Application of object detection and action recognition toward automated recognition of chemical experiments

Abstract

Developments in deep learning-based computer vision technology have significantly improved the performance of applied research. The use of image recognition methods to manually conduct chemical experiments is promising for digitizing traditional practices in terms of experimental recording, hazard management, and educational applications. This study investigated the feasibility of automatically recognizing manual chemical experiments using recent image recognition technology. Both object detection and action recognition were evaluated, that is, the identification of the locations and types of objects in images and the inference of human actions in videos. The image and video datasets for the chemical experiments were originally constructed by capturing scenes from actual organic chemistry laboratories. The assessment of inference accuracy indicates that image recognition methods can effectively detect chemical apparatuses and classify manipulations in experiments.