible symptoms [7]. Therefore, manual detection of plant diseases is a slow and inaccurate process. Hence, numerous Machine Learning (ML) and DL techniques have been developed in the last 10 years for an early, quick, and accurate diagnosis and detection of plant diseases [8]. In the following Figure 1, the process of the plant disease detection models is displayed. Figure 1: Process of Plant disease detection Some of the OD algorithms utilized to detect numerous types of plant diseases are some prevailing techniques, namely YOLO, Convolutional Neural Network (CNN), Region-based CNN (RCNN), FRCNN, EfficientNet, and SSD [9]. These established models categorized healthy and ISSN 2278-3091 Volume 13, No.3, May - June 2024 International Journal of Advanced Trends in Computer Science and Engineering Available Online at http://www.warse.org/IJATCS1E/static/pdf/file/ijatcse081332024.pdf https://doi.org/10.30534/ijatcse/2024/081332024