requirements.txt

import cv2
import numpy as np
import tensorflow as tf
import gradio as gr

# Load trained model
model = tf.keras.models.load_model('emotion_detection_model.h5')

# Load Haar Cascade
face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

# Emotion labels
class_names = ['Angry', 'Disgust', 'Fear', 'Happy', 'Sad', 'Surprise', 'Neutral']

# Function to detect emotion
def detect_emotion_frame(frame):
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(
        gray, scaleFactor=1.1, minNeighbors=5, minSize=(60, 60)
    )

    for (x, y, w, h) in faces:
        roi_gray = gray[y:y + h, x:x + w]
        resized = cv2.resize(roi_gray, (48, 48))
        normalized = resized / 255.0
        reshaped = np.reshape(normalized, (1, 48, 48, 1))
        prediction = model.predict(reshaped)
        max_index = int(np.argmax(prediction))
        emotion = class_names[max_index]

        # Draw box and emotion
        cv2.rectangle(frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
        cv2.putText(
            frame, emotion, (x, y - 10),
            cv2.FONT_HERSHEY_SIMPLEX, 0.9, (255, 0, 0), 2
        )
    return frame

# Gradio interface
demo = gr.Interface(
    fn=detect_emotion_frame,
    inputs=gr.Image(source="webcam", streaming=True),
    outputs=gr.Image(),
    live=True,
    title="Live Emotion Detection",
    description="Real-time face emotion detection using deep learning."
)

if __name__ == "__main__":
    demo.launch()