This research presents a model for detecting and counting students in educational environments. To achieve this, computer vision and computational neural networks (CNN) were used to analyze the “Classroom Monitoring Dataset.” Data cleaning and image normalization were performed with a 640 \(\,\times \,\) 640 resolution. An annotation process was performed using Roboflow. Different pretrained CNN models were tested using YOLOv8 to verify the accuracy of student identification and counting. The database was divided into 80% for training, 10% for testing, and 10% for evaluation. The goal was to develop a robust, efficient system that accurately counts students in a classroom in real time. This system was able to adapt to a variety of environmental and occlusion conditions, as well as classroom diversity, and provide reliable attendance metrics for use in educational strategies.