A Comparison of Different Optimization Techniques in AlexNet for Plant Disease Classification: SGD, Adadelta, ASGD and Adagrad

Plant diseases are a biggest challenge for the farmers. Agriculture relies heavily on its production, and diagnosis of plant disease in an accurate manner will help in identification of the appropriate disease. If correct identification was not performed, there might be a significant financial loss that could have an impact on both farmers and the national economy. For resolving this issue, the AlexNet was employed, a convolutional neural network method. In this research, AlexNet is used to classify the diseases occurring in chilli, cauliflower and sunflower. This AlexNet model, with Stochastic Gradient Descent(SGD) algorithm optimization techniques had achieved 82% accuracy for the overall classification of the test images of chilli plant, 98% accuracy for the overall classification of the test images of cauliflower plant and 91% accuracy for the overall classification of the test images of sunflower plant; with Adadelta optimization 86%, 99% and 93% accuracy was achieved for the overall classification of the test pictures of chilli plant, cauliflower plant and sunflower plant respectively. After using the Asynchronous Stochastic Gradient(ASGD) optimization with AlexNet model, the accuracy obtained are 88% for the test images of chilli plant, 98% for the test images of cauliflower plant and 91% for the test images of sunflower plant; and finally, AdaGrad optimization with AlexNet achieved accuracy of 80% for the test images of chilli plant, 9 8% for the test images of cauliflower plant and 93% for the test images of sunflower plant.