ocr_sandbox.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Try OCR: to extract text from creative\n",
    "- [tl;dr](#Conclusion)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import pyocr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "data_dir = '../dataset/understanding_ads/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "ls: ../dataset/understanding_ads/: No such file or directory\r\n"
     ]
    }
   ],
   "source": [
    "!ls $data_dir"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "from io import BytesIO\n",
    "from PIL import Image, ImageDraw\n",
    "from urllib.request import urlopen"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## From Color Image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {