Workshop on Computer Vision for Bioanalytical Chemists: Classification and Detection of Amoebae Using Optical Microscopy Image Analysis with Machine Learning

Abstract

Computer vision (CV) is a subfield of artificial intelligence (AI) that trains computers to understand our visual world based on digital images. There are many successful applications of CV including face and hand gesture detection, weather recording, smart farming, and self-driving cars. Recent advances in computer vision with machine learning (ML) provide a new avenue for microbiological analysis. ML has been proven efficient and precise due to its automatic analysis of the geometric features and texture of organisms in optical microscopy images. This work describes a workshop that teaches basics of CV using ML (image classification, object detection) using Python notebook examples in Google Colab and Jetson Nano. The workshop is designed for senior undergraduate or beginning graduate chemistry students who would like to learn how to classify and detect microorganisms such as amoebae. The workshop content includes three sections: image classification with convolutional neutral netowork (CNN) in Google Colab, object detection with Mask R-CNN in Google Colab, and object detection with SSD-mobilenet in Jetson Nano.