1st

WORKING.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "e3cee31f",
+   "metadata": {},
+   "source": [
+    "Create Data set"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c6811868",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import cv2\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "af2467d4",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "face_id = input('enter your id ')\n",
+    "# Start capturing video\n",
+    "vid_cam = cv2.VideoCapture(0)\n",
+    "\n",
+    "# Detect object in video stream using Haarcascade Frontal Face\n",
+    "face_detector = cv2.CascadeClassifier(\"haarcascade_frontalface_default.xml\")\n",
+    "\n",
+    "# Initialize sample face image\n",
+    "count = 0\n",
+    "\n",
+    "\n",
+    "\n",
+    "# Start looping\n",
+    "while (True):\n",
+    "\n",
+    "    # Capture video frame\n",
+    "    _, image_frame = vid_cam.read()\n",
+    "\n",
+    "    # Convert frame to grayscale\n",
+    "    gray = cv2.cvtColor(image_frame, cv2.COLOR_BGR2GRAY)\n",
+    "\n",
+    "    # Detect frames of different sizes, list of faces rectangles\n",
+    "    faces = face_detector.detectMultiScale(gray, 1.3, 5)\n",
+    "\n",
+    "    # Loops for each faces\n",
+    "    for (x, y, w, h) in faces:\n",
+    "        # Crop the image frame into rectangle\n",
+    "        cv2.rectangle(image_frame, (x, y), (x + w, y + h), (255, 0, 0), 2)\n",
+    "\n",
+    "        # Increment sample face image\n",
+    "        count += 1\n",
+    "\n",
+    "        # Save the captured image into the datasets folder\n",
+    "        cv2.imwrite(\"data/User.\" + str(face_id) + '.' + str(count) + \".jpg\", gray[y:y + h, x:x + w])\n",
+    "\n",
+    "        # Display the video frame, with bounded rectangle on the person's face\n",
+    "        cv2.imshow(\"frame\", image_frame)\n",
+    "        \n",
+    "        \n",
+    "\n",
+    "    # To stop taking video, press 'q' for at least 100ms\n",
+    "    if cv2.waitKey(1)==13 or int(count)==100:\n",
+    "    #if cv2.waitKey(100) & 0xFF == ord('q'):\n",
+    "        break\n",
+    "\n",
+    "    # If image taken reach 100, stop taking video\n",
+    "    elif count >= 50:\n",
+    "        print(\"Successfully Captured\")\n",
+    "        break\n",
+    "\n",
+    "# Stop video\n",
+    "vid_cam.release()\n",
+    "\n",
+    "# Close all started windows\n",
+    "cv2.destroyAllWindows()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7715ea46",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "##Train Dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "36639b47",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os,cv2\n",
+    "import numpy as np\n",
+    "from PIL import Image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8e9bd387",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "recognizer = cv2.face.LBPHFaceRecognizer_create()\n",
+    "detector= cv2.CascadeClassifier(\"haarcascade_frontalface_default.xml\");\n",
+    "\n",
+    "def getImagesAndLabels(path):\n",
+    "    #get the path of all the files in the folder\n",
+    "    imagePaths=[os.path.join(path,f) for f in os.listdir(path)]\n",
+    "    #create empth face list\n",
+    "    faceSamples=[]\n",
+    "    #create empty ID list\n",
+    "    Ids=[]\n",
+    "    #now looping through all the image paths and loading the Ids and the images\n",
+    "    for imagePath in imagePaths:\n",
+    "        #loading the image and converting it to gray scale\n",
+    "        pilImage=Image.open(imagePath).convert('L')\n",
+    "        #Now we are converting the PIL image into numpy array\n",
+    "        imageNp=np.array(pilImage,'uint8')\n",
+    "        #getting the Id from the image\n",
+    "        Id=int(os.path.split(imagePath)[-1].split(\".\")[1])\n",
+    "        # extract the face from the training image sample\n",
+    "        faces=detector.detectMultiScale(imageNp)\n",
+    "        #If a face is there then append that in the list as well as Id of it\n",
+    "        for (x,y,w,h) in faces:\n",
+    "            faceSamples.append(imageNp[y:y+h,x:x+w])\n",
+    "            Ids.append(Id)\n",
+    "    return faceSamples,Ids\n",
+    "\n",
+    "faces,Ids = getImagesAndLabels(\"data\")\n",
+    "s = recognizer.train(faces, np.array(Ids))\n",
+    "print(\"Successfully trained\")\n",
+    "recognizer.write(\"trainer/trainer.yml\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61d56dba",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import cv2\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f4f63033",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "face_detector = cv2.CascadeClassifier(\"haarcascade_frontalface_default.xml\")\n",
+    "cap = cv2.VideoCapture(0);\n",
+    "recognizer = cv2.face.LBPHFaceRecognizer_create();\n",
+    "recognizer.read(\"trainer/trainer.yml\")\n",
+    "id = 0\n",
+    "font = cv2.FONT_HERSHEY_SIMPLEX\n",
+    "while True:\n",
+    "    ret, img = cap.read();\n",
+    "    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)\n",
+    "    faces = face_detector.detectMultiScale(gray, 1.3, 5)\n",
+    "    for (x, y, w, h) in faces:\n",
+    "        roi_gray = gray[y:y + h, x:x + w]\n",
+    "        cv2.rectangle(img, (x, y), (x + w, y + h), (255, 0, 0), 2)\n",
+    "        id, conf = recognizer.predict(roi_gray)\n",
+    "        if(id==1):\n",
+    "            id=\"Harsha\"\n",
+    "        elif(id==2):\n",
+    "            id=\"Ishara\"\n",
+    "        elif(id==2):\n",
+    "            id=\"Saluk\"\n",
+    "        else:\n",
+    "            id = \"Unknown, can not recognize\"\n",
+    "        cv2.putText(img, str(id) + \" \" + str(conf), (x, y - 10), font, 0.55, (120, 255, 120), 1)\n",
+    "        #cv2.cv.PutText(cv2.cv.fromarray(img),str(id),(x,y+h),font,255)\n",
+    "        \n",
+    "    cv2.imshow(\"frame\", img)\n",
+    "    if cv2.waitKey(100) & 0xFF == ord('q'):\n",
+    "    \n",
+    "        break\n",
+    "vid_cam.release()\n",
+    "cv2.destroyAllWindows()\n",
+    "        \n",
+    "        "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a11261e4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f76ddfe4",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "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": "3.9.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}