Merge pull request #1 from Sookeyy-12/main

updated best

.gitignore

@@ -0,0 +1,4 @@
+dlib
+venv
+Faces/*
+windows

AntiSpoofing.py

@@ -0,0 +1,42 @@
+from ultralytics import YOLO
+import cv2
+import cvzone
+import math
+import time
+
+confidence = 0.9
+
+cap = cv2.VideoCapture(0) # for webcam
+cap.set(3, 640)
+cap.set(4, 480)
+# cap = cv2.VideoCapture("test.mp4") # for video file
+
+model = YOLO("models/best.pt")
+model.overrides['verbose'] = False
+
+classNames = ["fake", "real"]
+
+while True:
+    success, img = cap.read()
+    results = model(img, stream=True)
+    for r in results:
+        boxes = r.boxes
+        for box in boxes:
+            # Confidence
+            conf = math.ceil((box.conf[0] * 100))/100
+            # class name
+            if conf > confidence:
+                cls = int(box.cls[0])
+                if classNames[cls] == "real":
+                    print("Real")
+                else:
+                    print("Spoof")
+
+    cv2.imshow("Image", img)
+    key = cv2.waitKey(1) & 0xFF
+
+    # Exit if 'q' key is pressed
+    if key == ord("q"):
+        break
+
+cv2.destroyAllWindows()

FaceRecognition.py

@@ -0,0 +1,45 @@
+import cv2
+import os
+import pickle
+import face_recognition
+import numpy as np
+import cvzone
+
+cap = cv2.VideoCapture(0)
+cap.set(3, 640)  # Set width
+cap.set(4, 480)  # Set height
+
+# Load the Encoding File
+print("Loading encodings...")
+encodings = open("GeneratedEncodings.p", "rb")
+encodingListKnownWithIDs = pickle.load(encodings)
+encodings.close()
+encodeListKnown, studentIDs = encodingListKnownWithIDs
+print("Encodings loaded.")
+
+while True:
+    success, img = cap.read()
+
+    imgS = cv2.resize(img, (0, 0), None, 0.25, 0.25)
+    imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)    
+
+    faceCurrentFrame = face_recognition.face_locations(imgS)
+    encodeCurrentFrame = face_recognition.face_encodings(imgS,faceCurrentFrame)
+
+    for encodeFace, faceLocation in zip(encodeCurrentFrame, faceCurrentFrame):
+        matches = face_recognition.compare_faces(encodeListKnown, encodeFace)
+        faceDistance = face_recognition.face_distance(encodeListKnown, encodeFace)
+        matchIndex = np.argmin(faceDistance)
+        if matches[matchIndex]:
+            print("Known Face Detected")
+            print(studentIDs[matchIndex])
+
+
+    cv2.imshow("Face Attendance", img)
+
+    # Wait for a key press to break the loop
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()

README.md

@@ -1 +1,21 @@
-# DoorAutoCompiled
+# Should be the Correct One
+
+## How to Run:
+
+Note: if you windows, you will first need to build `dlib` using wheel.
+
+1. create a virtual environment 
+    ```bash
+    python -m venv venv
+    ```
+
+2. install requirements
+    ```bash
+    pip install -r reqs.txt
+    ```
+    This 100% works on windows, but might need calibration in linux.
+
+3. run the app
+    ```bash
+    python main.py
+    ```

encodeGenerator.py

@@ -0,0 +1,34 @@
+import cv2
+import face_recognition
+import pickle
+import os
+
+### Importing the Faces
+folderPath = "Faces"
+pathList = os.listdir(folderPath)
+imgList = []
+studentIDs = []
+for path in pathList:
+    imgList.append(cv2.imread(os.path.join(folderPath, path)))
+    studentIDs.append(os.path.splitext(path)[0])
+
+### Encodings Generator ###
+def findEncodings(imagesList):
+    encodeList  = []
+    for img in imagesList:
+        img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
+        encode = face_recognition.face_encodings(img)[0]
+        encodeList.append(encode)
+
+    return encodeList
+
+print("Encoding Started...")
+encodeListKnown = findEncodings(imgList)
+encodingListKnownWithIDs = (encodeListKnown, studentIDs)
+print("Encoding Complete.")
+
+file = open("GeneratedEncodings.p", "wb")
+pickle.dump(encodingListKnownWithIDs, file)
+file.close()
+
+print("Encodings Saved.")

main.py

@@ -0,0 +1,70 @@
+import cv2
+import pickle
+import face_recognition
+import numpy as np
+import math
+from ultralytics import YOLO
+
+# Initialize video capture
+cap = cv2.VideoCapture(0)
+cap.set(3, 640)  # Set width
+cap.set(4, 480)  # Set height
+
+# Load the Encoding File
+print("Loading encodings...")
+encodings = open("GeneratedEncodings.p", "rb")
+encodingListKnownWithIDs = pickle.load(encodings)
+encodings.close()
+encodeListKnown, studentIDs = encodingListKnownWithIDs
+print("Encodings loaded.")
+
+# Load the anti-spoofing model
+model = YOLO("models/best.pt")
+model.overrides['verbose'] = False
+classNames = ["fake", "real"]
+confidence = 0.9
+
+while True:
+    success, img = cap.read()
+
+    # Anti-spoofing check
+    results = model(img, stream=True)
+    is_real = False
+    for r in results:
+        boxes = r.boxes
+        for box in boxes:
+            conf = math.ceil((box.conf[0] * 100))/100
+            if conf > confidence:
+                cls = int(box.cls[0])
+                if classNames[cls] == "real":
+                    is_real = True
+                    break
+        if is_real:
+            break
+
+    if is_real:
+        # Face recognition
+        imgS = cv2.resize(img, (0, 0), None, 0.25, 0.25)
+        imgS = cv2.cvtColor(imgS, cv2.COLOR_BGR2RGB)    
+
+        faceCurrentFrame = face_recognition.face_locations(imgS)
+        encodeCurrentFrame = face_recognition.face_encodings(imgS, faceCurrentFrame)
+
+        for encodeFace, faceLocation in zip(encodeCurrentFrame, faceCurrentFrame):
+            matches = face_recognition.compare_faces(encodeListKnown, encodeFace)
+            faceDistance = face_recognition.face_distance(encodeListKnown, encodeFace)
+            matchIndex = np.argmin(faceDistance)
+            if matches[matchIndex]:
+                print("Known Face Detected")
+                print(studentIDs[matchIndex])
+    else:
+        print("Spoofing Attempt Detected")
+
+    cv2.imshow("Face Attendance", img)
+
+    # Wait for a key press to break the loop
+    if cv2.waitKey(1) & 0xFF == ord('q'):
+        break
+
+cap.release()
+cv2.destroyAllWindows()