Classification of Microscopic Images of Bacteria using Deep Convolutional Neural Network

With the advancement of technology, now the task of recognizing images from digital electron microscopes is being performed by computers supported machine-learning and computer-vision technologies. Besides, the newest generation of convolutional neural networks (CNN) have achieved impressive leads to the sector of image classification recently. Thus, during this paper, we have investigated an approach to automate the method of bacteria recognition and classification with the utilization of deep convolutional neural network (DCNN). We have used the transfer learning method to retrain the Inception DCNN model with of a dataset of quite 500 microscopic images of 5 different species that are harmful to human-health. 20% images of the dataset were randomly chosen and separated, which were wont to test the classification accuracy of the network. The retrained model was ready to recognize and classify all 5 different species of bacteria, while the experimental results of prediction achieved accuracy of around 95%.