https://github.com/akshaypatra/expression_detector

The Expression Detector is an AI-based system that identifies and classifies human facial expressions in real-time . It utilizes computer vision and deep learning techniques to analyze facial features and determine the emotional state of a person, such as happiness, sadness, anger, surprise, fear, disgust, or neutrality.
https://github.com/akshaypatra/expression_detector

keras-tensorflow neural-network numpy opencv-python python3

Last synced: 10 months ago
JSON representation

The Expression Detector is an AI-based system that identifies and classifies human facial expressions in real-time . It utilizes computer vision and deep learning techniques to analyze facial features and determine the emotional state of a person, such as happiness, sadness, anger, surprise, fear, disgust, or neutrality.

• Host: GitHub
• URL: https://github.com/akshaypatra/expression_detector
• Owner: akshaypatra
• Created: 2025-04-09T14:10:07.000Z (10 months ago)
• Default Branch: main
• Last Pushed: 2025-04-10T16:46:51.000Z (10 months ago)
• Last Synced: 2025-04-11T04:43:55.880Z (10 months ago)
• Topics: keras-tensorflow, neural-network, numpy, opencv-python, python3
• Language: Python
• Homepage:
• Size: 11.7 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
## 🎭 Expression Detector 

### Description

An Expression Detector is a system that automatically detects and identifies facial expressions from a person's face using techniques from computer vision and machine learning. Its goal is to classify human emotions such as happy, sad, angry, surprised, neutral, etc., based on facial features.

### 🔑 Key Points of Expression Detector

#### 1. Face Detection

-- First, the system detects the face region in the image or video frame.

-- OpenCV is used .

#### 2. Feature Extraction

-- Facial landmarks (eyes, eyebrows, mouth, nose, etc.) are extracted.

--  MediaPipe and deep learning models (like CNNs) is used.

#### 3. Emotion Classification

-- Once features are extracted, the model classifies the expression.

-- Deep learning models (e.g. custom CNNs) is used.

-- Typical emotions: Happy, Sad, Angry, Fear, Disgust, Surprise, Neutral.

#### 4. Real-time Analysis 

-- Webcam or camera feed is used to analyze and predict expressions in real-time.

-- Useful for interactive systems or monitoring applications.

#### 5. Output

-- Displays the detected emotion label predicted by the Model .

### Sample Output :





## Before you run 

### Step 1: install python@3.10 or 3.11

### Step 2:  create a virtual environment 

1. for mac :

        python3.10 -m venv myenv

        source myenv/bin/activate

2. for windows : 

        python -m venv myenv

        myenv\Scripts\activate

### Step 3: Configure VS Code to Use Python 3.10

If you're using VS Code, follow these steps:

1. Press Ctrl+Shift+P → Type "Python: Select Interpreter".

   

2. Select Python 3.10 or the virtual environment myenv/bin/python.

   

3. Restart VS Code to apply changes.

### Step 4 : install dependencies 

        pip install mediapipe numpy tensorflow keras opencv-python