First Commit

.gitignore

@@ -0,0 +1,42 @@
+# Ignore files generated by the IDE
+.idea/
+.vscode/
+/src/api/.env
+# Ignore compiled binaries and libraries
+*.exe
+*.dll
+*.so
+*.dylib
+
+# Ignore build output directories
+/bin/
+/build/
+/dist/
+# Ignore build output directories
+/bin/*
+/build/*
+/dist/*
+/pycache/*
+# Ignore package manager directories
+/node_modules/
+/vendor/
+
+# Ignore log files
+*.log
+*.env
+# Ignore temporary files
+*.tmp
+*.swp
+*.bak
+
+# Ignore system files
+.DS_Store
+Thumbs.db
+
+# Ignore sensitive or personal information
+config.ini
+secrets.txt
+
+# Ignore specific files or directories
+/path/to/file.txt
+/path/to/directory/

DockerFile

@@ -0,0 +1,24 @@
+# Use an official Python runtime as a parent image
+FROM python:3.8
+
+# Set the working directory in the container to /app
+WORKDIR /app
+
+# Add the current directory contents into the container at /app
+ADD . /app
+
+# Install Poetry
+RUN pip install poetry
+
+# Install project dependencies
+RUN poetry config virtualenvs.create false \
+  && poetry install --no-interaction --no-ansi
+
+# Make port 5000 available to the world outside this container
+EXPOSE 5000
+
+# # Run the command to start uWSGI
+# CMD ["uwsgi", "app.ini"]
+
+# # Run the GUI application
+# CMD ["python", "gui.py"]

README.md

@@ -1,2 +1,42 @@
-# Real-Time-Face-Recognition-System
-An End-to-End Real-Time Face recognition built using FaceNet Model Deployed with Streamlit UI and Flask API
+ # Real-Time-Face-Recognition
+This repository is dedicated to the Project "End-to-End real-time face recognition system" 
+
+## Usage
+
+### Install Dependencies
+* Clone the Project Repository to your system
+```bash
+git clone <GITHUB_REPO_URL>
+```
+* Go to the Project Directory and Create a Virtual Environment in Python
+
+```bash
+python -m venv face-recognition-system
+source face-recognition-system/bin/activate
+
+```
+
+```py
+pip install requirements.txt
+```
+
+### Start the Flask API Server
+
+* Navigate to src/api Folder
+```bash
+python endpoints.py
+```
+**Note:** This will start your Flask API at : **http://localhost:5000/**  
+The API has two endpoints (you can test the API using POSTMAN)
+>* **http://localhost:5000/api/register**(for User FaceID registration)
+>* **http://localhost:5000/api/recognize** (for recognizing user given face image)
+
+### Start the Interactive UI(Streamlit)
+* After Starting the API, We can use the Face Recognition system interactively through streamlit application
+
+* Run the command
+```bash
+streamlit run streamlit_app.py
+```
+
+* Streamlit UI will start at : **http://localhost:8501**

__init__.py

@@ -0,0 +1,11 @@
+# Import necessary modules or packages here
+
+# Define any global variables or constants here
+
+# Define any helper functions or classes here
+
+# Define the main entry point of your module here
+
+if __name__ == "__main__":
+    # Code to be executed when the module is run as a standalone script
+    pass

requirements.txt

@@ -0,0 +1,88 @@
+absl-py==2.1.0
+aioice==0.9.0
+aiortc==1.8.0
+altair==5.3.0
+astunparse==1.6.3
+attrs==23.2.0
+av==11.0.0
+blinker==1.8.2
+cachetools==5.3.3
+certifi==2024.2.2
+cffi==1.16.0
+charset-normalizer==3.3.2
+click==8.1.7
+coloredlogs==15.0.1
+cryptography==42.0.7
+dnspython==2.6.1
+Flask==3.0.3
+flatbuffers==24.3.25
+gast==0.5.4
+gitdb==4.0.11
+GitPython==3.1.43
+google-crc32c==1.5.0
+google-pasta==0.2.0
+grpcio==1.63.0
+h5py==3.11.0
+humanfriendly==10.0
+idna==3.7
+ifaddr==0.2.0
+itsdangerous==2.2.0
+Jinja2==3.1.4
+joblib==1.4.2
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+keras==3.3.3
+libclang==18.1.1
+Markdown==3.6
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+ml-dtypes==0.3.2
+mpmath==1.3.0
+mysql-connector-python==8.4.0
+namex==0.0.8
+numpy==1.26.4
+onnxruntime==1.17.3
+opencv-python==4.9.0.80
+opt-einsum==3.3.0
+optree==0.11.0
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+protobuf==4.25.3
+pyarrow==16.0.0
+pycparser==2.22
+pydeck==0.9.1
+pyee==11.1.0
+Pygments==2.18.0
+pylibsrtp==0.10.0
+pyOpenSSL==24.1.0
+python-dateutil==2.9.0.post0
+pytz==2024.1
+referencing==0.35.1
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.1
+scikit-learn==1.4.2
+scipy==1.13.0
+six==1.16.0
+smmap==5.0.1
+streamlit==1.34.0
+streamlit-webrtc==0.47.6
+sympy==1.12
+tenacity==8.3.0
+tensorboard==2.16.2
+tensorboard-data-server==0.7.2
+tensorflow==2.16.1
+termcolor==2.4.0
+threadpoolctl==3.5.0
+toml==0.10.2
+toolz==0.12.1
+tornado==6.4
+typing_extensions==4.11.0
+tzdata==2024.1
+urllib3==2.2.1
+watchdog==4.0.0
+Werkzeug==3.0.3
+wrapt==1.16.0
+python-dotenv==1.0.1

src/api/face_recognition_model.py

@@ -0,0 +1,42 @@
+import cv2
+import tensorflow as tf
+import numpy as np
+from preprocessing import Preprocessor
+
+
+class FaceRecognizer():
+    def __init__(self, model_path):
+        self.interpreter = tf.lite.Interpreter(model_path=model_path)
+        self.interpreter.allocate_tensors()
+
+    def preprocess_image(self, img):
+        img = cv2.resize(img, (160, 160))  # Resize image to the size expected by the FaceNet model
+        img = img.astype('float32') / 255  # Normalize pixel values to [0, 1]
+        img = np.expand_dims(img, axis=0)  # Add batch dimension
+        return img
+
+    def get_embedding(self, img):
+        img = self.preprocess_image(img)
+        input_details = self.interpreter.get_input_details()
+        output_details = self.interpreter.get_output_details()
+        self.interpreter.set_tensor(input_details[0]['index'], img)
+        self.interpreter.invoke()
+        return self.interpreter.get_tensor(output_details[0]['index'])
+
+
+
+from tensorflow.keras.models import load_model
+
+class FaceRecognizerH5():
+    def __init__(self, model_path):
+        self.model = load_model(model_path)
+
+    def preprocess_image(self, img):
+        img = cv2.resize(img, (160, 160))  # Resize image to the size expected by the FaceNet model
+        img = img.astype('float32') / 255  # Normalize pixel values to [0, 1]
+        img = np.expand_dims(img, axis=0)  # Add batch dimension
+        return img
+
+    def get_embedding(self, img):
+        img = self.preprocess_image(img)
+        return self.model.predict(img)

src/api/preprocessing.py

@@ -0,0 +1,63 @@
+import cv2
+import numpy as np
+import tensorflow as tf
+import sklearn.preprocessing
+import tensorflow as tf
+import numpy as np
+import numpy as np
+from scipy import ndimage
+from scipy.spatial import distance
+
+
+class Preprocessor():
+    def __init__(self, transforms, width, height, channels):
+        super().__init__()
+        self.transforms = transforms
+        self.width = width
+        self.height = height
+        self.channels = channels
+        self.face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')
+        self.eye_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_eye.xml')  
+
+
+    def face_detect(self, image):
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+        faces = self.face_cascade.detectMultiScale(gray, 1.3, 5)
+        for (x,y,w,h) in faces:
+            image = image[y:y+h, x:x+w]
+        return image
+
+    def face_align(self, image):
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        faces = self.face_cascade.detectMultiScale(gray, 1.3, 5)
+
+        for (x, y, w, h) in faces:
+            eyes = self.eye_cascade.detectMultiScale(gray[y:y+h, x:x+w])
+            if len(eyes) >= 2:
+                # Find the largest two eye regions
+                eyes = sorted(eyes, key=lambda x: -x[2])[:2]
+                # Sort the eye regions such that left_eye[0] <= right_eye[0]
+                eyes = sorted(eyes, key=lambda x: x[0])
+                left_eye, right_eye = eyes
+                # Calculate the angle between the two eyes
+                dy = right_eye[1] - left_eye[1]
+                dx = right_eye[0] - left_eye[0]
+                angle = np.degrees(np.arctan2(dy, dx))
+                # Rotate the image to align the eyes horizontally
+                M = cv2.getRotationMatrix2D(((left_eye[0] + right_eye[0]) // 2, (left_eye[1] + right_eye[1]) // 2), angle, 1)
+                image = cv2.warpAffine(image, M, (self.width, self.height))
+        return image
+
+    def crop_face_image(self, image):
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+        faces = self.face_cascade.detectMultiScale(gray, 1.3, 5)
+        for (x, y, w, h) in faces:
+            image = image[y:y+h, x:x+w]
+        return image
+
+    def scale_face_image(self, image):
+        return cv2.resize(image, (self.width, self.height))
+
+    def normalize_color(self, image):
+        return image / 255.0

src/models/weights/__init__.py

@@ -0,0 +1 @@
+from . import face_recognition_model