Machine Learning for the Visually Impaired: Benchmarking Object Detection Models

Abstract

This research paper benchmarks object detection models, a form of machine learning, to determine which algorithm would be most beneficial for the visually impaired to locate objects that are used in everyday life. As most benchmarking experiments test object detection models with a variety of objects, it is essential to test the models using images of more relevant objects to find the most suitable algorithm. The models are tested using still images from the COCO database. Pretrained models employing five of the most popular object detection algorithms are used to process the images and find each model’s detection accuracy. To simulate real life scenarios, these objects may be partially hidden or at a distance. For each image, the models return a list of detections providing the names, confidence rating, and location of each object detected. These results will be filtered to remove detections with low confidence ratings as well as detections of irrelevant objects. The remaining results are compared to the dataset of object names and locations provided by the COCO database to calculate the distance between the predicted object locations and the true location. The algorithms will be ranked based on the number of failed detections, the time taken to analyze each image, and the accuracy of each object’s determined location.