This study presents a classification method for microscopic images of bacteria using a convolutional neural network (CNN). The proposed approach includes a pre-processing step to enhance the contrast and reduce noise in the images, followed by a feature extraction step using a pre-trained CNN. The extracted features are then fed into a support vector machine (SVM) classifier to classify the images into different bacterial species. The method was evaluated on a dataset of microscopic images of bacteria and achieved an accuracy of over 95%, demonstrating its potential as a tool for automated bacterial species identification. The proposed approach has the potential to improve the efficiency and accuracy of bacterial classification in various fields, such as microbiology, medicine, and environmental monitoring. The results of this study can inform the development of more accurate and efficient tools for automated bacterial identification, which can have significant implications for disease diagnosis and treatment, as well as environmental monitoring and management