Scribd
Upload
3 views

app.py

Uploaded by

mi539919
Copyright
© © All Rights Reserved
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
3 views

app.py

Uploaded by

mi539919
Copyright
© © All Rights Reserved
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

import streamlit as st

import cv2
from keras.models import model_from_json
import numpy as np
import tensorflow as tf
from PIL import Image

# Load the model


json_file = open("facialemotionmodel.json", "r")
model_json = json_file.read()
json_file.close()
model = model_from_json(model_json)
model.load_weights("facialemotionmodel.h5")

# Load the Haar Cascade for face detection


haar_file = cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'
face_cascade = cv2.CascadeClassifier(haar_file)

# Emotion labels
labels = {0: 'angry', 1: 'disgust', 2: 'fear', 3: 'happy', 4: 'neutral', 5: 'sad',
6: 'surprise'}

# Function to extract features from the image


def extract_features(image):
feature = np.array(image)
feature = feature.reshape(1, 48, 48, 1)
return feature / 255.0

# Function to process the webcam feed and make predictions


def process_frame(frame):
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(frame, 1.3, 5)

for (p, q, r, s) in faces:


image = gray[q:q + s, p:p + r]
image = cv2.resize(image, (48, 48))
img = extract_features(image)
pred = model.predict(img)
prediction_label = labels[pred.argmax()]

# Draw rectangle and put text on the face


cv2.rectangle(frame, (p, q), (p + r, q + s), (255, 0, 0), 2)
cv2.putText(frame, '% s' % (prediction_label), (p - 10, q - 10),
cv2.FONT_HERSHEY_COMPLEX_SMALL, 2, (0, 0, 255))

return frame

# Streamlit UI elements
st.title("Facial Emotion Recognition")
st.write("Webcam live feed with emotion prediction.")

# Displaying video from webcam


video_stream = st.camera_input("Take a snapshot", key="webcam",
use_column_width=True)

if video_stream:
# Get image from the Streamlit camera input
frame = video_stream.getvalue()
np_frame = np.frombuffer(frame, dtype=np.uint8)
frame = cv2.imdecode(np_frame, 1)

# Process the frame to predict emotion


output_frame = process_frame(frame)

# Convert processed frame to RGB for Streamlit display


output_frame = cv2.cvtColor(output_frame, cv2.COLOR_BGR2RGB)
st.image(output_frame, channels="RGB", use_column_width=True)

You might also like