Upload 5 files

X.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb7df34faf4afc36da1e0452e949f0b5639cf308692054f6abec2782b7b4448
+size 47232

Y.npy

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb3aee1dadae6a8f2c1e812cecd917e099d358fc57914b522fda60872cd67f1
+size 1232

app.py

@@ -0,0 +1,42 @@
+from flask import Flask, render_template, request, send_file
+# Import your attendance model and processing functions
+from run import predict_and_show
+
+app = Flask("Ogs")
+
+
+@app.route('/')
+def index():
+    return render_template('index.html')
+
+
+@app.route('/upload', methods=['POST'])
+def upload():
+    if 'file' not in request.files:
+        return "No file part"
+
+    file = request.files['file']
+
+    if file.filename == '':
+        return "No selected file"
+
+    file.save("image.jpeg")
+    # # Access file properties
+    # filename = file.filename
+    # content_type = file.content_type
+    # file_size = len(file.read())
+
+    # # Reset file cursor to the beginning after reading it
+    # file.seek(0)
+
+    # # Read the content of the uploaded image
+    # image_content = file.read()
+
+    # Process the image using your attendance model
+    predict_and_show("image.jpeg")
+
+    return send_file("attendance.csv", as_attachment=True)
+
+
+if __name__ == '__main__':
+    app.run(debug=True)

run.py

@@ -0,0 +1,48 @@
+import os
+import face_recognition
+import numpy as np
+from PIL import Image, ImageDraw
+import pandas as pd
+
+
+def predict_and_show(image_path):
+    X = np.load("X.npy")
+    Y = np.load("Y.npy")
+
+    attendance = []
+    image = face_recognition.load_image_file(image_path)
+    face_bounding_boxes = face_recognition.face_locations(image)
+    if len(face_bounding_boxes) == 0:
+        print("No face found in the image")
+        return
+    X_test = face_recognition.face_encodings(image, known_face_locations=face_bounding_boxes)
+    for i in range(len(X_test)):
+        distances = np.linalg.norm(np.array(X) - np.array(X_test[i]), axis=1)
+        min_distance = np.min(distances)
+        if min_distance > 0.55:
+            print("Unknown")
+        else:
+            print(Y[np.argmin(distances)], min_distance)
+            attendance.append(Y[np.argmin(distances)])
+            top, right, bottom, left = face_bounding_boxes[i]
+            face_image = image[top:bottom, left:right]
+            pil_image = Image.fromarray(face_image)
+            draw = ImageDraw.Draw(pil_image)
+            draw.text((0, 0), Y[np.argmin(distances)], (255, 255, 255))
+            #pil_image.show()
+
+    x = pd.DataFrame(attendance, columns=["Name"])
+    x.to_csv("attendance.csv", index=False)
+    return True
+
+# predict_and_show()
+
+# #ask for input string from user
+# print("Enter the name of the image file")
+# image_path = input()
+
+# predict_and_show(image_path)
+# #save the attendance list to a txt file
+# with open("attendance.txt", "w") as file:
+#     for i in attendance:
+#         file.write(i + "\n")