Update app.py

app.py

@@ -1,45 +1,30 @@
 import streamlit as st
-# from transformers import pipeline
 from PIL import Image
 import face_recognition
 import cv2
 import numpy as np
-import requests
 import os
 
-st.title("AIMLJan24 - Face Recognition")
-
-# create list of encoding of all images in photos folder
-# Load images for face recognition
-Images = []   # List to store Images
-classnames = []  # List to store classnames
-directory = "photos"
-myList = os.listdir(directory)
-
-st.write("Photographs found in folder : ")
-for cls in myList:
-    if os.path.splitext(cls)[1] in [".jpg", ".jpeg"]:
-        img_path = os.path.join(directory, cls)
-        curImg = cv2.imread(img_path)
-        Images.append(curImg)
-        st.write(os.path.splitext(cls)[0])
-        classnames.append(os.path.splitext(cls)[0])
+def load_images(directory):
+    images = []
+    classnames = []
+    file_list = os.listdir(directory)
 
-# Load images for face recognition
-encodeListknown = [face_recognition.face_encodings(img)[0] for img in Images]
-
-# camera to take photo of user in question
-file_name = st.camera_input("Take a picture")  #st.file_uploader("Upload image  ")
-
-if file_name is not None:
-    col1, col2 = st.columns(2)
+    st.write("Photographs found in folder : ")
+    for file in file_list:
+        if os.path.splitext(file)[1] in [".jpg", ".jpeg"]:
+            img_path = os.path.join(directory, file)
+            cur_img = cv2.imread(img_path)
+            images.append(cur_img)
+            st.write(os.path.splitext(file)[0])
+            classnames.append(os.path.splitext(file)[0])
 
-    test_image = Image.open(file_name)
-    image = np.asarray(test_image)
+    return images, classnames
 
-    imgS = cv2.resize(image, (0, 0), None, 0.25, 0.25)
+def recognize_faces(test_image, known_encodings, class_names):
+    imgS = cv2.resize(test_image, (0, 0), None, 0.25, 0.25)
     imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)
-    facesCurFrame   = face_recognition.face_locations(imgS)
+    facesCurFrame = face_recognition.face_locations(imgS)
     encodesCurFrame = face_recognition.face_encodings(imgS, facesCurFrame)
 
     name = "Unknown"  # Default name for unknown faces
@@ -48,48 +33,36 @@ if file_name is not None:
     # Checking if faces are detected
     if len(encodesCurFrame) > 0:
         for encodeFace, faceLoc in zip(encodesCurFrame, facesCurFrame):
-            # Assuming that encodeListknown is defined and populated in your code
-            matches = face_recognition.compare_faces(encodeListknown, encodeFace)
-            faceDis = face_recognition.face_distance(encodeListknown, encodeFace)
+            matches = face_recognition.compare_faces(known_encodings, encodeFace)
+            faceDis = face_recognition.face_distance(known_encodings, encodeFace)
             matchIndex = np.argmin(faceDis)
 
             if matches[matchIndex]:
-                name = classnames[matchIndex].upper()
+                name = class_names[matchIndex].upper()
                 match_found = True  # Set the flag to True
                 
             y1, x2, y2, x1 = faceLoc
             y1, x2, y2, x1 = (y1 * 4), (x2 * 4), (y2 * 4) ,(x1 * 4)
-            cv2.rectangle(test_image , (x1, y1), (x2, y2), (0, 255, 0), 2)
-            cv2.rectangle(test_image , (x1, y2 - 35), (x2, y2), (0, 255, 0), cv2.FILLED)
-            cv2.putText(test_image , name, (x1 + 6, y2 - 6), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 255), 2)
+            cv2.rectangle(test_image, (x1, y1), (x2, y2), (0, 255, 0), 2)
+            cv2.rectangle(test_image, (x1, y2 - 35), (x2, y2), (0, 255, 0), cv2.FILLED)
+            cv2.putText(test_image, name, (x1 + 6, y2 - 6), cv2.FONT_HERSHEY_COMPLEX, 1, (255, 255, 255), 2)
             
-            st.image(test_image , use_column_width=True, output_format="PNG")
-    else:
-            st.warning("No faces detected in the image. Face recognition failed.")
+    return test_image
 
-    # image = Image.open(file_name)
-    # col1.image(image, use_column_width=True)
-
-# pipeline = pipeline(task="image-classification", model="julien-c/hotdog-not-hotdog")
-
-# st.title("AIMLJan24 First App on Hugging face - Hot Dog? Or Not?")
-
-# file_name = st.file_uploader("Upload the test image to find is this hot dog ! ")
-
-# if file_name is not None:
-#     col1, col2 = st.columns(2)
+st.title("AIMLJan24 - Face Recognition")
 
-#     image = Image.open(file_name)
-#     col1.image(image, use_column_width=True)
-#     predictions = pipeline(image)
+# Load images for face recognition
+directory = "photos"
+Images, classnames = load_images(directory)
 
-#     col2.header("Probabilities")
-#     for p in predictions:
-#         col2.subheader(f"{ p['label'] }: { round(p['score'] * 100, 1)}%")
+# Load images for face recognition
+encodeListknown = [face_recognition.face_encodings(img)[0] for img in Images]
 
+# camera to take photo of user in question
+file_name = st.file_uploader("Upload image")
 
-# # my first app
-# import streamlit as st
+if file_name is not None:
+    test_image = np.array(Image.open(file_name))
+    image_with_recognition = recognize_faces(test_image, encodeListknown, classnames)
+    st.image(image_with_recognition, use_column_width=True, output_format="PNG")
 
-# x = st.slider('Select a value')
-# st.write(x, 'squared is', x * x)