{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "from ipfml import processing, utils, metrics\n",
    "from PIL import Image\n",
    "from scipy import signal\n",
    "from skimage import color\n",
    "import scipy.stats as stats\n",
    "import seaborn as sns\n",
    "import cv2\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import os"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_folder = \"../fichiersSVD_light\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MSCN analysis on Synthesis Images "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Utils functions definition"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def compute_images_path(scene, prefix, indices):\n",
    "    images_path = []\n",
    "    for index in indices:\n",
    "        path = os.path.join(data_folder, os.path.join(scene, prefix + index + \".png\"))\n",
    "        print(path)\n",
    "        images_path.append(path)\n",
    "    return images_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_L_canal(img):\n",
    "    img_lab = metrics.get_LAB_L(img)\n",
    "    img_lab = np.asarray(img_lab, 'uint8')\n",
    "    \n",
    "    return Image.fromarray(img_lab)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_MSCN_canal(img):\n",
    "    img_mscn = processing.get_mscn_coefficients(img)\n",
    "    img_mscn = np.asarray(utils.normalize_2D_arr(img_mscn)*255, 'uint8')\n",
    "    \n",
    "    return Image.fromarray(img_mscn)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Scenes MSCN variance analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Cuisine01 scene "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "scene_name = \"Cuisine01\"\n",
    "prefix_name = \"cuisine01_\"\n",
    "image_indices = [\"00050\", \"00100\", \"00200\", \"00300\", \"00500\", \"00900\",\"01200\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "../fichiersSVD_light/Cuisine01/cuisine01_00050.png\n",
      "../fichiersSVD_light/Cuisine01/cuisine01_00100.png\n",
      "../fichiersSVD_light/Cuisine01/cuisine01_00200.png\n",
      "../fichiersSVD_light/Cuisine01/cuisine01_00300.png\n",
      "../fichiersSVD_light/Cuisine01/cuisine01_00500.png\n",
      "../fichiersSVD_light/Cuisine01/cuisine01_00900.png\n",
      "../fichiersSVD_light/Cuisine01/cuisine01_01200.png\n"
     ]
    }
   ],
   "source": [
    "images_path = compute_images_path(scene_name, prefix_name, image_indices)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [],
   "source": [
    "get_L_canal(processing.divide_in_blocks(Image.open(images_path[0]), (200, 200))[10]).save('tmp_images/cuisine01_zone10_00050_lab.png')\n",
    "get_L_canal(processing.divide_in_blocks(Image.open(images_path[5]), (200, 200))[10]).save('tmp_images/cuisine01_zone10_01200_lab.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "metadata": {},
   "outputs": [],
   "source": [
    "get_MSCN_canal(processing.divide_in_blocks(Image.open(images_path[0]), (200, 200))[10]).save('tmp_images/cuisine01_zone10_00050_mscn.png')\n",
    "get_MSCN_canal(processing.divide_in_blocks(Image.open(images_path[5]), (200, 200))[10]).save('tmp_images/cuisine01_zone10_01200_mscn.png')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {},
   "outputs": [],
   "source": [
    "processing.divide_in_blocks(Image.open(images_path[0]), (200, 200))[10].save('tmp_images/cuisine01_zone10_noisy.png')\n",
    "processing.divide_in_blocks(Image.open(images_path[5]), (200, 200))[10].save('tmp_images/cuisine01_zone10_ref.png')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "thesis-venv",
   "language": "python",
   "name": "thesis-venv"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}