AI face points detection using python and openCV.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import cv2\n",
    "import mediapipe as mp\n",
    "mp_face_detection = mp.solutions.face_detection\n",
    "mp_drawing = mp.solutions.drawing_utils"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "# For static images:\n",
    "IMAGE_FILES = []\n",
    "with mp_face_detection.FaceDetection(\n",
    "    model_selection=1, min_detection_confidence=0.5) as face_detection:\n",
    "  for idx, file in enumerate(IMAGE_FILES):\n",
    "    image = cv2.imread(file)\n",
    "    # Convert the BGR image to RGB and process it with MediaPipe Face Detection.\n",
    "    results = face_detection.process(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "  # Draw face detections of each face.\n",
    " if not results.detections:\n",
    "      continue\n",
    "    annotated_image = image.copy()\n",
    "    for detection in results.detections:\n",
    "      print('Nose tip:')\n",
    "      print(mp_face_detection.get_key_point(\n",
    "          detection, mp_face_detection.FaceKeyPoint.NOSE_TIP))\n",
    "      mp_drawing.draw_detection(annotated_image, detection)\n",
    "    cv2.imwrite('/tmp/annotated_image' + str(idx) + '.png', annotated_image)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "# For webcam input:\n",
    "cap = cv2.VideoCapture(0)\n",
    "with mp_face_detection.FaceDetection(\n",
    "    model_selection=0, min_detection_confidence=0.5) as face_detection:\n",
    "  while cap.isOpened():\n",
    "    success, image = cap.read()\n",
    "    if not success:\n",
    "      print(\"Ignoring empty camera frame.\")\n",
    "      # If loading a video, use 'break' instead of 'continue'.\n",
    "      continue\n",
    "\n",
    "    # Flip the image horizontally for a later selfie-view display, and convert\n",
    "    # the BGR image to RGB.\n",
    "    image = cv2.cvtColor(cv2.flip(image, 1), cv2.COLOR_BGR2RGB)\n",
    "    # To improve performance, optionally mark the image as not writeable to\n",
    "    # pass by reference.\n",
    "    image.flags.writeable = False\n",
    "    results = face_detection.process(image)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "    # Draw the face detection annotations on the image.\n",
    "    image.flags.writeable = True\n",
    "    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)\n",
    "    if results.detections:\n",
    "      for detection in results.detections:\n",
    "        mp_drawing.draw_detection(image, detection)\n",
    "    cv2.imshow('MediaPipe Face Detection', image)\n",
    "    if cv2.waitKey(5) & 0xFF == 27:\n",
    "      break\n",
    "cap.release()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}