Python script to extract text from bank slip in Thai language.

ocr-slip.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## dependencies\n",
    "\n",
    "```sh\n",
    "brew install tesseract --with-all-languages\n",
    "pip install pytesseract\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from PIL import Image\n",
    "import pytesseract\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def printTextOn(img_name):\n",
    "    img = Image.open(img_name)\n",
    "    img_to_str = pytesseract.image_to_string(img, lang='tha')\n",
    "    strip = re.sub(' +', ' ', img_to_str).split('\\n')\n",
    "    final = [x for x in strip if x is not ' ' and x is not '']\n",
    "    print(final)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "printTextOn('ktb1.jpg')"
   ]
  }
 ],
 "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}