Guiding the Creation of Deep Learning-based Object Detectors

TL;DR

This paper presents a set of Jupyter notebooks designed to simplify the creation of YOLO-based object detection models, demonstrated with stomata images achieving high accuracy.

Contribution

It introduces an accessible toolkit that democratizes YOLO model development for non-experts through interactive notebooks.

Findings

Achieved a mAP of 90.91% on stomata dataset.

Made YOLO model creation more accessible for non-experts.

Validated the approach with real-world biomedical images.

Abstract

Object detection is a computer vision field that has applications in several contexts ranging from biomedicine and agriculture to security. In the last years, several deep learning techniques have greatly improved object detection models. Among those techniques, we can highlight the YOLO approach, that allows the construction of accurate models that can be employed in real-time applications. However, as most deep learning techniques, YOLO has a steep learning curve and creating models using this approach might be challenging for non-expert users. In this work, we tackle this problem by constructing a suite of Jupyter notebooks that democratizes the construction of object detection models using YOLO. The suitability of our approach has been proven with a dataset of stomata images where we have achieved a mAP of 90.91%.