added 4 assignment

assignments/04_assignment.ipynb

@@ -0,0 +1,211 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "collapsed": true
+   },
+   "source": [
+    "# Image Processing SS 18 - Assignment - 04\n",
+    "\n",
+    "### Deadline is 16.5.2016 at 8:00 o'clock\n",
+    "\n",
+    "Please solve the assignments together with a partner.\n",
+    "I will run every notebook. Make sure the code runs through. Select `Kernel` -> `Restart & Run All` to test it.\n",
+    "Please strip the output from the cells, either select `Cell` -> `All Output` -> `Clear` or use the `nb_strip_output.py` script / git hook."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# display the plots inside the notebook\n",
+    "%matplotlib inline"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pylab\n",
+    "try:\n",
+    "    import urllib.request as urllib2\n",
+    "except ImportError:\n",
+    "    import urllib2\n",
+    "\n",
+    "import random\n",
+    "try:\n",
+    "    from StringIO import StringIO as BytesIO\n",
+    "except ImportError:\n",
+    "    from io import BytesIO\n",
+    "    \n",
+    "from PIL import Image\n",
+    "\n",
+    "pylab.rcParams['figure.figsize'] = (12, 12)   # This makes the plot bigger"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Exercise 1 - Qualify sharpness and noise - 5 Points\n",
+    "\n",
+    "Qualify the noise and sharpness in the images. Make a plot images, noise\n",
+    "\n",
+    "Please download sample picture from [here](http://www.imageprocessingplace.com/downloads_V3/root_downloads/image_databases/standard_test_images.zip)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Load the pictures here\n",
+    "sample_images = None"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def qualify_noise(img):\n",
+    "    \"\"\"Qualify the noise based on the std of a gaussian model.\n",
+    "       You may find a window that is contant in the images.\n",
+    "    \"\"\"\n",
+    "    # your code here\n",
+    "    return random.randint(0, 10)\n",
+    "\n",
+    "plt.bar(range(len(sample_images)), [qualify_noise(i) for i in sample_images])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def qualify_sharpness(img):\n",
+    "    \"\"\"Qualify the sharpness based on the average pixel differences.\"\"\"\n",
+    "    # your code here\n",
+    "    return random.randint(0, 10)\n",
+    "plt.bar(range(len(sample_images)), [qualify_sharpness(i) for i in sample_images])"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Does the result match the expectations? If not what processing step can be done?/"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Exercise 2 - SSIM JPEG Compression - 5 Points"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "def jpeg_enocde(img, quality):\n",
+    "    pil_img = Image.fromarray(img)\n",
+    "    buffer = BytesIO()\n",
+    "    im1.save(buffer, \"JPEG\", quality=quality)\n",
+    "    return buffer\n",
+    "\n",
+    "def jpeg_decode(buffer):\n",
+    "    img = Image.open(buffer)\n",
+    "    return np.array(img)\n",
+    "\n",
+    "def jpeg_quality_filter(img, quality):\n",
+    "    as_jpeg = jpeg_enocde(img, quality)\n",
+    "    return jpeg_decode(as_jpeg)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "len(images_for_jpeg)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "images10 = [jpeg_quality_filter(img, 10) for img in sample_images]\n",
+    "images50 = [jpeg_quality_filter(img, 10) for img in sample_images]\n",
+    "images80 = [jpeg_quality_filter(img, 10) for img in sample_images]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def ssim(img, filtered_img):\n",
+    "    \"\"\"The SSIM similarity measure. Use the parameters from the paper \n",
+    "    as on the second to last slide from the lecture\"\"\"\n",
+    "    # your code\n",
+    "    return random.randint(0, 10)\n",
+    "\n",
+    "for i, img in enumerate(images_for_jpeg):\n",
+    "    print(i)\n",
+    "    compressed_images = [images10[i], images50[i], images80[i]]\n",
+    "    plt.bar(range(len(compressed_images)),\n",
+    "             [ssim(img, comp) for comp in compressed_images])\n",
+    "    plt.show()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "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": "3.5.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}