Abstract
In this comparative study, the effectiveness of three prominent object detection models—Teachable Machine, MobileNet, and YOLO—was evaluated using a diverse dataset consisting of images from four distinct categories: bird, horse, laptop, and sandwich. The objective was to identify the most efficient model in terms of accuracy, speed, and usability for practical applications in fields such as self-driving vehicles, robotics, security systems, and augmented reality. The dataset was meticulously curated and subjected to training across the three models. Results from the comprehensive analysis indicated that the Teachable Machine model surpassed both MobileNet and YOLO in performance, demonstrating superior accuracy and effectiveness in detecting objects across the specified categories. This research contributes significantly to the domain of artificial intelligence by providing detailed insights and comparisons of model performances, offering a valuable resource for further advancements in object detection technologies. The study not only showcases the Teachable Machine’s superiority in handling multi-class object detection problems but also sets a benchmark for future explorations in enhancing object detection methodologies.