app.py

import os
# os.environ['OPENCV_AVFOUNDATION_SKIP_AUTH'] = '1'

import streamlit as st
import cv2
import numpy as np
from transformers import pipeline
from PIL import Image, ImageDraw
from mtcnn import MTCNN

# Initialize the Hugging Face pipeline for facial emotion detection
emotion_pipeline = pipeline("image-classification", model="trpakov/vit-face-expression")

# Initialize MTCNN for face detection
mtcnn = MTCNN()

# Function to analyze sentiment
def analyze_sentiment(face):
    # Convert face to RGB
    rgb_face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
    # Convert the face to a PIL image
    pil_image = Image.fromarray(rgb_face)
    # Analyze sentiment using the Hugging Face pipeline
    results = emotion_pipeline(pil_image)
    # Get the dominant emotion
    dominant_emotion = max(results, key=lambda x: x['score'])['label']
    return dominant_emotion

TEXT_SIZE = 3

# Function to detect faces, analyze sentiment, and draw a red box around them
def detect_and_draw_faces(frame):
    # Detect faces using MTCNN
    results = mtcnn.detect_faces(frame)
    
    # Draw on the frame
    for result in results:
        x, y, w, h = result['box']
        face = frame[y:y+h, x:x+w]
        sentiment = analyze_sentiment(face)
        cv2.rectangle(frame, (x, y), (x+w, y+h), (0, 0, 255), 10)  # Thicker red box
        
        # Calculate position for the text background and the text itself
        text_size = cv2.getTextSize(sentiment, cv2.FONT_HERSHEY_SIMPLEX, TEXT_SIZE, 2)[0]
        text_x = x
        text_y = y - 10
        background_tl = (text_x, text_y - text_size[1])
        background_br = (text_x + text_size[0], text_y + 5)
        
        # Draw black rectangle as background
        cv2.rectangle(frame, background_tl, background_br, (0, 0, 0), cv2.FILLED)
        # Draw white text on top
        cv2.putText(frame, sentiment, (text_x, text_y), cv2.FONT_HERSHEY_SIMPLEX, TEXT_SIZE, (255, 255, 255), 2)
    
    return frame

# Function to capture video from webcam
def video_stream():
    video_capture = cv2.VideoCapture(0)
    if not video_capture.isOpened():
        st.error("Error: Could not open video capture device.")
        return

    while True:
        ret, frame = video_capture.read()
        if not ret:
            st.error("Error: Failed to read frame from video capture device.")
            break
        yield frame

    video_capture.release()

# Streamlit UI
st.markdown(
    """
    <style>
        .main {
            background-color: #FFFFFF;
        }
        .reportview-container .main .block-container{
            padding-top: 2rem;
        }
        h1 {
            color: #E60012;
            font-family: 'Arial Black', Gadget, sans-serif;
        }
        h2 {
            color: #E60012;
            font-family: 'Arial', sans-serif;
        }
        h3 {
            color: #333333;
            font-family: 'Arial', sans-serif;
        }
        .stButton button {
            background-color: #E60012;
            color: white;
            border-radius: 5px;
            font-size: 16px;
        }
    </style>
    """,
    unsafe_allow_html=True
)

st.title("Computer Vision Test Lab")
st.subheader("Facial Sentiment")

# Columns for input and output streams
col1, col2 = st.columns(2)

with col1:
    st.header("Input Stream")
    st.subheader("Webcam")
    video_placeholder = st.empty()

with col2:
    st.header("Output Stream")
    st.subheader("Analysis")
    output_placeholder = st.empty()

sentiment_placeholder = st.empty()

# Start video stream
video_capture = cv2.VideoCapture(0)
if not video_capture.isOpened():
    st.error("Error: Could not open video capture device.")
else:
    while True:
        ret, frame = video_capture.read()
        if not ret:
            st.error("Error: Failed to read frame from video capture device.")
            break

        # Display the input stream with the red box around the face
        video_placeholder.image(frame, channels="BGR")
        
        # Detect faces, analyze sentiment, and draw red boxes with sentiment labels
        frame_with_boxes = detect_and_draw_faces(frame)
        
        # Display the output stream (here it's the same as input, modify as needed)
        output_placeholder.image(frame_with_boxes, channels="BGR")
        
        # Add a short delay to control the frame rate
        if cv2.waitKey(1) & 0xFF == ord('q'):
            break