Created
July 1, 2020 22:37
-
-
Save tuffacton/f1c4005e56e13460370db0083c6ec70c to your computer and use it in GitHub Desktop.
Revisions
-
tuffacton revised this gist
Jul 1, 2020 . 1 changed file with 12 additions and 1 deletion.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -6,14 +6,25 @@ "name": "hwmk4", "provenance": [], "collapsed_sections": [], "authorship_tag": "ABX9TyNw4Jmg6kd+pTlN9PEtQ6LP", "include_colab_link": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "<a href=\"https://colab.research.google.com/gist/tuffacton/f1c4005e56e13460370db0083c6ec70c/hwmk4.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>" ] }, { "cell_type": "code", "metadata": { -
Jul 1, 2020 .There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,405 @@ { "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "hwmk4", "provenance": [], "collapsed_sections": [], "authorship_tag": "ABX9TyNw4Jmg6kd+pTlN9PEtQ6LP" }, "kernelspec": { "name": "python3", "display_name": "Python 3" } }, "cells": [ { "cell_type": "code", "metadata": { "id": "GwoxGCt04nbE", "colab_type": "code", "colab": {} }, "source": [ "import numpy as np\n", "import cv2\n", "import time\n", "import scipy.ndimage as ndimg\n", "from sklearn.cluster import KMeans\n", "import matplotlib.pyplot as plt\n", "from google.colab.patches import cv2_imshow\n", "from IPython.display import Image\n", "%matplotlib inline" ], "execution_count": 60, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "8lDvdGDMiHmT", "colab_type": "code", "colab": {} }, "source": [ "NROT = 6\n", "NPER = 8\n", "NFILT = NROT*NPER \n", "FILTSIZE = 35\n", "NCLUSTERS = 4\n", "TEXELSIZE = 4\n", "doMakeTexels = True" ], "execution_count": 2, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "r-oFJyHeiTzP", "colab_type": "code", "colab": {} }, "source": [ "# Source from this code as permitted in the homework directions:\n", "# https://github.com/tonyjo/LM_filter_bank_python/blob/master/lm.py\n", "\n", "### LM Helper Functions ###\n", "\n", "# First-Order Gaussian Definition\n", "def gaussian1d(sigma, mean, x, ord):\n", " x = np.array(x)\n", " x_ = x - mean\n", " var = sigma**2\n", "\n", " # Gaussian Function\n", " g1 = (1/np.sqrt(2*np.pi*var))*(np.exp((-1*x_*x_)/(2*var)))\n", " \n", " if ord == 0:\n", " g = g1\n", " return g\n", " elif ord == 1:\n", " g = -g1*((x_)/(var))\n", " return g\n", " else:\n", " g = g1*(((x_*x_) - var)/(var**2))\n", " return g\n", "\n", "# Second-Order Gaussian Definition\n", "def gaussian2d(sup, scales):\n", " var = scales * scales\n", " shape = (sup,sup)\n", " n,m = [(i - 1)/2 for i in shape]\n", " x,y = np.ogrid[-m:m+1,-n:n+1]\n", " g = (1/np.sqrt(2*np.pi*var))*np.exp( -(x*x + y*y) / (2*var) )\n", " return g\n", "\n", "# Gaussian and Laplacian Logarithmic Definition\n", "def log2d(sup, scales):\n", " var = scales * scales\n", " shape = (sup,sup)\n", " n,m = [(i - 1)/2 for i in shape]\n", " x,y = np.ogrid[-m:m+1,-n:n+1]\n", " g = (1/np.sqrt(2*np.pi*var))*np.exp( -(x*x + y*y) / (2*var) )\n", " h = g*((x*x + y*y) - var)/(var**2)\n", " return h\n", "\n", "# Make a singular filter\n", "def makefilter(scale, phasex, phasey, pts, sup):\n", "\n", " gx = gaussian1d(3*scale, 0, pts[0,...], phasex)\n", " gy = gaussian1d(scale, 0, pts[1,...], phasey)\n", "\n", " image = gx*gy\n", "\n", " image = np.reshape(image,(sup,sup))\n", " return image\n", "\n", "# This function will compute and return the Leung-Malik filters\n", "# The filters are in a 3D array of floats, F(FILTSIZE, FILTSIZE, NFILT)\n", "def makeLMfilters():\n", " sup = 49\n", " scalex = np.sqrt(2) * np.array([1,2,3])\n", " norient = 6\n", " nrotinv = 12\n", "\n", " nbar = len(scalex)*norient\n", " nedge = len(scalex)*norient\n", " nf = nbar+nedge+nrotinv\n", " resF = np.zeros([sup,sup,nf])\n", " hsup = (sup - 1)/2\n", "\n", " x = [np.arange(-hsup,hsup+1)]\n", " y = [np.arange(-hsup,hsup+1)]\n", "\n", " [x,y] = np.meshgrid(x,y)\n", "\n", " orgpts = [x.flatten(), y.flatten()]\n", " orgpts = np.array(orgpts)\n", " \n", " count = 0\n", " for scale in range(len(scalex)):\n", " for orient in range(norient):\n", " angle = (np.pi * orient)/norient\n", " c = np.cos(angle)\n", " s = np.sin(angle)\n", " rotpts = [[c+0,-s+0],[s+0,c+0]]\n", " rotpts = np.array(rotpts)\n", " rotpts = np.dot(rotpts,orgpts)\n", " resF[:,:,count] = makefilter(scalex[scale], 0, 1, rotpts, sup)\n", " resF[:,:,count+nedge] = makefilter(scalex[scale], 0, 2, rotpts, sup)\n", " count = count + 1\n", " \n", " count = nbar+nedge\n", " scales = np.sqrt(2) * np.array([1,2,3,4])\n", "\n", " for i in range(len(scales)):\n", " resF[:,:,count] = gaussian2d(sup, scales[i])\n", " count = count + 1\n", " \n", " for i in range(len(scales)):\n", " resF[:,:,count] = log2d(sup, scales[i])\n", " count = count + 1\n", " \n", " for i in range(len(scales)):\n", " resF[:,:,count] = log2d(sup, 3*scales[i])\n", " count = count + 1\n", " \n", " return resF" ], "execution_count": 3, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "lv4AE2VSlT9q", "colab_type": "code", "colab": {} }, "source": [ "def saveFilters(img):\n", " (height, width, depth) = img.shape\n", " count = 0\n", " for row in range(NPER):\n", " for col in range(NROT):\n", " tempImg = img[:, :, count]\n", " filename = \"Filters\\\\LM_\" + str(row) + \"_\" + str(col)\n", " normedFilter = normImg(tempImg)\n", " saveImage(normedFilter, filename)\n", " count = count + 1\n", " return" ], "execution_count": 4, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "x79t47uTlgd-", "colab_type": "code", "colab": {} }, "source": [ "# This function will apply the filter bank in the 3D array filt to\n", "# the inputImg; the result is an array of results res(height, width, NFILT)\n", "def applyLMfilters(inputImg, filt):\n", " img = inputImg.astype(float)\n", " img_y = img.shape[0]\n", " img_x = img.shape[1]\n", " num_filters = filt.shape[2]\n", " res = np.zeros([img_y, img_x, num_filters])\n", " \n", " for i in range(filt.shape[2]):\n", " r = ndimg.convolve(img, filt[:,:,i])\n", " res[:,:,i] = r\n", " return res" ], "execution_count": 5, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "b2DvTTbVmUgY", "colab_type": "code", "colab": {} }, "source": [ "def normImg(img):\n", " tempImg = np.zeros_like(img)\n", " tempImg = (cv2.normalize(img, tempImg, 0.0, 127.0, cv2.NORM_MINMAX))\n", " res = (tempImg + 128.0).astype(np.uint8)\n", " return res" ], "execution_count": 6, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "tbT_309gmiJY", "colab_type": "code", "colab": {} }, "source": [ "def makeMosaic(img):\n", " (height, width, depth) = img.shape\n", " res = np.zeros((height*8, width*6), np.float64)\n", " count = 0\n", " for row in range(8):\n", " for col in range(6):\n", " res[row*height:(row+1)*height, col*width:(col+1)*width] = \\\n", " normImg(img[:,:,count])\n", " count = count + 1\n", " return res" ], "execution_count": 7, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "1-PpJ54FnfwC", "colab_type": "code", "colab": {} }, "source": [ "def saveImage(img, name):\n", " cv2.imwrite(pathName + name + \".png\", img)\n", " return" ], "execution_count": 8, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "l4KC6QipnnZ8", "colab_type": "code", "colab": {} }, "source": [ "# This function will take a 3D array of filter bank responses and form texels\n", "# by combining the feature vectors in nonoverlapping squares of size sz\n", "# the result newR is an array of floats the same size as R, but within\n", "# texels all feature vectors are identical\n", "def formTexels(R, sz):\n", " (ROWS, COLS, PLANES) = R.shape\n", " newR = np.int(np.ceil(ROWS/sz))\n", " newC = np.int(np.ceil(COLS/sz))\n", " res = np.zeros((newR, newC, PLANES), dtype=np.float64)\n", " for row in range(0, newR):\n", " for col in range(0, newC, sz):\n", " res[row:row+sz, col:col+sz,:] = \\\n", " np.median(R[(sz*row):(sz*row)+sz, (sz*col):(sz*col)+sz, :], (0,1))\n", " return res" ], "execution_count": 9, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "byVW4-UzoUvu", "colab_type": "code", "colab": {} }, "source": [ "# This function will take an image-sized collection of filter bank responses\n", "# and use the KMeans algorithm to find the best segments\n", "# it returns a pseucolor rendition of the original image, where each color\n", "# corresponds to a separate cluster (a separate type of texture)\n", "\n", "## Influenced heavily by Dr. Creed Jone's python implementation on \n", "## slide 20 of ECE5554 Lecture 8a - Segmentation by Clustering\n", "def segmentKMeans(R, nclus):\n", " # reshape the image to be a list of pixels\n", " vecs = R.reshape((R.shape[0]*R.shape[1], NFILT))\n", " \n", " # Define and fit our K-Means Model\n", " clus = KMeans(nclus)\n", " clus.fit(vecs)\n", "\n", " newfeatures = np.uint8(clus.predict(vecs))\n", " newAugmentedImage = newfeatures.reshape((R.shape[0], R.shape[1]))\n", " pcolor = cv2.applyColorMap(cv2.equalizeHist(newAugmentedImage), cv2.COLORMAP_RAINBOW)\n", " return pcolor" ], "execution_count": 66, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "awcl1Juyo1EM", "colab_type": "code", "colab": { "base_uri": "https://localhost:8080/", "height": 51 }, "outputId": "d69e0f9a-22a9-46fa-f13a-cb256e7a87d1" }, "source": [ "####### CODE EXECUTION #######\n", "# Pull Images from Github\n", "!wget \"https://github.com/tuffacton/ece5554/raw/master/hmwk4/aerial-houses.png\" -O aerial-houses.png -q\n", "!wget \"https://github.com/tuffacton/ece5554/raw/master/hmwk4/texture.png\" -O texture.png -q\n", "!wget \"https://github.com/tuffacton/ece5554/raw/master/hmwk4/selfie.png\" -O selfie.png -q\n", "\n", "pathName = \"/content/\"\n", "#fileName = \"aerial-houses.png\"\n", "fileName = \"texture.png\"\n", "#fileName = \"selfie.png\"\n", "\n", "currTime = time.time()\n", "# Call the make filter function\n", "F = makeLMfilters()\n", "saveFilters(F)\n", "saveImage(makeMosaic(F), \"allFilters\")\n", "\n", "# load an image\n", "inputImage = cv2.cvtColor(cv2.imread(pathName+fileName), cv2.COLOR_BGR2GRAY)\n", "\n", "# find filter responses\n", "rawR = applyLMfilters(inputImage, F)\n", "R = formTexels(rawR, TEXELSIZE)\n", "\n", "filterTime = time.time() - currTime\n", "print(\"Filter time = \", filterTime)\n", "\n", "# try segmenting\n", "pcolor = segmentKMeans(R, NCLUSTERS)\n", "saveImage(pcolor, fileName+\"_Seg_\"+str(NCLUSTERS))\n", "\n", "elapsedTime = time.time() - currTime\n", "print(\"Completed; elapsed time = \", elapsedTime)" ], "execution_count": 64, "outputs": [ { "output_type": "stream", "text": [ "Filter time = 38.52336096763611\n", "Completed; elapsed time = 38.84861421585083\n" ], "name": "stdout" } ] }, { "cell_type": "code", "metadata": { "id": "p8hDXtU1ofAu", "colab_type": "code", "colab": {} }, "source": [ "" ], "execution_count": null, "outputs": [] } ] }