Handwritten Digits Detection Using Convolutional Neural Network

Numbers are a collection of many lines and curves and play a vital role in everyday life. Each person has unique characteristics in handwriting, making handwritten digit detection a challenging task. This paper presents an approach for detecting handwritten digits using deep learning algorithms, particularly the Convolutional Neural Network (CNN)-based YOLOv8 family models. The main objective is to compare various YOLOv8 variants (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, and YOLOv8x) and determine the most optimal one in detecting handwritten digits. Experimental results show that the YOLOv8x variant achieves the highest performance, with a mean Average Precision (mAP) of 96.9%, a recall of 100%, a precision of 99.8%, and an F1-score of 99.9%. The research contributions are achieving high accuracy in handwritten digit detection using the YOLOv8x model and utilizing a custom primary dataset of 3,000 handwritten digits for training and evaluation, which adds novelty and real-world relevance to the study.