{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "4a1a4b15-c1ca-4fc1-bc71-d569b006ddf5",
   "metadata": {},
   "outputs": [],
   "source": [
    "# importing packages\n",
    "import cv2\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import os # helps to interact with the operating system\n",
    "import pickle # helps to zip/compress the image file to byte(binary) format"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "09f066ec-6b25-40cf-a04e-2ee411af20c0",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'C:\\\\Users\\\\NIRNIT ROY\\\\Downloads\\\\Realtime Emotion Detection\\\\Emotion'"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# accessing the images present in \"Emotion\"\n",
    "# getcwd() - fetching the current working directory\n",
    "img_dir = os.path.join(os.getcwd(), 'Emotion')\n",
    "img_dir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "2e5d46e8-ddf6-4174-a063-aa182e516c98",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "C:\\Users\\NIRNIT ROY\\Downloads\\Realtime Emotion Detection\n"
     ]
    }
   ],
   "source": [
    "# to check the directory where currently we are working\n",
    "print(os.getcwd())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8f4dbd24-9da7-434b-9e1e-2e5a58544e64",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'C:\\\\Users\\\\NIRNIT ROY\\\\Downloads\\\\Realtime Emotion Detection\\\\data'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# creating a path to store the pickle files inside the data folder\n",
    "img_final = os.path.join(os.getcwd(), \"data\")\n",
    "img_final"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "cad8581c-7fbb-4935-b04e-a58c8d643cbd",
   "metadata": {},
   "outputs": [],
   "source": [
    "# to store all the input(images) and output(labels) in different []\n",
    "images = []\n",
    "labels = []"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "d5de381b-f846-47cd-9aef-590fc6372059",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "angry -----> Completed\n",
      "happy -----> Completed\n",
      "neutral -----> Completed\n",
      "sad -----> Completed\n",
      "surprised -----> Completed\n"
     ]
    }
   ],
   "source": [
    "# performing image preprocessing and saving the files\n",
    "# listdir() - to list all the files/folders present in the directory\n",
    "for i in os.listdir(img_dir): # to access the individual emntion folders\n",
    "    for j in os.listdir(os.path.join(img_dir,i)): # to access the actual images from each folder\n",
    "        img_path = os.path.join(os.path.join(img_dir,i),j)\n",
    "        img = cv2.imread(img_path)\n",
    "        img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)\n",
    "        img = cv2.resize(img, (48,48))\n",
    "        images.append(img)\n",
    "        labels.append(i.split(' ')[0]) \n",
    "    print(i, '-----> Completed')\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "db8f4a89-8b35-437f-a2b6-d1bd54724fed",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'angry', 'happy', 'neutral', 'sad', 'surprised'}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "set(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "2d806857-f685-401a-bacf-69404d23ca21",
   "metadata": {},
   "outputs": [],
   "source": [
    "images = np.array(images)\n",
    "labels = np.array(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "615fb70d-243e-49bf-9458-cf2da0c60a30",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(16082, 48, 48)"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "images.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "2af44c21-7271-4d29-8ddf-d69d0e24a1c6",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAaAAAAGeCAYAAADSRtWEAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjgsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvwVt1zgAAAAlwSFlzAAAPYQAAD2EBqD+naQAALZdJREFUeJzt3XlwVeX5wPEXlSV7SEgIgSQEN0BERvaxVgtUxlqFwnRsxxmptTpadAT+aGVG7bTTDoydcWsRnVaxnani0BYtOi6IgpUCsllZBLGNsmYjZCGJYbu/eU9/wQQ4z3Nz3lzfS/L9zNyB5M177rnvPTdPzr3Pc54esVgsZgAA+Jpd8HXfIQAABCAAgDecAQEAvCAAAQC8IAABALwgAAEAvCAAAQC8IAABALwgAAEAvLjIJJlTp06ZgwcPmoyMDNOjRw/fuwMA6CB7gZ2GhgZTWFhoLrhAOM+JJcjvf//7WElJSax3796xcePGxTZs2BDXvH379tlLA3FjDTgGOAY4Bsz5vQb297kkIWdAL7/8spk3b5555plnzPjx480TTzxhpk6danbv3m3y8/PFufbMx/r+979vevbsec6fOXHiROR9E6OxMaZXr17ieNg+WRdeeKE41+WMTttvbdtlZWWhY5999pk4t7m52em+jx8/Lp7xSvr06SOOp6WlhY5px0lOTo7TfUvbbz2Oo6yJVVdXFzrW0tJiXGjH+JEjR0LHGhsbxbna63vkyJGhYwMGDHBas5SUlNCxIUOGiHOLiorE8fT09MivT+04PHnypIlKu5SntmbafOm1Lf2+s8fJ9OnT1ddBQgLQY489Zu666y5zxx13BF/bQPT666+b559/3jz44INxPWD7iz7shSI92dqCakEikQFICyIuc7UgkMj91u47kY9b2nftWLjoooucxqOut+u+ufwBpm1bW3OX50N7ffXu3TvyfmnzpeCk/SGTzAHolPIHnK8AFM/8hCQhHDt2zGzevNlMmTLlqzu54ILg63Xr1p3zr7n6+vp2NwBA19fpAai6ujqI6P3792/3fft1eXn5WT+/YMECk5WVdfqmnQoDALoG72nY8+fPD97vbr3t27fP9y4BAL4Gnf4ZUL9+/YL3BisqKtp9335dUFBwzvdttfd+AQBdT6cHIPsh4+jRo82qVauCLIjWD8rs1/fdd1/c27Ef3EX58Fqbo304rI27fKCucdn29u3bxfFt27ZF3raWmKF90ChlRmVnZ4tz8/LyxPHi4uLQMS0Dx/UPH+nDZS2DTvvwWBrXPidtamoSx7UPxWtqakLHDhw4IM4919vsbf3zn/8MHbv22mvFuYMGDUpYlqn2YbzruIuYw7a1RAGXBIjOkJAsOJuCPWvWLDNmzBgzbty4IA3bpuW1ZsUBAJCQAHTrrbeaqqoq88gjjwR/EY0aNcq8+eabZyUmAAC6r4Rdise+3daRt9wAAN2L9yw4AED3RAACAHhBAAIAeJF07RjiIaVbulznyvW+NS7XVDvXZYza2rNnT+SUYy1lODMzUxzXkkukNOy+ffuKc7U0bWnNXK7r53ptMm1uampq5H3TjiN7OSzJl19+KY67zD106JA4vnbt2tCxf//73+Jc7TjV0rQTKZFp2In8fRXP9dyibDve35OcAQEAvCAAAQC8IAABALwgAAEAvCAAAQC8IAABALwgAAEAvDgv64Ck3HWt9sO1p70037XGSKr10ep8tJ73LjUpWpfa3NzchNULaK0FpMftWuej1ZRJx5q2pi7HmdbKQdu29rildg3a66u0tFQcLykpiVzrtmXLlsj1ZtprU1tTlzof1233SGCbCW3bUX+nUQcEAEhqvAUHAPCCAAQA8IIABADwggAEAPCCAAQA8IIABADwImnrgGweeVguuVTnkMg6H21c2/YHH3wgjm/bti1y3xytZkXaN62OJy0tTRzX6m2kfdN6vGjjGRkZkfsYabVT2rEg7Zv2fGj1GS59WlxJPX+0+qbm5ubI9ztp0qTI+2Vt3bo1dOyyyy4ziSQdK9pzfUqpE3Lhq/8ZdUAAgKTGW3AAAC8IQAAALwhAAAAvCEAAAC8IQAAALwhAAAAvkrYOyNZRhNVSSDUWWk2KVl+h5eRL/VA2btwozt2+fbs4LtVYnDx5MnI9jJWVlRW5HkbrAaPVvEj1Mtp9S/ut1fqkp6eLc7WaFu1xS/Ud2vPl0rdKq+3Qng+NtO/Hjh1zelxHjx6NPHfy5Mni+J/+9KfQsU8//dSp55XGpedVD2XcpRdRsuMMCADgBQEIAOAFAQgA4AUBCADgBQEIAOAFAQgA4EXSpmHblMywtEwpzdT18uNaGnd9fX3o2M6dO8W5vXv3jnzfWmsBLaVYSvXUUqFdW1hI87X11tZMelzafmuPW9u3lpaWyPut3ffx48cjbzsvL08cd2kPoKVhNzY2iuOVlZWRXlvxpNWXlpaGjr3zzjvi3DFjxjiVOSSypYJPUVPA453HGRAAwAsCEACAAAQA6D44AwIAeEEAAgB4QQACAHhBAAIAeJG0dUC2tiSsvkSqA9IubR7P/Up27doVOtbU1CTO1Wp5pLoTrSZFG3e5RP+JEyecaiCkfdNqdbS2BtJ4Q0OD03OtralLywSNdN9aPYz2XGvPp1RnpNWbSa03tOdLqyH68ssvxfGCgoLQsa1bt4pz9+/fL44PHjw48ppqv5MuVF4DLtvW6nFcx13ncQYEAPCCAAQA8IIABADwggAEAPCCAAQA8IIABADwggAEAPAiaeuAbC1DWC2EVGOh5dRrpB4v1qFDhyLXjWj7JtVvaPUVGqn/jNZfxrXXifS4XGogXO43nhojl1oe7XFp9RvSsST1Coqnr47W00eq4XDp/aQ9btfaKek1kp2dLc795JNPxPEJEyYkbM16ONYuunCpA+qM/eYMCADgBQEIAOAFAQgA4AUBCADgBQEIAOAFAQgA4MV52Y4hkemx2iXhpXEtLVHb75ycnNCxXr16GRdSqnVaWppTGrb2uKRUam3bWoq4lHqrPS4tTVu7b2lcS5vX0l+lVGstjVo7VrT50n27ppcnaq72fGZlZYlz9+3bJ45XVVVFbgWhpftrpNdX1HYJ8a65NB51rC3OgAAAXhCAAABeEIAAAF4QgAAAXhCAAABeEIAAAF4QgAAAXiRtHZDNIw/LJZdyzLW8eK1mRbuU/Zdffhmp5UE8tSFS/YbWliAzM1Mcz8jIiLwmrnUMUq2PVleSnp4ujkuX2dfqfFzrm1zqgDTScay1DNFq2VJTUyMfh9qaaGvqUmOk1S9Jvxek49+qrKwUx48cOSKOFxUVJaSlSKK51hF97WdA77//vrn55ptNYWFh8IS/8sorZz2gRx55xAwYMCD4hTxlyhSzZ8+eztxnAEAX0OEAZP+6uuqqq8yiRYvOOf7oo4+ap556yjzzzDNmw4YNQTX61KlTxTMHAED30+G34G688cbgdi727OeJJ54wDz30kJk2bVrwvT//+c+mf//+wZnSD37wA/c9BgB0CZ2ahFBWVmbKy8uDt93aXoNp/PjxZt26daHvZ9vPXdreAABdX6cGIBt8LHvG05b9unXsTAsWLAiCVOtN+jAPANB1eE/Dnj9/vqmrqzt9065KCwDoGjo1ALVekryioqLd9+3XYZcrt6msNoW47Q0A0PV1ah1QaWlpEGhWrVplRo0aFXzPfqZjs+HuvffeTusHlEg1NTWR6xy0+gqXvjl9+/YV5575tmdHala0Oh8tg1HrmyPVR2m1U1qdQnV1deS5Wm2IS/2Ta68h7ViSaDVIWm8c6RjX1lSrUZLWVKsD0u5bWjPtuT58+LA4/t///lccb/19F0XMoXbRtUbvvAtAR48eNZ999lm7xIOPPvooaKZWXFxs5syZY37961+bSy+9NAhIDz/8cFAzNH369M7edwBAdwpAmzZtMt/61rdOfz1v3rzg31mzZpkXXnjB/OxnPwtqhe6++25TW1trvvGNb5g333zTuTIcANDNA9D1118vnjLaqyP86le/Cm4AACRtFhwAoHsiAAEAvCAAAQC8OC/bMUhpidrl4DXapYCkS75rl4vX0rCl1F0tjVTaL+2+m5ubjQstwWTXrl2hY2vXrhXnamsqfR6p7Vd+fr44rq15WG2bNWTIEKe0eSntXjtGtXTmAwcOiOPS8eCSwq2lSmtr0tTUFHm/pefK0q7Yr7VrkI5TLVU65tASQZurjWutIrRjKer9tuIMCADgBQEIAOAFAQgA4AUBCADgBQEIAOAFAQgA4AUBCADgRdLWAdn887AcdCnHXKu1cc2L1y6zL+nVq5c4LrUmSEtLMy6kGgmt1ka7xP57770njldVVUV+XFodgvS4tPqLjz/+WBzX9s1e8T1qrc5VV10V+VjRni+tzmf79u3i+MaNG0PH7IWGJVo/L6kNxejRo8W5V155ZeTXT3p6euS58bQkSWQtj8tc17rIqO0zqAMCACQ13oIDAHhBAAIAeEEAAgB4QQACAHhBAAIAeEEAAgB4kbR1QC69b1xoNS9anZBLTr5Uq6DVw2i1IcePHw8dq6mpEefu3btXHNdy/qX6jry8vMh1I1qdQnV1tThXq2nRet9ItT51dXWRnw/tcWvrXVFRIY7v378/8ppqdXDasST1aFq2bFnk+iTrlltuidSHKJ7fKa59dxJ13zHlfrVaOG1c+r0jzdW224ozIACAFwQgAIAXBCAAgBcEIACAFwQgAIAXBCAAgBcEIACAF0lbB2Tz28Ny3F3qgLRaHK2eRuvp4yJqzn08tH4mkosvvthpTaR6mbVr1zrtt1TfUVJSIs4tLCx0qgOSamIyMjLEuVpdilQvo9Wi5eTkRO5jpO27Vr+krdlll10WuXbq7bffFsdff/310LEZM2Y4HcPamrvU6sQcxl37AbnM13qvxYMzIACAFwQgAIAXBCAAgBcEIACAFwQgAIAXBCAAgBdJm4Zt0//CUgBd0v+0FG5t2z179ox8qXrXcYmWHiulU2ZnZzu1LdixY4c4LqWQDxo0SJy7Z88ecTwzMzN07MEHHxTn/u1vf3Nqa+DyfGjp5VVVVZGPYS1luLKyUhw/dOhQ6NiuXbuc0nr79u0bOjZhwgRx7ne/+11x/J133gkdq62tFee6ps27rEkP5fl0aXvg0iYi0a1vLM6AAABeEIAAAF4QgAAAXhCAAABeEIAAAF4QgAAAXhCAAABeJG0dUCJaGmh1PPHk+zc3N0eu43GpB9DqRrRtp6enh441NTWJc7XL5Ofn54vjpaWloWODBw92ah2Qm5sbOrZ//36nbbe0tIjj0rr17t1bnFtTU2Oikp7LeI7xgoKCyOuibfuTTz4Rx6dNmxY69uGHHzrVZY0dOzZymxXXFhfSa9e1Dqgr4wwIAOAFAQgA4AUBCADgBQEIAOAFAQgA4AUBCADgBQEIAODFRclczxNW0yPl9JeVlYnbTUlJEcfr6+sj98bp06ePOFerDZF6yGg1RlptiLRv2ppItTbatrX52uMaOnRo5P5N5eXlxoW2pmlpaZHrybTaK6nPkdTbKZ7jTKrL0upWrrvuOnHuxIkTxfHLL7888mtvzZo1kbctrWc8dXbaMS6tmVYHdEp5PrsyzoAAAF4QgAAAXhCAAABeEIAAAF4QgAAAXhCAAABeJG0atk2vDUux3b59e+i8L774wimtV0rltI4ePRo6tmfPHqfLrrtclt2lzURWVpZTiwttv6X52dnZ4lwtnVlK45ZStK2qqipxvF+/fpFTqaW2HfE8LimVWns+tLR5LS1Yak2gtc/IyMgQxw8fPhw6Nnz4cONCWhdtv7Q1GTBgQMJSqWPKfZ88eTLyXG3cN86AAABeEIAAAF4QgAAAXhCAAABeEIAAAF4QgAAAXhCAAABeJG0dkK2jCMut37dvX+i8UaNGOdVIaJeEHz16dOS2BtXV1ZHrL7TaD+1y8lIdhEtNSjzze/XqFamlgbYmVktLS6T2FvHUTkmtN7Rxrf5CWzPp+ZbakcTzuPPy8iLXVmmPSztOpbYIUo2dVVJSEvm+pWPQKigoEMfz8/Mjr7l2DGukNdfqj1xbPUi1dC51i6e335EfXrBggRk7dmzwy8w+IdOnTze7d+8+6xfh7Nmzg1/0tp/KzJkzTUVFhfOOAgC6lg4FINsQygaX9evXm5UrVwZR/4Ybbmj3l+DcuXPNihUrzLJly4KfP3jwoJkxY0Yi9h0A0F3egnvzzTfbff3CCy8EZ0KbN2823/zmN01dXZ157rnnzIsvvmgmTZoU/MySJUvMsGHDgqA1YcKEzt17AED3TEKwAcfKyckJ/rWByJ4VTZkypd2114qLi826detC38O3n7u0vQEAur7IAch+uDVnzhxzzTXXmBEjRgTfKy8vDz7sO/MCk/379w/Gwj5XshfDbL0VFRVF3SUAQHcIQPazIHtV6qVLlzrtwPz584MzqdablOEGAOjmadj33Xefee2118z7779vBg0a1C6V0aaI1tbWtjsLsllwYWmONsVXS/MFAHTzAGTz0e+//36zfPlys3r1alNaWnpWjYytrVi1alWQfm3ZNO29e/eaiRMndmjHpFoHqYeMls/fp08fcVzr41JZWRk6NnDgQHGuS/2G1ttGq7+QalZaP8OL2rPH5Q8IrUZCq2mRni+tBkLqs2I1NDSI4zU1NaFjhYWFTmsmrYt2DGuPWzvGpZoXqQdSPONSPY52nGmvH5d6G61fkPa4tNfQ+dyzJ2kCkH3bzWa4vfrqq8ET1vq5jv3sxhZh2n/vvPNOM2/evOAJsUVnNmDZ4EMGHAAgcgBavHhx8O/111/f7vs21fpHP/pR8P/HH388+GvdngHZDLepU6eap59+uiN3AwDoBjr8FpzGvj2waNGi4AYAQBguRgoA8IIABADwggAEAPCCAAQA8CJp+wHZupWwGhCp5kXrLzN8+HBxvKysTBzfunVr5FodrfZDqnnRem9otSFS3xytxkGrv9DqTqTHpdUvaTUrUi2PVpsh1XRZ2nUJpd42tiQh6lytZ49WY7R//35x/IsvvhDHpeNY22/tWJDqgLSeO1KfIktq+6I9l0OGDHFas88//zx07Nprr3Xq5RUTkr8SXUOU6O1zBgQA8IIABADwggAEAPCCAAQA8IIABADwggAEAPAiadOw7aXVw1KPtZRjyc6dO8Xx9evXi+P/+c9/QsfGjh0rztVSqV3SIV1aD2htB+yVzl0ugy+l3mqptVqKeL9+/SK1S4gn5X7w4MGR09Nts0aJlhY8ZsyYyG0ktMctrZl2LGmvPS2lWCoHSE1NdToOpdeXdhxJae/W4cOHxXGpkeaZF2/GVzgDAgB4QQACAHhBAAIAeEEAAgB4QQACAHhBAAIAeEEAAgB4kbR1QPbS7GHtC6S6E60GQruselVVlTguXQpfq5GQ2hJodQxaDZFWGyJdYl+bW11dLY737Nkz8uPW1kxrqSCty1tvvSXOzc3NFcc//PBDcXzDhg2R9ssaN25c5DYUWluPNWvWiOPXXHONOD506NDILUe0GiOpBYb2+tBqjFzamQwYMEAcP3r0qEnGlgc9lMelbdtlfme0ieAMCADgBQEIAOAFAQgA4AUBCADgBQEIAOAFAQgA4AUBCADgRdLWAdn6kLB6h7S0tEj1E/HUEvTv318cv+yyy0LHamtrjYsLL7wwIb2EtB4vWq8U7b7T09Mjz5ceczw1LwcOHIjcX6aiosLpvq+44orI/WOk/daer/Hjx4tzS0tLxfG1a9eK40VFRaFjn3/+udOxID0nR44cceo7JdH6Tkk9q+Ih1atpvbp6ONbynM84AwIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHiRtGnY9rLvYZd+ly7/r6VZa+mWWVlZ4nhBQUHoWENDQ0IvjZ4oWjsG7TL52ppK41qq9LFjxyJvW2t5UFdXJ45rrT1KSkoip/Nr6efSczJw4MDIadRWS0uLOH7xxReHjm3fvl2cq6VpDxkyJPJx5vL60Y5xqU2Etu14Uq1dtp1I2ppKj0va73jXgzMgAIAXBCAAgBcEIACAFwQgAIAXBCAAgBcEIACAFwQgAIAXSVsHJJFqR44ePSrOzc7OFse1WoSqqqrQscbGRqfLydsWFFG51FBodQjafmt1JSkpKZHrgLQ1kdpvaNuW9iuedZGOtdzcXKdaHakGSWv1oNW8aOsitefIzMwU51ZXV4vjhYWFJlHHuDSu1V1ptVWHDh0SxwcMGBA6FlbP+HXUCWltKLRjJdE4AwIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHhBAAIAeJG0dUC2n0RYTwmpjkHqFRRPzx6tRkKq9endu7c4t76+PvJ9a7UAWj6/VKuj7be2ba1OSJqv1W1p49K+HzlyJHJNVzy9paQapQMHDjitqVS/odV2aPutHYcurw/tWJDuW+tNoz1uqSZMo9WyafVPUv8n7bm+UKlRSmQdj9a3x7WGScMZEADACwIQAMALAhAAwAsCEADACwIQAMALAhAAwAsCEADAi6StA7I1AWF1AVJNTEFBgbjdY8eOieO9evWKXA9w8OBBp5oWadsuvYK0egGtdkOrFdBqKKQ119ZM69kj3Xdtba1TjYP2uKV6G61nj1YnJPWX0WrdtNoQbb60Lv369RPnasepVEen1cNoz4d0nLnsVzzHoVSPpu13D6XGT6uP8tVrqDNwBgQA8IIABADwggAEAPCCAAQA8IIABADwggAEAPAiadOwbXpglBRBLZUzPz9fHK+srBTH9+7dGzpWXl6esJRH18uuu1xW3SX91WpqagodO378uDhXaxUhbVtLL9faMWj7JqWAa/etpQVLKd7V1dXiXC39XErxtkaOHBk5hVt7vqR1cU1Hlo5D7fjX1jQrK8tp33zpoaypNi6tmzQ33t91HfqttHjx4uDgtPUq9jZx4kTzxhtvtHvRzJ492+Tm5pr09HQzc+ZMU1FR0ZG7AAB0Ex0KQIMGDTILFy40mzdvNps2bTKTJk0y06ZNMzt27AjG586da1asWGGWLVtm1qxZExQZzpgxI1H7DgDoLm/B3Xzzze2+/s1vfhOcFa1fvz4ITs8995x58cUXg8BkLVmyxAwbNiwYnzBhQufuOQDgvHaBy2cSS5cuDS5hYd+Ks2dF9j3zKVOmnP6ZoUOHmuLiYrNu3TrxfXTbprftDQDQ9XU4AG3bti34fMd+2HjPPfeY5cuXm+HDhwcfwNvrqGVnZ5/VK136cH7BggXBB3ytt6KiomiPBADQtQPQ5Zdfbj766COzYcMGc++995pZs2aZnTt3Rt6B+fPnm7q6utO3ffv2Rd4WAKALp2Hbs5xLLrkk+P/o0aPNxo0bzZNPPmluvfXWIA3SpoC2PQuyWXDSFartmZSWugkA6Hqc64BsjYj9HMcGI1sjsGrVqiD92tq9e3dQN2M/I4qy3bD6EynHXMvHT0tLE8ftW4ZR6xi0uhGphkir9dHqm7Q6IZecfa2GQqsNkWpetDVraGgQx6V2DlpdllRr49qa49JLLxXnDhkyRBwfMWJE6FhNTY049x//+Ic4/vHHH4vj9i32MDbZSKIdp9Kxph1nzc3N4nhqamrkY1SrZZPWxPW1e0qps+vKLuro22U33nhjkFhgfzHYjLfVq1ebt956K/j85s477zTz5s0zOTk5wYvz/vvvD4IPGXAAAKcAZK8ScPvtt5tDhw4FAccWpdrg8+1vfzsYf/zxx4O/YuwZkD0rmjp1qnn66ac7chcAgG6iQwHI1vlob7UsWrQouAEAIOFipAAALwhAAAAvCEAAAC8IQAAAL5K2H5Ct5wmr6XGpadFy7lNSUsRxqZ7g8OHDkesUtFoCrV5GI9VHudRuxDNfWjPXGiSplkdbb63mS9s3qa/OFVdc4XTfBw4cEC+H5dLbRrve4tatW0PHSkpKxLla/ZNUdK4d41odkLRtraZLO1a0Y1yi1Sb2cOyD5LJt7fXl0sMsHpwBAQC8IAABALwgAAEAvCAAAQC8IAABALwgAAEAvEjaNOxEcU15lFJFpbYDVkZGRuRLwmvpktq4lOKttXLQaOmzUuq7lhafn58fORVaa8eg0Vp3nNn9t63c3NzIc62LLgp/aWpdg7VjobWfV5SUYy0dWbtv6XE1NjZGboWiPd8DBw50SovXJDpduaviDAgA4AUBCADgBQEIAOAFAQgA4AUBCADgBQEIAOAFAQgA4EXS1gHZ2pKwmgLp0upaHYJW5+N66fSoNRBaHZA0Fs/l5qO2NIin9kOr5WlpaYn8fDU1NYnj6enpoWOZmZni3MrKSqfHLdVPNTQ0iHO11h1SHZFW06Idw1rLkdLS0kjPZTxrJtXyaHU+2nEm1eG5tDSI576l7SdzjdAp5XFJr8/OeFycAQEAvCAAAQC8IAABALwgAAEAvCAAAQC8IAABALwgAAEAvLgomfPTw3LUpfoLra4knvuVuGzfpVeKVqvjsm2tH5BWn6GNS/um1S/V1dVFrr/Q+i/l5OSI43v37hXHy8rKItcgFRcXi+O1tbWRa22ysrLE8YKCgsj9nbTnWqtXk+qItBoj7TUgSXQtTiJ/J5106NflWv8krVvUsbY4AwIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHiRtGnYUjqnlOKntTzwSUunlC4n39zcLM7VxqVtJ/pxSS0VtDRsLe1XStPW9ktLVx42bFjkVGlpzKqpqYm8b4MGDRLn5ufni+NaWrC05lp6bX19vYlKS7PWnk/pte/ahsUlndk1FdrXtrXtk4YNADhv8RYcAMALAhAAwAsCEADACwIQAMALAhAAwAsCEADAi6QtmrH1BD179uzw5eK1OoWwbSY6L16bq9UxaHU8Uq2NtmautVNaewCpfkO779TUVKfH7TJX27e8vLzQsZKSEnFudnZ25LYg2jGstRRpaGgQx13qO1xqebT91mrGpPnats/XOiCf9+2y3q04AwIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHhBAAIAeJG0dUC2X0pYHYZU0+Ja56PJzMyM3K9EI9VYpKWlOdVftLS0RN5vrc5Hq5eRnhNt23379o1cy6P1+9H64mj71rt378hztftOSUmJXA+jvQa0Wh5pXHrtxbNtqc+X9ri0mhbtvl22ncg6IY207UTvl1TPI613vPfLGRAAwAsCEADACwIQAMALAhAAwAsCEADACwIQAMALAhAAwIukrQOyfWCi9ANqbGwUt6vVZ2h9LEaNGhU6VlZW5lSrk5OTE7luRKsTknrAnDhxIqG1BNJ8qS4knvuWanG0epiMjAxxXJsvHUvacZaenh75+dTWRFtTrbdU1Hoyq7m5OXLNmLZmiawDSiTX+kCfotYgUQcEAEhqvAUHAPCCAAQA8IIABADwggAEAPCCAAQA8CJp07BLS0tDU2zr6uoipxRrKaoDBw4Ux6+44opIKcHWwoULxXFp37WWB1par5S6rqWHu6aRSo+rtrZWnKtdol9aFy0tV9u29ny6pKdrKcfSvmnPh5YqrT3f0r7ZNikuayKVE2ivXdc0bXQuqWRFK2fplDMg+wvVvsjnzJnT7uCePXu2yc3NDX4pzpw501RUVLjcDQCgC4ocgDZu3GieffZZM3LkyHbfnzt3rlmxYoVZtmyZWbNmjTl48KCZMWNGZ+wrAKC7B6CjR4+a2267zfzhD39o17HSvjX23HPPmccee8xMmjTJjB492ixZssT861//MuvXr+/M/QYAdMcAZN9iu+mmm8yUKVPafX/z5s3BZw1tvz906FBTXFxs1q1bF/p+dX19fbsbAKDr63ASwtKlS82WLVuCt+DOVF5eHnx4mp2d3e77/fv3D8bOZcGCBeaXv/xlR3cDANCdzoD27dtnHnjgAfOXv/zF6YKGbc2fPz946671Zu8DAND1dSgA2bfYKisrzdVXXx2kv9qbTTR46qmngv/bMx2b5nxmaq3NgisoKAhNdc3MzGx3AwB0fR16C27y5Mlm27Zt7b53xx13BJ/z/PznPzdFRUXBJexXrVoVpF9bu3fvNnv37jUTJ07s0I7Zepyws6y2iQ9nqqqqErdr3z6UTJ06NXLdidSqwbrrrrvE8eeffz50zAZ3F9IZq1Qj1Bn1FVI9jlTTFU/dllQvk5KS4lQPo41nZWWJ4y7blmpetDqgI0eOiONavU1TU1PkY0F7Z0Q71ly4tGNwPcaluhfX+qVTwrYT2SpFI9V0ae1jIgUg2z9lxIgRZ/UtsTU/rd+/8847zbx584LeNvZs5v777w+Cz4QJEzpyVwCALq7Tr4Tw+OOPB9HPngHZDDd7RvH000939t0AALp7AFq9evVZp+CLFi0KbgAAhOFipAAALwhAAAAvCEAAAC8IQAAAL5K2H5BN+Q6r45BqP1566SVxuwMGDBDHr7zyysg1FFptx3e+853INRL2EkiS1NRUcdzWZ0XN2dfqTrT6C6kOQtovq7GxURw/fPhw5B5KWm8brZ5GqgPSaj+0GiWpF5G2ba0XizYu3bd2nGl1Wy51J9p+S+viuibafkvjLnO18Xj77nzdNUharVkrzoAAAF4QgAAAXhCAAABeEIAAAF4QgAAAXhCAAABeJG0atk33DEv5XLlyZei87du3i9sdM2aMOJ6eni6ONzc3R05nli5zb82YMSN0zF51XLJkyZLIKd5aWq+WWquR0jW1VGmXdGUtLV5Lw66uro58rGhtCbRjxZYhhJHKELQ1scJ6c8Wz5lrar5aSL427bluSyFRo13YMPZTH5ZJqncjH1RnzOAMCAHhBAAIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHiRtHVAH3zwQWi9w+rVq0Pn5efni9vdsmWLOF5VVSWO5+bmmqi0fP+jR4+Gjk2dOlWc27dvX3H8iSeeCB2rr69PaJ2CVPPS0tIiztXaNUj1Nlq9jFbzpbWCkOqMpLqreFpcSDVjhYWF4tzBgweL467tHBLVbsGlhsh3HVCi5iaaSx2Q9HzE+5g5AwIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHhBAAIAeJG0dUBvvfVWaP2IVMeg9UI5cOCAOC7VGFm333575HoarQeMlFdfW1srzh05cqQ4/tBDD4WOLV68WJyr9VjSet9odScSrV+QS42F9ny49PTRala04/Tiiy8OHSsqKnKqMTpx4oQ4LtVPaTVC2vMhrYtrHZDL86Hx2ZMnkf18EnXf1AEBAJIab8EBALwgAAEAvCAAAQC8IAABALwgAAEAvCAAAQC8SNo6IJu3H5a7L+X7a/nnWo+YFStWiOM//OEPI9d2aPUX0uPSamnq6urE8by8vNCxuXPninOXLl0qjq9cudJEpfX70UjrotXDSP184jmW0tLSIq23NXDgQHE8MzPTRKX1A/rss88SVjul1Z241OO41vK47LfLuLZmiay38VX/RB0QACCp8RYcAMALAhAAwAsCEADACwIQAMALAhAAwIukTcNOVGphSkqKOL5jxw5xfP369aFjt9xyizh3//79CUvlTE9PF8ebmpoip4//5Cc/Ecf79esnjv/973+P3G7B5TL4Wuq6liqqpc3n5OSEjg0bNkycqz3uxsbG0LHc3Fxx7rXXXiuOf/rpp+dlqnQy33eijuFkfszS44r3MXMGBADwggAEAPCCAAQA8IIABADwggAEAPCCAAQA8CLp0rBbU2MTlbqopS1q9yulM9fX14tzGxoaTFRaGraWcizt9/Hjx51ShrWrSkvpzFqqs/Z8aPsedb/iGZfuW1sTlzVtbm52Os5aWloSltqrrZkLbb+k14D2+tHWVLuKvnTl9UReDduV62tA+32jXq07lshHF4GtlSkqKvK9GwAAR/v27TODBg06fwKQ/Yv34MGDJiMjI/iLx55V2IBkH4hLj5TuhDVjzTjOklN3eW3GYrHgTLywsFA8A0y6t+Dszp4rYtonqys/YYnAmrFmHGfJqTu8NrOystSfIQkBAOAFAQgA4EXSByB7ocxf/OIX6gUzwZpxnH29eG2yZq6SLgkBANA9JP0ZEACgayIAAQC8IAABALwgAAEAvCAAAQC8SPoAtGjRIjN48GDTp08fM378ePPhhx/63qWk8f7775ubb745uNyFvWzRK6+80m7cJjg+8sgjZsCAASYlJcVMmTLF7Nmzx3RXCxYsMGPHjg0u85Sfn2+mT59udu/efdZFQGfPnm1yc3NNenq6mTlzpqmoqDDd2eLFi83IkSNPV+9PnDjRvPHGG6fHWTPZwoULg9fnnDlzWLPzKQC9/PLLZt68eUEd0JYtW8xVV11lpk6daiorK33vWlJobGwM1sQG6XN59NFHzVNPPWWeeeYZs2HDBpOWlhasn3al5q5qzZo1QXBZv369WblyZXA16xtuuCFYx1Zz5841K1asMMuWLQt+3l6XcMaMGaY7s5fGsr9EN2/ebDZt2mQmTZpkpk2bZnbs2BGMs2bhNm7caJ599tkggLfFmv2/WBIbN25cbPbs2ae/PnnyZKywsDC2YMECr/uVjOxTuXz58tNfnzp1KlZQUBD77W9/e/p7tbW1sd69e8deeuklT3uZXCorK4N1W7Nmzen16dmzZ2zZsmWnf+aTTz4JfmbdunUe9zT59O3bN/bHP/6RNRM0NDTELr300tjKlStj1113XeyBBx4Ivs9x9pWkPQM6duxY8BeXfduo7YVK7dfr1q3zum/ng7KyMlNeXt5u/ezFAe3bmKzf/9TV1QX/5uTkBP/a482eFbVds6FDh5ri4mLWrE3fm6VLlwZnjfatONYsnD3bvummm9odTxxnSX417FbV1dXBwd6/f/9237df79q1y9t+nS9s8LHOtX6tY92Zbfth35O/5pprzIgRI4Lv2XWxjceys7Pb/SxrZsy2bduCgGPfvrWfjS1fvtwMHz7cfPTRR6zZOdggbT82sG/BnYnj7DwIQECi/zrdvn27+eCDD1joOFx++eVBsLFnjX/961/NrFmzgs/IcDbb6+eBBx4IPme0yVMIl7RvwfXr1y9osXtmBpL9uqCgwNt+nS9a14j1O9t9991nXnvtNfPee++16z1l18y+9VtbW9vu5znm/teS+pJLLjGjR48Osglt8suTTz7Jmp2DfVvSJkpdffXVQet1e7PB2iYE2f/bM2qOsyQPQPaAtwf7qlWr2r1tYr+2bwVAVlpaGvxyaLt+thujzYbrrutnczVs8LFvH7377rvBGrVlj7eePXu2WzObpr13795uu2Zh7GuxpaWFNTuHyZMnB29Z2jPG1tuYMWPMbbfddvr/HGf/L5bEli5dGmRtvfDCC7GdO3fG7r777lh2dnasvLzc964lTZbN1q1bg5t9Kh977LHg/1988UUwvnDhwmC9Xn311djHH38cmzZtWqy0tDTW3Nwc647uvffeWFZWVmz16tWxQ4cOnb41NTWd/pl77rknVlxcHHv33XdjmzZtik2cODG4dWcPPvhgkClYVlYWHEf26x49esTefvvtYJw107XNgmPNvpLUAcj63e9+F/xC6NWrV5CWvX79et+7lDTee++9IPCceZs1a9bpVOyHH3441r9//yCQT548ObZ79+5Yd3WutbK3JUuWnP4ZG5x/+tOfBmnGqampse9973tBkOrOfvzjH8dKSkqC12BeXl5wHLUGH4s163gAYs3+h35AAAAvkvYzIABA10YAAgB4QQACAHhBAAIAeEEAAgB4QQACAHhBAAIAeEEAAgB4QQACAHhBAAIAeEEAAgAYH/4PeqgwZ+gZEnoAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# to plot the image after pre-processing\n",
    "plt.imshow(images[1000], cmap='gray')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "9fa21976-85fd-4eed-b079-a0107373f5ed",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Pickling the images and labels files\n",
    "with open(os.path.join(img_final,'images.p'),'wb') as f:\n",
    "    pickle.dump(images,f)\n",
    "\n",
    "with open(os.path.join(img_final, 'labels.p'), 'wb') as f:\n",
    "    pickle.dump(labels,f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cf64e348-8ee5-4a8f-bb79-120d3703da76",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "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": "3.12.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}