{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "u1Pj_BMa6U0B"
      },
      "source": [
        "# Facial Verification - ITI110 python code with chromadb\n",
        "\n",
        "---\n",
        "\n",
        "\n",
        "\n",
        "The code is referenced and adapted from ITI108-Face verification and face recogniton lab. Only relevant code was retained and integrated to work with chromaDb.\n",
        "\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6u37N7Ie7WCa"
      },
      "source": [
        "## Section 1 - Installing Necessary Libraries\n",
        "\n",
        "Run the following cell below to install the latest MTCNN library.\n",
        "\n",
        "The MTCNN library is a Python library that uses the Multi-Task Cascading Convolutional Neural Networks used to detect faces in an image. The Keras implementation can be found here with pre-trained weights can be found here: https://github.com/ipazc/mtcnn"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2iLzJaOirxl0",
        "outputId": "72bc94c3-63f8-495d-c6e9-276ffff23424"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: mtcnn in /usr/local/lib/python3.10/dist-packages (0.1.1)\n",
            "Requirement already satisfied: keras>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from mtcnn) (2.15.0)\n",
            "Requirement already satisfied: opencv-python>=4.1.0 in /usr/local/lib/python3.10/dist-packages (from mtcnn) (4.8.0.76)\n",
            "Requirement already satisfied: numpy>=1.21.2 in /usr/local/lib/python3.10/dist-packages (from opencv-python>=4.1.0->mtcnn) (1.23.5)\n"
          ]
        }
      ],
      "source": [
        "!pip install mtcnn"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "It is an ease to use Chroma DB is a vector db to store facenet embeddings of cropped faces. By default it uses Squared L2 for distance calculation and has option to use, inner product, or cosine similarity."
      ],
      "metadata": {
        "id": "JxA9Du9lxoMg"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install chromadb"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "TnkuyXzNJlpI",
        "outputId": "dce02ec0-88cb-4261-fe58-64523cba1d11"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: chromadb in /usr/local/lib/python3.10/dist-packages (0.4.22)\n",
            "Requirement already satisfied: build>=1.0.3 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.0.3)\n",
            "Requirement already satisfied: requests>=2.28 in /usr/local/lib/python3.10/dist-packages (from chromadb) (2.31.0)\n",
            "Requirement already satisfied: pydantic>=1.9 in /usr/local/lib/python3.10/dist-packages (from chromadb) (2.6.1)\n",
            "Requirement already satisfied: chroma-hnswlib==0.7.3 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.7.3)\n",
            "Requirement already satisfied: fastapi>=0.95.2 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.109.2)\n",
            "Requirement already satisfied: uvicorn[standard]>=0.18.3 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.27.0.post1)\n",
            "Requirement already satisfied: numpy>=1.22.5 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.23.5)\n",
            "Requirement already satisfied: posthog>=2.4.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (3.4.0)\n",
            "Requirement already satisfied: typing-extensions>=4.5.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (4.9.0)\n",
            "Requirement already satisfied: pulsar-client>=3.1.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (3.4.0)\n",
            "Requirement already satisfied: onnxruntime>=1.14.1 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.17.0)\n",
            "Requirement already satisfied: opentelemetry-api>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.22.0)\n",
            "Requirement already satisfied: opentelemetry-exporter-otlp-proto-grpc>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.22.0)\n",
            "Requirement already satisfied: opentelemetry-instrumentation-fastapi>=0.41b0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.43b0)\n",
            "Requirement already satisfied: opentelemetry-sdk>=1.2.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.22.0)\n",
            "Requirement already satisfied: tokenizers>=0.13.2 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.15.1)\n",
            "Requirement already satisfied: pypika>=0.48.9 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.48.9)\n",
            "Requirement already satisfied: tqdm>=4.65.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (4.66.1)\n",
            "Requirement already satisfied: overrides>=7.3.1 in /usr/local/lib/python3.10/dist-packages (from chromadb) (7.7.0)\n",
            "Requirement already satisfied: importlib-resources in /usr/local/lib/python3.10/dist-packages (from chromadb) (6.1.1)\n",
            "Requirement already satisfied: grpcio>=1.58.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (1.60.1)\n",
            "Requirement already satisfied: bcrypt>=4.0.1 in /usr/local/lib/python3.10/dist-packages (from chromadb) (4.1.2)\n",
            "Requirement already satisfied: typer>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (0.9.0)\n",
            "Requirement already satisfied: kubernetes>=28.1.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (29.0.0)\n",
            "Requirement already satisfied: tenacity>=8.2.3 in /usr/local/lib/python3.10/dist-packages (from chromadb) (8.2.3)\n",
            "Requirement already satisfied: PyYAML>=6.0.0 in /usr/local/lib/python3.10/dist-packages (from chromadb) (6.0.1)\n",
            "Requirement already satisfied: mmh3>=4.0.1 in /usr/local/lib/python3.10/dist-packages (from chromadb) (4.1.0)\n",
            "Requirement already satisfied: packaging>=19.0 in /usr/local/lib/python3.10/dist-packages (from build>=1.0.3->chromadb) (23.2)\n",
            "Requirement already satisfied: pyproject_hooks in /usr/local/lib/python3.10/dist-packages (from build>=1.0.3->chromadb) (1.0.0)\n",
            "Requirement already satisfied: tomli>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from build>=1.0.3->chromadb) (2.0.1)\n",
            "Requirement already satisfied: starlette<0.37.0,>=0.36.3 in /usr/local/lib/python3.10/dist-packages (from fastapi>=0.95.2->chromadb) (0.36.3)\n",
            "Requirement already satisfied: certifi>=14.05.14 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (2024.2.2)\n",
            "Requirement already satisfied: six>=1.9.0 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (1.16.0)\n",
            "Requirement already satisfied: python-dateutil>=2.5.3 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (2.8.2)\n",
            "Requirement already satisfied: google-auth>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (2.17.3)\n",
            "Requirement already satisfied: websocket-client!=0.40.0,!=0.41.*,!=0.42.*,>=0.32.0 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (1.7.0)\n",
            "Requirement already satisfied: requests-oauthlib in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (1.3.1)\n",
            "Requirement already satisfied: oauthlib>=3.2.2 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (3.2.2)\n",
            "Requirement already satisfied: urllib3>=1.24.2 in /usr/local/lib/python3.10/dist-packages (from kubernetes>=28.1.0->chromadb) (2.0.7)\n",
            "Requirement already satisfied: coloredlogs in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (15.0.1)\n",
            "Requirement already satisfied: flatbuffers in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (23.5.26)\n",
            "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (3.20.3)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from onnxruntime>=1.14.1->chromadb) (1.12)\n",
            "Requirement already satisfied: deprecated>=1.2.6 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-api>=1.2.0->chromadb) (1.2.14)\n",
            "Requirement already satisfied: importlib-metadata<7.0,>=6.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-api>=1.2.0->chromadb) (6.11.0)\n",
            "Requirement already satisfied: backoff<3.0.0,>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (2.2.1)\n",
            "Requirement already satisfied: googleapis-common-protos~=1.52 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.62.0)\n",
            "Requirement already satisfied: opentelemetry-exporter-otlp-proto-common==1.22.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.22.0)\n",
            "Requirement already satisfied: opentelemetry-proto==1.22.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-exporter-otlp-proto-grpc>=1.2.0->chromadb) (1.22.0)\n",
            "Requirement already satisfied: opentelemetry-instrumentation-asgi==0.43b0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.43b0)\n",
            "Requirement already satisfied: opentelemetry-instrumentation==0.43b0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.43b0)\n",
            "Requirement already satisfied: opentelemetry-semantic-conventions==0.43b0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.43b0)\n",
            "Requirement already satisfied: opentelemetry-util-http==0.43b0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (0.43b0)\n",
            "Requirement already satisfied: setuptools>=16.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation==0.43b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (67.7.2)\n",
            "Requirement already satisfied: wrapt<2.0.0,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation==0.43b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (1.14.1)\n",
            "Requirement already satisfied: asgiref~=3.0 in /usr/local/lib/python3.10/dist-packages (from opentelemetry-instrumentation-asgi==0.43b0->opentelemetry-instrumentation-fastapi>=0.41b0->chromadb) (3.7.2)\n",
            "Requirement already satisfied: monotonic>=1.5 in /usr/local/lib/python3.10/dist-packages (from posthog>=2.4.0->chromadb) (1.6)\n",
            "Requirement already satisfied: annotated-types>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.9->chromadb) (0.6.0)\n",
            "Requirement already satisfied: pydantic-core==2.16.2 in /usr/local/lib/python3.10/dist-packages (from pydantic>=1.9->chromadb) (2.16.2)\n",
            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.28->chromadb) (3.3.2)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.28->chromadb) (3.6)\n",
            "Requirement already satisfied: huggingface_hub<1.0,>=0.16.4 in /usr/local/lib/python3.10/dist-packages (from tokenizers>=0.13.2->chromadb) (0.20.3)\n",
            "Requirement already satisfied: click<9.0.0,>=7.1.1 in /usr/local/lib/python3.10/dist-packages (from typer>=0.9.0->chromadb) (8.1.7)\n",
            "Requirement already satisfied: h11>=0.8 in /usr/local/lib/python3.10/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.14.0)\n",
            "Requirement already satisfied: httptools>=0.5.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.6.1)\n",
            "Requirement already satisfied: python-dotenv>=0.13 in /usr/local/lib/python3.10/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (1.0.1)\n",
            "Requirement already satisfied: uvloop!=0.15.0,!=0.15.1,>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.19.0)\n",
            "Requirement already satisfied: watchfiles>=0.13 in /usr/local/lib/python3.10/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (0.21.0)\n",
            "Requirement already satisfied: websockets>=10.4 in /usr/local/lib/python3.10/dist-packages (from uvicorn[standard]>=0.18.3->chromadb) (12.0)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (5.3.2)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.3.0)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.10/dist-packages (from google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (4.9)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub<1.0,>=0.16.4->tokenizers>=0.13.2->chromadb) (3.13.1)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub<1.0,>=0.16.4->tokenizers>=0.13.2->chromadb) (2023.6.0)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib-metadata<7.0,>=6.0->opentelemetry-api>=1.2.0->chromadb) (3.17.0)\n",
            "Requirement already satisfied: anyio<5,>=3.4.0 in /usr/local/lib/python3.10/dist-packages (from starlette<0.37.0,>=0.36.3->fastapi>=0.95.2->chromadb) (3.7.1)\n",
            "Requirement already satisfied: humanfriendly>=9.1 in /usr/local/lib/python3.10/dist-packages (from coloredlogs->onnxruntime>=1.14.1->chromadb) (10.0)\n",
            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->onnxruntime>=1.14.1->chromadb) (1.3.0)\n",
            "Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.4.0->starlette<0.37.0,>=0.36.3->fastapi>=0.95.2->chromadb) (1.3.0)\n",
            "Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5,>=3.4.0->starlette<0.37.0,>=0.36.3->fastapi>=0.95.2->chromadb) (1.2.0)\n",
            "Requirement already satisfied: pyasn1<0.6.0,>=0.4.6 in /usr/local/lib/python3.10/dist-packages (from pyasn1-modules>=0.2.1->google-auth>=1.0.1->kubernetes>=28.1.0->chromadb) (0.5.1)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "JLAnrEBeNTcF",
        "outputId": "3068fd87-279c-40d0-ce3c-30d8b80a1c62"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: keras-facenet in /usr/local/lib/python3.10/dist-packages (0.3.2)\n",
            "Requirement already satisfied: mtcnn in /usr/local/lib/python3.10/dist-packages (from keras-facenet) (0.1.1)\n",
            "Requirement already satisfied: keras>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from mtcnn->keras-facenet) (2.15.0)\n",
            "Requirement already satisfied: opencv-python>=4.1.0 in /usr/local/lib/python3.10/dist-packages (from mtcnn->keras-facenet) (4.8.0.76)\n",
            "Requirement already satisfied: numpy>=1.21.2 in /usr/local/lib/python3.10/dist-packages (from opencv-python>=4.1.0->mtcnn->keras-facenet) (1.23.5)\n"
          ]
        }
      ],
      "source": [
        "#https://pypi.org/project/keras-facenet/\n",
        "!pip install keras-facenet\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "oSukhDDh7dER"
      },
      "source": [
        "## Section 2 - Mount Google Drive\n",
        "\n",
        "Run the following cell as is to mount Google Drive.\n",
        "\n",
        "Upload all necessary content for this practical into your Google Drive's Data/D7 folder.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LeiWW7cS0Ip5",
        "outputId": "54f98de6-b030-4c37-ff2d-11d7cb4315a2"
      },
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "folder = '/content/drive/My Drive/ITI108/D5/'\n",
        "train_folder = folder + '/data/data/'\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "\n",
        "#google drive mounting was used to test the code before integrating with docker and app components. This storage will not be used for final code.\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "folder = '/content/drive/MyDrive/ITI108/D5/'\n",
        "\n",
        "train_folder = folder + '/data/data/'"
      ],
      "metadata": {
        "id": "YFkMpf5xXVE3",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "f97c344d-091b-4f34-e994-cb05b2340417"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vk5by8v_7m-d"
      },
      "source": [
        "## Section 3 - Declare a List of Functions\n",
        "\n",
        "Run the following cell to define a list of functions that we will be using later on.\n",
        "\n",
        "---\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Uewvppe-vTvi"
      },
      "outputs": [],
      "source": [
        "#@title\n",
        "import numpy as np\n",
        "import cv2\n",
        "from IPython.display import Image, display\n",
        "from google.colab.patches import cv2_imshow\n",
        "from mtcnn import MTCNN\n",
        "\n",
        "import tensorflow\n",
        "from tensorflow import keras\n",
        "\n",
        "from tensorflow.keras.layers import Conv2D, Activation, Input, Add, MaxPooling2D, Flatten, Dense, Dropout, BatchNormalization, Concatenate, Lambda, add, GlobalAveragePooling2D, Convolution2D, LocallyConnected2D, ZeroPadding2D, concatenate, AveragePooling2D\n",
        "from tensorflow.keras.models import Model, Sequential\n",
        "from tensorflow.keras import backend as K\n",
        "\n",
        "from chromadb.api.types import EmbeddingFunction, Embeddings, Image, Images\n",
        "import numpy as np\n",
        "from typing import List\n",
        "\n",
        "\n",
        "# Loads an image from a file using OpenCV.\n",
        "# NOTE: OpenCV loads an image in BGR format by default,\n",
        "#       so we must convert it back to the RGB format.\n",
        "#\n",
        "def load_image(filename):\n",
        "    img = cv2.imread(filename)\n",
        "    return cv2.cvtColor(img, cv2.COLOR_BGR2RGB)\n",
        "\n",
        "def normalize(img):\n",
        "    mean, std = img.mean(), img.std()\n",
        "    return (img - mean) / std\n",
        "\n",
        "# Draw a bounding box over the image with a\n",
        "# text.\n",
        "#\n",
        "def draw_box(img, x1, y1, x2, y2, text):\n",
        "    img = cv2.rectangle(img,(x1,y1),(x2,y2),(255,255,0),2)\n",
        "\n",
        "    if text != \"\":\n",
        "        img = cv2.rectangle(img,(x1,y1),(x2,y1 + 12),(255,255,0),-1)\n",
        "        img = cv2.putText(img, text, (x1, y1 + 10), cv2.FONT_HERSHEY_PLAIN, 0.7, (0,0,0), 1, cv2.LINE_AA)\n",
        "\n",
        "    return img\n",
        "\n",
        "\n",
        "# Crops out parts of an image based on a list of bounding\n",
        "# boxes. The cropped faces are also resized to 160x160 in\n",
        "# preparation for passing it to FaceNet to compute the\n",
        "# face embeddings.\n",
        "#\n",
        "def crop_faces_to_160x160(img, bounding_boxes):\n",
        "    cropped_faces = []\n",
        "\n",
        "    for (x,y,w,h) in bounding_boxes:\n",
        "        cropped_face = img[y:y+h, x:x+w]\n",
        "        normalize(cropped_face)\n",
        "        cropped_face = cv2.resize(cropped_face, (160, 160), interpolation=cv2.INTER_CUBIC)\n",
        "        cropped_faces.append(cropped_face)\n",
        "\n",
        "    return np.array(cropped_faces)\n",
        "\n",
        "\n",
        "# Shows an image in Colab\n",
        "#\n",
        "def show_image(img):\n",
        "    cv2_imshow(cv2.cvtColor(img, cv2.COLOR_RGB2BGR))\n",
        "\n",
        "\n",
        "\n",
        "from IPython.display import display, Javascript\n",
        "from google.colab.output import eval_js\n",
        "from base64 import b64decode\n",
        "\n",
        "def take_photo(filename='photo.jpg', quality=0.8):\n",
        "  js = Javascript('''\n",
        "    async function takePhoto(quality) {\n",
        "      const div = document.createElement('div');\n",
        "      const capture = document.createElement('button');\n",
        "      capture.textContent = 'Capture';\n",
        "      div.appendChild(capture);\n",
        "\n",
        "      const video = document.createElement('video');\n",
        "      video.style.display = 'block';\n",
        "      const stream = await navigator.mediaDevices.getUserMedia({video: true});\n",
        "\n",
        "      document.body.appendChild(div);\n",
        "      div.appendChild(video);\n",
        "      video.srcObject = stream;\n",
        "      await video.play();\n",
        "\n",
        "      // Resize the output to fit the video element.\n",
        "      google.colab.output.setIframeHeight(document.documentElement.scrollHeight, true);\n",
        "\n",
        "      // Wait for Capture to be clicked.\n",
        "      await new Promise((resolve) => capture.onclick = resolve);\n",
        "\n",
        "      const canvas = document.createElement('canvas');\n",
        "      canvas.width = video.videoWidth;\n",
        "      canvas.height = video.videoHeight;\n",
        "      canvas.getContext('2d').drawImage(video, 0, 0);\n",
        "      stream.getVideoTracks()[0].stop();\n",
        "      div.remove();\n",
        "      return canvas.toDataURL('image/jpeg', quality);\n",
        "    }\n",
        "    ''')\n",
        "  display(js)\n",
        "  data = eval_js('takePhoto({})'.format(quality))\n",
        "  binary = b64decode(data.split(',')[1])\n",
        "  with open(filename, 'wb') as f:\n",
        "    f.write(binary)\n",
        "  return filename\n",
        "\n",
        "\n",
        "def launch_camera(prompt, filename):\n",
        "\n",
        "    print (prompt)\n",
        "    try:\n",
        "      filename1 = take_photo(filename)\n",
        "      print('Saved to ' + filename1)\n",
        "\n",
        "      # Show the image which was just taken.\n",
        "      #show_image(filename1)\n",
        "\n",
        "    except Exception as err:\n",
        "      # Errors will be thrown if the user does not have a webcam or if they do not\n",
        "      # grant the page permission to access it.\n",
        "      print(str(err))\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "\n",
        "###### Class implementing Custom Embedding function for chroma db\n",
        "#\n",
        "class UserFaceEmbeddingFunction(EmbeddingFunction[Images]):\n",
        "    def __init__(self):\n",
        "        # Intitialize the FaceNet model\n",
        "        self.facenet = FaceNet()\n",
        "\n",
        "    def __call__(self, input: Images) -> Embeddings:\n",
        "        # Since the input images are assumed to be `numpy.ndarray` objects already,\n",
        "        # we can directly use them for embeddings extraction without additional processing.\n",
        "        # Ensure the input images are pre-cropped face images ready for embedding extraction.\n",
        "\n",
        "        # Extract embeddings using FaceNet for the pre-cropped face images.\n",
        "        embeddings_array = self.facenet.embeddings(input)\n",
        "\n",
        "        # Convert numpy array of embeddings to list of lists, as expected by Chroma.\n",
        "        return embeddings_array.tolist()\n",
        "\n",
        "\n",
        "# Usage example:\n",
        "# user_face_embedding_function = UserFaceEmbeddingFunction()\n",
        "# Assuming `images` is a list of `numpy.ndarray` objects where each represents a pre-cropped face image ready for embedding extraction.\n",
        "# embeddings = user_face_embedding_function(images)\n",
        "\n"
      ],
      "metadata": {
        "id": "u6MLEu2BxOWT"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [],
      "metadata": {
        "id": "4-tLTuwfxM19"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7ndfDDOUHg2a"
      },
      "source": [
        "Next, write the necessary codes to load the MTCNN library and use it to detect faces in an RGB image of any size.\n",
        "\n",
        "To load the MTCNN library, use the following code:\n",
        "\n",
        "```\n",
        "face_detector_mtcnn = MTCNN()\n",
        "```\n",
        "\n",
        "In the detect_faces_with_cnn function, use the following codes to call MTCNN to detect faces and draw bounding boxes in an image:\n",
        "\n",
        "```\n",
        "bounding_boxes = []\n",
        "detected_faces = face_detector_mtcnn.detect_faces(img)\n",
        "for detected_face in detected_faces:\n",
        "    bounding_boxes.append(detected_face[\"box\"])\n",
        "\n",
        "return bounding_boxes\n",
        "```\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "q0Hq8JgS84Mq"
      },
      "outputs": [],
      "source": [
        "# TODO:\n",
        "# Loads the MTCNN pre-trained model for facial detection\n",
        "#...#\n",
        "face_detector_mtcnn = MTCNN()\n",
        "\n",
        "\n",
        "# Use MTCNN to detect face bounding boxes. The bounding boxes\n",
        "# returned from this function will be in the following format:\n",
        "# [\n",
        "#    (x, y, w, h),\n",
        "#    (x, y, w, h),\n",
        "#    ...\n",
        "# ]\n",
        "#\n",
        "def detect_faces_with_mtcnn(img):\n",
        "\n",
        "    # TODO:\n",
        "    # Call the face_detector_mtcnn's detect_faces_with_mtcnn function.\n",
        "    # Then, extract only the bounding boxes and return the results\n",
        "    # to the caller as described in the format above.\n",
        "    #\n",
        "    #...#\n",
        "    bounding_boxes = []\n",
        "    detected_faces = face_detector_mtcnn.detect_faces(img)\n",
        "    for detected_face in detected_faces:\n",
        "        bounding_boxes.append(detected_face[\"box\"])\n",
        "\n",
        "    return bounding_boxes"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "WLDfzNRvHvmw"
      },
      "source": [
        "The FaceNet implementation in Keras with the pre-trained weights on the Microsoft 1 Million Celeb dataset can be found at: https://github.com/nyoki-mtl/keras-facenet. The same model has been provided to you in the data that you downloaded from Polymall.\n",
        "\n",
        "In the next cell,\n",
        "\n",
        "1. Load up a pre-trained FaceNet model:\n",
        "\n",
        "    ```\n",
        "    from keras_facenet import FaceNet\n",
        "    face_embedding_facenet = FaceNet()\n",
        "    ```\n",
        "\n",
        "2. Call the FaceNet model to retrieve our face embeddings:\n",
        "\n",
        "    ```\n",
        "    embeddings = face_embedding_facenet.embeddings(cropped_faces)\n",
        "    ```\n",
        "\n",
        "   \n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "EZOBWQlN8-DQ"
      },
      "outputs": [],
      "source": [
        "# TODO:\n",
        "# Load the FaceNet's pre-trained face embedding model.\n",
        "#...#\n",
        "\n",
        "\n",
        "from keras_facenet import FaceNet\n",
        "face_embedding_facenet = FaceNet()\n",
        "\n",
        "# Gets a list of face embeddings from FaceNet for each cropped face.\n",
        "#\n",
        "# The cropped_faces parameter is a numpy array of Nx160x160x3,\n",
        "# where N is any number of faces cropped from an image.\n",
        "#\n",
        "def get_face_embeddings_with_facenet(cropped_faces):\n",
        "\n",
        "    # TODO:\n",
        "\n",
        "    # Then pass the result into the face_embedding_facenet's predict\n",
        "    # model and return the results (Nx128 embeddings) as is.\n",
        "    #...#\n",
        "\n",
        "    embeddings = face_embedding_facenet.embeddings(cropped_faces)\n",
        "    return embeddings\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "Chromadb instantiation with facenet"
      ],
      "metadata": {
        "id": "AMDJBauobU_A"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Setup Chromadb in local filesystem\n",
        "\n",
        "import chromadb\n",
        "\n",
        "client = chromadb.PersistentClient(\"./drive/MyDrive/Data/chromadb\")"
      ],
      "metadata": {
        "id": "r9-Cs3cOurRj"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Instantiate custom user face embedding function\n",
        "userface_ef = UserFaceEmbeddingFunction()\n",
        "\n",
        "# Get the persistent store collection of registered users\n",
        "user_faces_db = client.get_or_create_collection(name=\"user_faces_db\", embedding_function=userface_ef)"
      ],
      "metadata": {
        "id": "lcg2DXLrvL5X"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HKYBpj9r9sy5"
      },
      "source": [
        "## Section 3 - Using FaceNet for Facial Verification\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZF-FgpEvFK2s"
      },
      "source": [
        "Let's write for the last time, a function to extract embeddings from a photograph, and assuming that there's only 1 person in the photo.\n",
        "\n",
        "In the following function, called get_embedding_from_photo:\n",
        "\n",
        "1. Load the image from the filename.\n",
        "\n",
        "    ```\n",
        "    img = load_image(filename)\n",
        "    ```\n",
        "\n",
        "2. Detect all bounding boxes of faces with MTCNN.\n",
        "\n",
        "    ```\n",
        "    face_boxes = detect_faces_with_mtcnn(img)\n",
        "    ```\n",
        "\n",
        "3. Crop out all the detected faces from the image to 160x160 pixels.\n",
        "\n",
        "    ```\n",
        "    cropped_faces = crop_faces_to_160x160(img, face_boxes)\n",
        "    if cropped_faces.shape[0] == 0:\n",
        "        return\n",
        "    ```\n",
        "\n",
        "4. Extract the cropped face of only the first detected face:\n",
        "\n",
        "    ```\n",
        "    cropped_face = cropped_faces[0:1, :, :, :]\n",
        "    ```\n",
        "\n",
        "5. Show the image of the cropped face:\n",
        "\n",
        "    ```\n",
        "    show_image(cropped_face[0])\n",
        "    ```\n",
        "\n",
        "6. Compute the face embedding and return the result.\n",
        "\n",
        "    ```\n",
        "    return get_face_embeddings_with_facenet(cropped_face)\n",
        "    ```"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "R9C9P9OY-xCN"
      },
      "outputs": [],
      "source": [
        "from numpy import dot\n",
        "from numpy.linalg import norm\n",
        "\n",
        "# Extract embedding from a photograph\n",
        "#\n",
        "def get_embedding_from_photo(filename):\n",
        "\n",
        "    # TODO:\n",
        "    # Load the image.\n",
        "    #...#\n",
        "    img = load_image(filename)\n",
        "\n",
        "    # TODO:\n",
        "    # Detect faces and extract all bounding boxes\n",
        "    #...#\n",
        "    bounding_boxes = detect_faces_with_mtcnn(img)\n",
        "\n",
        "    # TODO:\n",
        "    # Crop out the faces from the image\n",
        "    #...#\n",
        "    cropped_faces = crop_faces_to_160x160(img, bounding_boxes)\n",
        "\n",
        "    if cropped_faces.shape[0] == 0:\n",
        "        return\n",
        "\n",
        "    # TODO:\n",
        "    # Take the image of only the first detected face\n",
        "    #...#\n",
        "    cropped_face = cropped_faces[0:1, :, :, :]\n",
        "\n",
        "    # TODO:\n",
        "    # Show the cropped out face\n",
        "    #...#\n",
        "    show_image(cropped_face[0])\n",
        "\n",
        "    # TODO:\n",
        "    # Get the face embeddings using FaceNet and return\n",
        "    # the results.\n",
        "    #...#\n",
        "    return get_face_embeddings_with_facenet(cropped_face)\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Extract cropped user face image\n",
        "#\n",
        "def get_user_cropped_image_from_photo(filename):\n",
        "    # TODO:\n",
        "    # Load the image.\n",
        "    #...#\n",
        "    img = load_image(filename)\n",
        "\n",
        "    # TODO:\n",
        "    # Detect faces and extract all bounding boxes\n",
        "    #...#\n",
        "    bounding_boxes = detect_faces_with_mtcnn(img)\n",
        "\n",
        "    # TODO:\n",
        "    # Crop out the faces from the image\n",
        "    #...#\n",
        "    cropped_faces = crop_faces_to_160x160(img, bounding_boxes)\n",
        "\n",
        "    if cropped_faces.shape[0] == 0:\n",
        "        return\n",
        "\n",
        "    # TODO:\n",
        "    # Take the image of only the first detected face\n",
        "    #...#\n",
        "    cropped_face = cropped_faces[0:1, :, :, :]\n",
        "\n",
        "    # TODO:\n",
        "    # Show the cropped out face\n",
        "    #...#\n",
        "    show_image(cropped_face[0])\n",
        "\n",
        "    # TODO:\n",
        "    # Get the face embeddings using FaceNet and return\n",
        "    # the results.\n",
        "    #...#\n",
        "    return cropped_face[0]\n",
        "\n",
        "\n",
        "# Simple function to print the results of a query.\n",
        "# The 'results' is a dict {ids, distances, data, ...}\n",
        "# Each item in the dict is a 2d list.\n",
        "def print_query_results(query_results: dict)->None:\n",
        "    result_count = len(query_results['ids'][0])\n",
        "\n",
        "    i=0\n",
        "    #print(f'Results for query: {query_list[i]}')\n",
        "\n",
        "    for j in range(result_count):\n",
        "        id       = query_results[\"ids\"][i][j]\n",
        "        distance = query_results['distances'][i][j]\n",
        "        #data     = query_results['data'][i][j]\n",
        "        metadata = query_results['metadatas'][i][j]\n",
        "\n",
        "        print(f'id: {id}, distance: {distance}, metadata: {metadata}')\n",
        "\n",
        "        # Display image, the physical file must exist at URI.\n",
        "        # (ImageLoader loads the image from file)\n",
        "        #show_image(data)\n"
      ],
      "metadata": {
        "id": "zwvA6BFeuQ-p"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "0dp__yEs2ahx"
      },
      "source": [
        "A similarity function takes two sets of data and computes a value indicating how \"close\" two separate pieces of data are. We will have to use this later on to find out whether the photographs of two person belong to the same person.\n",
        "\n",
        "So, let's declare some functions to compute the cosine similarity and the Euclidean distance between 2 face embeddings.\n",
        "\n",
        "For the compute_cosine_similarity function, use the following code:\n",
        "\n",
        "```\n",
        "a = a[0]\n",
        "b = b[0]\n",
        "cos_sim = dot(a, b)/(norm(a)*norm(b))\n",
        "return cos_sim\n",
        "```\n",
        "\n",
        "For the compute_euclidean_distance function, use the following code:\n",
        "\n",
        "```\n",
        "a = a[0]\n",
        "b = b[0]\n",
        "euc_dist = norm(a - b)\n",
        "return euc_dist\n",
        "```\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "mJ__yC8H2Zzi"
      },
      "outputs": [],
      "source": [
        "\n",
        "# Update the codes for the following function to compute\n",
        "# the similarity.\n",
        "#\n",
        "# The formula is given by:\n",
        "#\n",
        "#                    A . B\n",
        "#     similarity = ---------\n",
        "#                   |A| |B|\n",
        "#\n",
        "def compute_cosine_similarity(a, b):\n",
        "\n",
        "    # TODO:\n",
        "    # Update your codes here:\n",
        "    #...#\n",
        "    a = a[0]\n",
        "    b = b[0]\n",
        "    cos_sim = dot(a, b)/(norm(a)*norm(b))\n",
        "    return cos_sim\n",
        "\n",
        "\n",
        "# Update the codes for the following function to compute\n",
        "# the eucldiean distance between two vectors.\n",
        "#\n",
        "# The formula is given by:\n",
        "#\n",
        "#     distance = | A - B |\n",
        "#\n",
        "def compute_euclidean_distance(a, b):\n",
        "\n",
        "    # TODO:\n",
        "    # Update your codes here:\n",
        "    #...#\n",
        "    a = a[0]\n",
        "    b = b[0]\n",
        "    euc_dist = norm(a - b)\n",
        "    return euc_dist"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HmtT2EPrGf98"
      },
      "source": [
        "Run the following cell to launch the camera in Colab to take a picture.\n",
        "\n",
        "We want to simulate using the photograph stored in an access card, passport of an identity card. So you can use any of of identification card that contains your photo.\n",
        "\n",
        "**NOTE: Your photograph is saved into Google Colab. If you are not comfortable with this, please use a photograph of another person that you can display on your mobile phone**"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "id": "BQD73Lhd2IZU",
        "outputId": "1c572979-2a00-4b10-e0ea-a00fc980ad35"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Take a photo of your identification card\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function takePhoto(quality) {\n",
              "      const div = document.createElement('div');\n",
              "      const capture = document.createElement('button');\n",
              "      capture.textContent = 'Capture';\n",
              "      div.appendChild(capture);\n",
              "\n",
              "      const video = document.createElement('video');\n",
              "      video.style.display = 'block';\n",
              "      const stream = await navigator.mediaDevices.getUserMedia({video: true});\n",
              "\n",
              "      document.body.appendChild(div);\n",
              "      div.appendChild(video);\n",
              "      video.srcObject = stream;\n",
              "      await video.play();\n",
              "\n",
              "      // Resize the output to fit the video element.\n",
              "      google.colab.output.setIframeHeight(document.documentElement.scrollHeight, true);\n",
              "\n",
              "      // Wait for Capture to be clicked.\n",
              "      await new Promise((resolve) => capture.onclick = resolve);\n",
              "\n",
              "      const canvas = document.createElement('canvas');\n",
              "      canvas.width = video.videoWidth;\n",
              "      canvas.height = video.videoHeight;\n",
              "      canvas.getContext('2d').drawImage(video, 0, 0);\n",
              "      stream.getVideoTracks()[0].stop();\n",
              "      div.remove();\n",
              "      return canvas.toDataURL('image/jpeg', quality);\n",
              "    }\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saved to webcam01.jpg\n"
          ]
        }
      ],
      "source": [
        "launch_camera(\"Take a photo of your identification card\", \"webcam01.jpg\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "J_xBEdblE_qa"
      },
      "source": [
        "Now, launch the camera again, to take another photograph of your live self.\n",
        "\n",
        "**NOTE: Your photograph is saved into Google Colab. If you are not comfortable with this, please use a photograph of another person that you can display on your mobile phone**\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 53
        },
        "id": "4MzI-ANk-T2s",
        "outputId": "e996703b-9eec-4fb2-9253-39922b081266"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Take a photo of yourself in the live camera\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "    async function takePhoto(quality) {\n",
              "      const div = document.createElement('div');\n",
              "      const capture = document.createElement('button');\n",
              "      capture.textContent = 'Capture';\n",
              "      div.appendChild(capture);\n",
              "\n",
              "      const video = document.createElement('video');\n",
              "      video.style.display = 'block';\n",
              "      const stream = await navigator.mediaDevices.getUserMedia({video: true});\n",
              "\n",
              "      document.body.appendChild(div);\n",
              "      div.appendChild(video);\n",
              "      video.srcObject = stream;\n",
              "      await video.play();\n",
              "\n",
              "      // Resize the output to fit the video element.\n",
              "      google.colab.output.setIframeHeight(document.documentElement.scrollHeight, true);\n",
              "\n",
              "      // Wait for Capture to be clicked.\n",
              "      await new Promise((resolve) => capture.onclick = resolve);\n",
              "\n",
              "      const canvas = document.createElement('canvas');\n",
              "      canvas.width = video.videoWidth;\n",
              "      canvas.height = video.videoHeight;\n",
              "      canvas.getContext('2d').drawImage(video, 0, 0);\n",
              "      stream.getVideoTracks()[0].stop();\n",
              "      div.remove();\n",
              "      return canvas.toDataURL('image/jpeg', quality);\n",
              "    }\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saved to webcam02.jpg\n"
          ]
        }
      ],
      "source": [
        "launch_camera(\"Take a photo of yourself in the live camera\", \"webcam02.jpg\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5X3O2lVjGk-Y"
      },
      "source": [
        "Finally run the following cell to call the necessary functions to compute the embedding from both photographs and use the cosine similarity and euclidean distance to compute the similarities.\n",
        "\n",
        "Additionally, see how we wrote a piece of code to judge if the two photographs belong to the same person if the cosine similarity is a larger than a pre-set threshold of 0.7.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "59HNedGm_Zys",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 877
        },
        "outputId": "c32778c1-b89f-4cd0-cf7e-f2d79fbf8e19"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 196ms/step\n",
            "1/1 [==============================] - 0s 116ms/step\n",
            "1/1 [==============================] - 0s 31ms/step\n",
            "1/1 [==============================] - 0s 29ms/step\n",
            "1/1 [==============================] - 0s 30ms/step\n",
            "1/1 [==============================] - 0s 24ms/step\n",
            "1/1 [==============================] - 0s 25ms/step\n",
            "1/1 [==============================] - 0s 22ms/step\n",
            "1/1 [==============================] - 0s 25ms/step\n",
            "1/1 [==============================] - 0s 23ms/step\n",
            "3/3 [==============================] - 0s 8ms/step\n",
            "1/1 [==============================] - 0s 151ms/step\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=160x160>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 2s 2s/step\n",
            "1/1 [==============================] - 0s 55ms/step\n",
            "1/1 [==============================] - 0s 44ms/step\n",
            "1/1 [==============================] - 0s 30ms/step\n",
            "1/1 [==============================] - 0s 33ms/step\n",
            "1/1 [==============================] - 0s 25ms/step\n",
            "1/1 [==============================] - 0s 23ms/step\n",
            "1/1 [==============================] - 0s 21ms/step\n",
            "1/1 [==============================] - 0s 21ms/step\n",
            "1/1 [==============================] - 0s 21ms/step\n",
            "1/1 [==============================] - 0s 21ms/step\n",
            "4/4 [==============================] - 0s 10ms/step\n",
            "1/1 [==============================] - 0s 39ms/step\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=160x160>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 92ms/step\n",
            "Cosine Similarity : 0.849604\n",
            "Euclidean Distance: 0.548445\n",
            "Photograph matches the real person (based on cosine similarity)\n",
            "512\n"
          ]
        }
      ],
      "source": [
        "e1 = get_embedding_from_photo('webcam01.jpg')\n",
        "e2 = get_embedding_from_photo('webcam02.jpg')\n",
        "\n",
        "similarity1 = compute_cosine_similarity(e1, e2)\n",
        "similarity2 = compute_euclidean_distance(e1, e2)\n",
        "\n",
        "print (\"Cosine Similarity : %f\" % similarity1)\n",
        "print (\"Euclidean Distance: %f\" % similarity2)\n",
        "\n",
        "if similarity1 >= 0.7:\n",
        "    print (\"Photograph matches the real person (based on cosine similarity)\" )\n",
        "else:\n",
        "    print (\"Photograph does NOT match the real person (based on cosine similarity)\")\n",
        "\n",
        "print(len(e1[0]))"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get Cropped image using MTCNN of the first face recognized\n",
        "registered_face = get_user_cropped_image_from_photo('webcam01.jpg')\n",
        "\n",
        "# Register the face into chroma db collection, with unique id, other meta data like user name can be added\n",
        "# In order to make ids unique, users email id would be recommended as ids\n",
        "user_faces_db.upsert(images=[registered_face], ids=[\"tyago@earthling.net\"])\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 429
        },
        "id": "XfGlWuzlpBGq",
        "outputId": "8ac6b0a4-c39f-42a0-fa88-4f453f64f3fa"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 60ms/step\n",
            "1/1 [==============================] - 0s 44ms/step\n",
            "1/1 [==============================] - 0s 37ms/step\n",
            "1/1 [==============================] - 0s 31ms/step\n",
            "1/1 [==============================] - 0s 26ms/step\n",
            "1/1 [==============================] - 0s 24ms/step\n",
            "1/1 [==============================] - 0s 23ms/step\n",
            "1/1 [==============================] - 0s 26ms/step\n",
            "1/1 [==============================] - 0s 22ms/step\n",
            "1/1 [==============================] - 0s 23ms/step\n",
            "3/3 [==============================] - 0s 10ms/step\n",
            "1/1 [==============================] - 0s 33ms/step\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=160x160>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(160, 160, 3)\n",
            "1/1 [==============================] - 0s 118ms/step\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Presented face is while login, and that too is cropped using MTCNN\n",
        "presented_face = get_user_cropped_image_from_photo('webcam02.jpg')\n",
        "\n",
        "# Cropped face is queried in vecror database for results, this is a scalable feature\n",
        "# result returned has disctance score to indicate similarity in Squared L2 distance should be < 0.5\n",
        "login_result = user_faces_db.query(query_images=[presented_face],n_results=3)\n",
        "\n",
        "# Print Results\n",
        "print_query_results(login_result)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 483
        },
        "id": "sFhQqU8pah9I",
        "outputId": "4f49d1d3-4581-49fe-8936-001bfd4c4f6a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 57ms/step\n",
            "1/1 [==============================] - 0s 36ms/step\n",
            "1/1 [==============================] - 0s 42ms/step\n",
            "1/1 [==============================] - 0s 26ms/step\n",
            "1/1 [==============================] - 0s 25ms/step\n",
            "1/1 [==============================] - 0s 22ms/step\n",
            "1/1 [==============================] - 0s 22ms/step\n",
            "1/1 [==============================] - 0s 21ms/step\n",
            "1/1 [==============================] - 0s 20ms/step\n",
            "1/1 [==============================] - 0s 21ms/step\n",
            "4/4 [==============================] - 0s 9ms/step\n",
            "1/1 [==============================] - 0s 36ms/step\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=160x160>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 2s 2s/step\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:chromadb.segment.impl.vector.local_persistent_hnsw:Add of existing embedding ID: tyago@earthling.net\n",
            "WARNING:chromadb.segment.impl.vector.local_persistent_hnsw:Number of requested results 3 is greater than number of elements in index 2, updating n_results = 2\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "id: tyago@earthling.net, distance: 0.30079176152134085, metadata: None\n",
            "id: krithika, distance: 1.693535580771108, metadata: None\n"
          ]
        }
      ]
    }
  ],
  "metadata": {
    "colab": {
      "provenance": []
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.9.9"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}