add all L2 notebooks

udacity · Apr 26, 2018 · 416365b · 416365b
1 parent 916b072
commit 416365b
Show file tree

Hide file tree

Showing 6 changed files with 818 additions and 0 deletions.
diff --git a/2_Convolutional_Filters_Edge_Detection/2. Finding Edges and Custom Kernels.ipynb b/2_Convolutional_Filters_Edge_Detection/2. Finding Edges and Custom Kernels.ipynb
@@ -0,0 +1,138 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Creating a Filter, Edge Detection"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Import resources and display image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "import matplotlib.image as mpimg\n",
+    "\n",
+    "import cv2\n",
+    "import numpy as np\n",
+    "\n",
+    "%matplotlib inline\n",
+    "\n",
+    "# Read in the image\n",
+    "image = mpimg.imread('images/curved_lane.jpg')\n",
+    "\n",
+    "plt.imshow(image)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Convert the image to grayscale"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Convert to grayscale for filtering\n",
+    "gray = cv2.cvtColor(image, cv2.COLOR_RGB2GRAY)\n",
+    "\n",
+    "plt.imshow(gray, cmap='gray')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### TODO: Create a custom kernel\n",
+    "\n",
+    "Below, you've been given one common type of edge detection filter: a Sobel operator.\n",
+    "\n",
+    "The Sobel filter is very commonly used in edge detection and in finding patterns in intensity in an image. Applying a Sobel filter to an image is a way of **taking (an approximation) of the derivative of the image** in the x or y direction, separately. The operators look as follows.\n",
+    "\n",
+    "<img src=\"images/sobel_ops.png\" width=200 height=200>\n",
+    "\n",
+    "**It's up to you to create a Sobel x operator and apply it to the given image.**\n",
+    "\n",
+    "For a challenge, see if you can put the image through a series of filters: first one that blurs the image (takes an average of pixels), and then one that detects the edges."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create a custom kernel\n",
+    "\n",
+    "# 3x3 array for edge detection\n",
+    "sobel_y = np.array([[ -1, -2, -1], \n",
+    "                   [ 0, 0, 0], \n",
+    "                   [ 1, 2, 1]])\n",
+    "\n",
+    "## TODO: Create and apply a Sobel x operator\n",
+    "\n",
+    "\n",
+    "# Filter the image using filter2D, which has inputs: (grayscale image, bit-depth, kernel)  \n",
+    "filtered_image = cv2.filter2D(gray, -1, sobel_y)\n",
+    "\n",
+    "plt.imshow(filtered_image, cmap='gray')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test out other filters!\n",
+    "\n",
+    "You're encouraged to create other kinds of filters and apply them to see what happens! As an **optional exercise**, try the following:\n",
+    "* Create a filter with decimal value weights.\n",
+    "* Create a 5x5 filter\n",
+    "* Apply your filters to the other images in the `images` directory.\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "anaconda-cloud": {},
+  "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": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}
diff --git a/2_Convolutional_Filters_Edge_Detection/3. Gaussian Blur.ipynb b/2_Convolutional_Filters_Edge_Detection/3. Gaussian Blur.ipynb
@@ -0,0 +1,144 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Gaussian Blur, Medical Images"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Import resources and display image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import cv2\n",
+    "\n",
+    "%matplotlib inline\n",
+    "\n",
+    "# Read in the image\n",
+    "image = cv2.imread('images/brain_MR.jpg')\n",
+    "\n",
+    "# Make a copy of the image\n",
+    "image_copy = np.copy(image)\n",
+    "\n",
+    "# Change color to RGB (from BGR)\n",
+    "image_copy = cv2.cvtColor(image_copy, cv2.COLOR_BGR2RGB)\n",
+    "\n",
+    "plt.imshow(image_copy)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Gaussian blur the image"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Convert to grayscale for filtering\n",
+    "gray = cv2.cvtColor(image_copy, cv2.COLOR_RGB2GRAY)\n",
+    "\n",
+    "# Create a Gaussian blurred image\n",
+    "gray_blur = cv2.GaussianBlur(gray, (9, 9), 0)\n",
+    "\n",
+    "f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))\n",
+    "\n",
+    "ax1.set_title('original gray')\n",
+    "ax1.imshow(gray, cmap='gray')\n",
+    "\n",
+    "ax2.set_title('blurred image')\n",
+    "ax2.imshow(gray_blur, cmap='gray')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Test performance with a high-pass filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# High-pass filter \n",
+    "\n",
+    "# 3x3 sobel filters for edge detection\n",
+    "sobel_x = np.array([[ -1, 0, 1], \n",
+    "                   [ -2, 0, 2], \n",
+    "                   [ -1, 0, 1]])\n",
+    "\n",
+    "\n",
+    "sobel_y = np.array([[ -1, -2, -1], \n",
+    "                   [ 0, 0, 0], \n",
+    "                   [ 1, 2, 1]])\n",
+    "\n",
+    "\n",
+    "# Filter the orginal and blurred grayscale images using filter2D\n",
+    "filtered = cv2.filter2D(gray, -1, sobel_x)\n",
+    "\n",
+    "filtered_blurred = cv2.filter2D(gray_blur, -1, sobel_y)\n",
+    "f, (ax1, ax2) = plt.subplots(1, 2, figsize=(20,10))\n",
+    "\n",
+    "ax1.set_title('original gray')\n",
+    "ax1.imshow(filtered, cmap='gray')\n",
+    "\n",
+    "ax2.set_title('blurred image')\n",
+    "ax2.imshow(filtered_blurred, cmap='gray')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Create threshold that sets all the filtered pixels to white\n",
+    "# Above a certain threshold\n",
+    "\n",
+    "retval, binary_image = cv2.threshold(filtered_blurred, 50, 255, cv2.THRESH_BINARY)\n",
+    "\n",
+    "plt.imshow(binary_image, cmap='gray')\n"
+   ]
+  }
+ ],
+ "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": "3.6.3"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 1
+}