File size: 4,034 Bytes
6781da9 56a64f9 6781da9 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 |
import threading
import streamlit as st
import cv2
import numpy as np
from transformers import pipeline
from PIL import Image, ImageDraw
from mtcnn import MTCNN
from streamlit_webrtc import webrtc_streamer
import logging
# Suppress transformers progress bars
logging.getLogger("transformers").setLevel(logging.ERROR)
lock = threading.Lock()
img_container = {"webcam": None,
"analyzed": None}
# 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
# 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()
def video_frame_callback(frame):
try:
with lock:
img = frame.to_ndarray(format="bgr24")
img_container["webcam"] = img
frame_with_boxes = detect_and_draw_faces(img)
img_container["analyzed"] = frame_with_boxes
except Exception as e:
st.error(f"Error processing frame: {e}")
return frame
ctx = webrtc_streamer(key="webcam", video_frame_callback=video_frame_callback)
while ctx.state.playing:
with lock:
print(img_container)
img = img_container["webcam"]
frame_with_boxes = img_container["analyzed"]
if img is None:
continue
video_placeholder.image(img, channels="BGR")
output_placeholder.image(frame_with_boxes, channels="BGR")
|