A Comparative Study on Algorithms for Plant Disease Detection Using Transfer Learning

There are many species of plants in this world. Some of which are known and some are unknown. Each variety of plants has different kinds of diseases. Recognising these diseases can help the plants from not getting affected further. This process requires the help of experts. But visually observing and diagnosing each diseases requires lots of time and resources. In this study, the authors make use of MobileNetV2, VGG16, VGG19, NASNet and Inception Resnet to process data of different plant image samples to get fast analysis of the various diseases. This knowledge of plant diseases collected can then help gardeners, horticulturists, environmentalists, farmers, researchers, etc for different needs.