Multi-face Detection, Face Count, and Individual Emotion Detection with Python

 To install the necessary Python packages 
 pip install -r requirements.txt

Basic Warnings:

a) Recommended Python Version for running this program: "Python 3.11"

b) To ensure the necessary Python packages work, the command "pip install -r requirements.txt" must be executed through Command Prompt (CMD) / Terminal (Linux - MacOS).

c) It is recommended to run this program with administrator privileges to avoid errors and ensure stable execution.

The aim of this project is to develop software using the Python programming language that performs these functions.
The software will be capable of detecting both a single face and multiple faces, and will perform individual emotion analysis for each face.
While similar studies have been conducted in the past, the unique aspect of this project is the use of up-to-date technologies and the goal of achieving more accurate results by utilizing a broader dataset.
The resulting software can be used as a tool for understanding human emotions.

In this project, the Convolutional Neural Network (CNN) method is used to perform multi-face detection, face counting, and individual emotion detection using the Python programming language.
This method allows the features of the data to be learned through filters, leading to more accurate results. The data is processed using OpenCV, an image processing library.
OpenCV provides many tools and functions used for image acquisition, face detection, and emotion analysis.
Additionally, the weights of the filters used in data processing are learned automatically using deep learning techniques.

A dataset consisting of images representing various emotions through facial expressions was used for data collection.
The images in the dataset include different light conditions, poses, and combinations of facial expressions.
In this study, the results were evaluated using various metrics, including accuracy rate, false positives, and false negatives.
The results show that high accuracy rates were achieved in multi-face detection, face counting, and individual emotion detection tasks.