Real-time Emotion Recognition with OpenCV in Python | Techniculus

Emotion recognition is the process of identifying and classifying emotions based on facial expressions. With the help of OpenCV and Python, we can easily build an application that can recognize emotions in real-time.

OpenCV is an open-source computer vision library that provides a wide range of tools for image and video processing. It is widely used for various applications such as object detection, face recognition, and tracking.

To create a real-time emotion recognition system using OpenCV, we need to follow the following steps:

1. Install OpenCV: To install OpenCV, we can use the pip command in the terminal.

pip install opencv-python

2. Collecting the dataset: We need a dataset that contains images of different emotions. The FER2013 dataset is a popular dataset for emotion recognition, containing facial images of different emotions. It can be downloaded from https://www.kaggle.com/c/challenges-in-representation-learning-facial-expression-recognition-challenge/data

3. Train the model: We can train our emotion recognition model using deep learning techniques. We can use pre-trained models like VGG16 or ResNet and fine-tune them for our dataset.

4. Detecting emotions: Once the model is trained, we can use OpenCV to detect emotions in real-time. We can use the Haar Cascade classifier to detect faces in the image and then pass the face region to our trained model to predict the emotion.

Here is the sample code to create a real-time emotion recognition system:

 

import cv2 import numpy as np from keras.models import load_model # Load the pre-trained model model = load_model('emotion_detection_model.h5') # Load the Haar Cascade classifier face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') # Define the emotion labels emotions = ['Angry', 'Disgust', 'Fear', 'Happy', 'Neutral', 'Sad', 'Surprise'] # Start the video capture cap = cv2.VideoCapture(0) while True: # Read the frames from the camera ret, frame = cap.read() # Convert the frame to grayscale gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # Detect faces using the Haar Cascade classifier faces = face_cascade.detectMultiScale(gray, scaleFactor=1.3, minNeighbors=5) # Loop over all the detected faces for (x, y, w, h) in faces: # Extract the face region roi_gray = gray[y:y + h, x:x + w] roi_gray = cv2.resize(roi_gray, (48, 48)) # Normalize the pixel values roi = roi_gray / 255.0 # Reshape the image roi = np.reshape(roi, (1, 48, 48, 1)) # Predict the emotion preds = model.predict(roi)[0] emotion_label = emotions[preds.argmax()] # Display the emotion label on the screen cv2.putText(frame, emotion_label, (x, y - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.9, (0, 255, 0), 2) # Draw a rectangle around the face cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2) # Display the output cv2.imshow('Emotion Detection', frame) # Exit on 'q' key press if cv2.waitKey(1) & 0xFF == ord('q'): break # Release the video capture cap.release() cv2.destroyAllWindows()

 

The cap.release() function is used to release the video capture and free up system resources. The cv2.destroyAllWindows() function is used to destroy all the windows created by OpenCV.

In conclusion, OpenCV and Python make it easy to build a real-time emotion recognition system. By following the above steps, one can build an emotion recognition system that can detect emotions in real-time. The code provided can be used as a starting point for building more complex emotion recognition systems.