Diseases in plants which are economically important results in a notable amount of degradation in both standard and quantity, which sometimes leads to the compensation of gain, can be obtained from entire crop. To enhance the profit, it becomes the need of the hour to diagnose the viruses at an initial phase. Recently, various ML techniques like convolutionary neural networks, automated drones and robots, transfer learning, mobile applications and integration with IOT devices have become increasingly popular in detecting plant diseases. This review mainly focuses on three research areas where progress has been made at fast pace. These areas include (a) utilization of several image processing techniques to analyze crop images for disease symptoms; (b)Imaging technologies that utilize multispectral and hyperspectral methods capture data outside the visible spectrum, uncovering concealed indicators of disease; (c)Integration of sensors with IoT devices to collect environmental data, aiding in the prediction of disease outbreaks.