BACTERIAL IMAGE CLASSIFICATION USING DEEP LEARNING

Abstract

Bacterial Image Classification Using Deep Learning is a system which is designed to classify bacterial images according to their species. Numerous uses for bacteria image classification include medical diagnosis, microbiological research, quality control, environmental monitor ing, and biodefense. Traditional methods of bacteria classification involve manual observation and analysis by experts, which can be time-consuming and prone to errors. The method of recognizing and categorizing various species of bacteria using microscopic photographs is known as ”bacterial image classification”. To process the image data and extract pertinent traits that can be used to categorize various species of bacteria, using deep learning techniques such as two CNN models, ResNet-50 and Resnet-34, as well as ANN and LSTM . In deep learning, high-level features are extracted from input data, such as photographs, using neural networks with several layers. Convolutional Neural Networks (CNNs), a type of deep learning model, are used to extract pertinent characteristics from images. Convolutional filters are used to the input picture in CNNs in order to extract spatial characteristics from images. Two CNN models, ResNet-50 and Resnet-34, as well as ANN and LSTM is used. These models focus on categorizing species of bacteria. Studies have demonstrated that the CNN model ResNet-50 exhibited a classification accuracy of 100 percent and produce the best outcomes than the Resnet-34,ANN and LSTM