{
 "metadata": {
  "name": "",
  "signature": "sha256:a479b8ae3be7bcbbe4e766c1d91526548e38aa69daade24b2b31aa72bd0f1f05"
 },
 "nbformat": 3,
 "nbformat_minor": 0,
 "worksheets": [
  {
   "cells": [
    {
     "cell_type": "markdown",
     "metadata": [],
     "source": [
      "> This is one of the 100 recipes of the [IPython Cookbook](http://ipython-books.github.io/), the definitive guide to high-performance scientific computing and data science in Python.\n"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "# 11.4. Finding points of interest in an image"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "You need to download the *Child* dataset on the book's website. (http://ipython-books.github.io)"
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "1. Let's import the packages."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "import numpy as np\n",
      "import matplotlib.pyplot as plt\n",
      "import skimage\n",
      "import skimage.feature as sf\n",
      "import matplotlib as mpl\n",
      "%matplotlib inline\n"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "2. We create a function to display a colored or grayscale image."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "def show(img, cmap=None):\n",
      "    cmap = cmap or plt.cm.gray\n",
      "    plt.figure(figsize=(4,2));\n",
      "    plt.imshow(img, cmap=cmap);\n",
      "    plt.axis('off');"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "3. We load an image."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "img = plt.imread('data/pic2.jpg')"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "show(img)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "4. We find salient points in the image with the Harris corner method. The first step consists in computing the **Harris corner measure response image** with the `corner_harris` function (we will explain this measure in *How it works...*)."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "corners = sf.corner_harris(img[:,:,0])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "show(corners)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "We see that the patterns in the child's coat are particularly well detected by this algorithm."
     ]
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "5. The next step consists in detecting corners from this measure image, using the `corner_peaks` function."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "peaks = sf.corner_peaks(corners)"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "show(img)\n",
      "plt.plot(peaks[:,1], peaks[:,0], 'or', ms=4);"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "6. Finally, we create a box around the corner points to define our region of interest."
     ]
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "ymin, xmin = peaks.min(axis=0)\n",
      "ymax, xmax = peaks.max(axis=0)\n",
      "w, h = xmax-xmin, ymax-ymin"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "k = .25\n",
      "xmin -= k*w\n",
      "xmax += k*w\n",
      "ymin -= k*h\n",
      "ymax += k*h"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "code",
     "collapsed": false,
     "input": [
      "show(img[ymin:ymax,xmin:xmax])"
     ],
     "language": "python",
     "metadata": {},
     "outputs": []
    },
    {
     "cell_type": "markdown",
     "metadata": {},
     "source": [
      "> You'll find all the explanations, figures, references, and much more in the book (to be released later this summer).\n",
      "\n",
      "> [IPython Cookbook](http://ipython-books.github.io/), by [Cyrille Rossant](http://cyrille.rossant.net), Packt Publishing, 2014 (500 pages)."
     ]
    }
   ],
   "metadata": {}
  }
 ]
}