Skip to content

I
image-compression
Commit ca65ae7f authored by Kelly Chang's avatar Kelly Chang
Browse files
Options

kelly push

parent fcbea69e
Hide whitespace changes
Inline Side-by-side
Showing with 387 additions and 0 deletions
Encoding_decoding.ipynb 0 → 100644
View file @ ca65ae7f
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "14f74f21",
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"from matplotlib import pyplot as plt\n",
"from itertools import product\n",
"import os\n",
"import sys\n",
"from PIL import Image\n",
"from scipy.optimize import minimize,linprog\n",
"import time\n",
"import seaborn as sns\n",
"from sklearn.neighbors import KernelDensity\n",
"import pandas as pd\n",
"from collections import Counter\n",
"import time"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "c16af61f",
"metadata": {},
"outputs": [],
"source": [
"def file_extractor(dirname=\"images\"):\n",
" files = os.listdir(dirname)\n",
" scenes = []\n",
" for file in files:\n",
" scenes.append(os.path.join(dirname, file))\n",
" return scenes\n",
"\n",
"def image_extractor(scenes):\n",
" image_folder = []\n",
" for scene in scenes:\n",
" files = os.listdir(scene)\n",
" for file in files:\n",
" image_folder.append(os.path.join(scene, file))\n",
" images = []\n",
" for folder in image_folder:\n",
" ims = os.listdir(folder)\n",
" for im in ims:\n",
" if im[-4:] == \".jp4\" or im[-7:] == \"_6.tiff\":\n",
" continue\n",
" else:\n",
" images.append(os.path.join(folder, im))\n",
" return images #returns a list of file paths to .tiff files in the specified directory given in file_extractor\n",
"\n",
"def im_distribution(images, num):\n",
" \"\"\"\n",
" Function that extracts tiff files from specific cameras and returns a list of all\n",
" the tiff files corresponding to that camera. i.e. all pictures labeled \"_7.tiff\" or otherwise\n",
" specified camera numbers.\n",
" \n",
" Parameters:\n",
" images (list): list of all tiff files, regardless of classification. This is NOT a list of directories but\n",
" of specific tiff files that can be opened right away. This is the list that we iterate through and \n",
" divide.\n",
" \n",
" num (str): a string designation for the camera number that we want to extract i.e. \"14\" for double digits\n",
" of \"_1\" for single digits.\n",
" \n",
" Returns:\n",
" tiff (list): A list of tiff files that have the specified designation from num. They are the files extracted\n",
" from the 'images' list that correspond to the given num.\n",
" \"\"\"\n",
" tiff = []\n",
" for im in images:\n",
" if im[-7:-5] == num:\n",
" tiff.append(im)\n",
" return tiff"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "aceba613",
"metadata": {},
"outputs": [],
"source": [
"def plot_hist(tiff_list):\n",
" \"\"\"\n",
" This function is the leftovers from the first attempt to plot histograms.\n",
" As it stands it needs some work in order to function again. We will\n",
" fix this later. 1/25/22\n",
" \"\"\"\n",
" \n",
" image = tiff_list\n",
" image = Image.open(image) #Open the image and read it as an Image object\n",
" image = np.array(image)[1:,:] #Convert to an array, leaving out the first row because the first row is just housekeeping data\n",
" image = image.astype(int)\n",
" A = np.array([[3,0,-1],[0,3,3],[1,-3,-4]]) # the matrix for system of equation\n",
" z0 = image[0:-2,0:-2] # get all the first pixel for the entire image\n",
" z1 = image[0:-2,1:-1] # get all the second pixel for the entire image\n",
" z2 = image[0:-2,2::] # get all the third pixel for the entire image\n",
" z3 = image[1:-1,0:-2] # get all the forth pixel for the entire image\n",
" # calculate the out put of the system of equation\n",
" y0 = np.ravel(-z0+z2-z3)\n",
" y1 = np.ravel(z0+z1+z2)\n",
" y2 = np.ravel(-z0-z1-z2-z3)\n",
" y = np.vstack((y0,y1,y2))\n",
" # use numpy solver to solve the system of equations all at once\n",
" predict = np.floor(np.linalg.solve(A,y)[-1])\n",
" # flatten the neighbor pixlels and stack them together\n",
" z0 = np.ravel(z0)\n",
" z1 = np.ravel(z1)\n",
" z2 = np.ravel(z2)\n",
" z3 = np.ravel(z3)\n",
" neighbor = np.vstack((z0,z1,z2,z3)).T\n",
" # calculate the difference\n",
" diff = np.max(neighbor,axis = 1) - np.min(neighbor, axis=1)\n",
" \n",
" # flatten the image to a vector\n",
" image = np.ravel(image[1:-1,1:-1])\n",
" error = image-predict\n",
" \n",
" return image, predict, diff, error, A"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "6b965751",
"metadata": {},
"outputs": [],
"source": [
"class NodeTree(object):\n",
" def __init__(self, left=None, right=None):\n",
" self.left = left\n",
" self.right = right\n",
"\n",
" def children(self):\n",
" return self.left, self.right\n",
"\n",
" def __str__(self):\n",
" return self.left, self.right\n",
"\n",
"\n",
"def huffman_code_tree(node, binString=''):\n",
" '''\n",
" Function to find Huffman Code\n",
" '''\n",
" if type(node) is str:\n",
" return {node: binString}\n",
" (l, r) = node.children()\n",
" d = dict()\n",
" d.update(huffman_code_tree(l, binString + '0'))\n",
" d.update(huffman_code_tree(r, binString + '1'))\n",
" return d\n",
"\n",
"\n",
"def make_tree(nodes):\n",
" '''\n",
" Function to make tree\n",
" :param nodes: Nodes\n",
" :return: Root of the tree\n",
" '''\n",
" while len(nodes) > 1:\n",
" (key1, c1) = nodes[-1]\n",
" (key2, c2) = nodes[-2]\n",
" nodes = nodes[:-2]\n",
" node = NodeTree(key1, key2)\n",
" nodes.append((node, c1 + c2))\n",
" nodes = sorted(nodes, key=lambda x: x[1], reverse=True)\n",
" return nodes[0][0]"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "b7561883",
"metadata": {},
"outputs": [],
"source": [
"def huffman(image):\n",
" origin, predict, diff, error, A = plot_hist(image)\n",
" \n",
" image = Image.open(image)\n",
" image = np.array(image)[1:,:] #Convert to an array, leaving out the first row because the first row is just housekeeping data\n",
" image = image.astype(int)\n",
" \n",
" boundary = np.hstack((image[0,:],image[-1,:],image[1:-1,0],image[1:-1,-1]))\n",
" boundary = boundary - image[0,0]\n",
" boundary[0] = image[0,0]\n",
"\n",
" string = [str(i) for i in boundary]\n",
" freq = dict(Counter(string))\n",
" freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)\n",
" node = make_tree(freq)\n",
" encode1 = huffman_code_tree(node)\n",
" \n",
" \n",
" mask = diff <= 25\n",
" string = [str(i) for i in error[mask].astype(int)]\n",
" freq = dict(Counter(string))\n",
" freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)\n",
" node = make_tree(freq)\n",
" encode2 = huffman_code_tree(node)\n",
"\n",
" \n",
" mask = diff > 25\n",
" new_error = error[mask]\n",
" mask2 = diff[mask] <= 40\n",
" string = [str(i) for i in new_error[mask2].astype(int)]\n",
" freq = dict(Counter(string))\n",
" freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)\n",
" node = make_tree(freq)\n",
" encode3 = huffman_code_tree(node)\n",
" \n",
"\n",
" mask = diff > 40\n",
" new_error = error[mask]\n",
" mask2 = diff[mask] <= 70\n",
" string = [str(i) for i in new_error[mask2].astype(int)]\n",
" freq = dict(Counter(string))\n",
" freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)\n",
" node = make_tree(freq)\n",
" encode4 = huffman_code_tree(node)\n",
" \n",
" \n",
" mask = diff > 70\n",
" string = [str(i) for i in error[mask].astype(int)]\n",
" freq = dict(Counter(string))\n",
" freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)\n",
" node = make_tree(freq)\n",
" encode5 = huffman_code_tree(node)\n",
"\n",
"\n",
" new_error = np.copy(image)\n",
" new_error[1:-1,1:-1] = np.reshape(error,(510, 638))\n",
" keep = new_error[0,0]\n",
" new_error[0,:] = new_error[0,:] - keep\n",
" new_error[-1,:] = new_error[-1,:] - keep\n",
" new_error[1:-1,0] = new_error[1:-1,0] - keep\n",
" new_error[1:-1,-1] = new_error[1:-1,-1] - keep\n",
" new_error[0,0] = keep\n",
" \n",
" \n",
" #new_error = np.ravel(new_error)\n",
" \n",
" bins = [25,40,70]\n",
" \n",
" # return the huffman dictionary\n",
" return encode1, encode2, encode3, encode4, encode5, np.ravel(image), error, new_error, diff, boundary, bins\n",
" \n",
"scenes = file_extractor()\n",
"images = image_extractor(scenes)\n",
"encode1, encode2, encode3, encode4, encode5, image, error, new_error, diff, boundary, bins = huffman(images[0])"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "2eb774d2",
"metadata": {},
"outputs": [],
"source": [
"def encoder(error, list_dic, diff, bound, bins):\n",
" encoded = np.copy(error).astype(int).astype(str).astype(object)\n",
" \n",
" diff = np.reshape(diff,(510,638))\n",
" \n",
" for i in range(encoded.shape[0]):\n",
" for j in range(encoded.shape[1]):\n",
" if i == 0 or i == encoded.shape[0]-1 or j == 0 or j == encoded.shape[1]-1:\n",
" encoded[i][j] = list_dic[0][encoded[i][j]]\n",
" elif diff[i-1][j-1] <= bins[0]:\n",
" encoded[i][j] = list_dic[1][encoded[i][j]]\n",
" elif diff[i-1][j-1] <= bins[1] and diff[i-1][j-1] > bins[0]:\n",
" encoded[i][j] = list_dic[2][encoded[i][j]]\n",
" elif diff[i-1][j-1] <= bins[2] and diff[i-1][j-1] > bins[1]:\n",
" encoded[i][j] = list_dic[3][encoded[i][j]]\n",
" else: \n",
" encoded[i][j] = list_dic[4][encoded[i][j]]\n",
"\n",
" \n",
" return encoded"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "8eeb40d0",
"metadata": {},
"outputs": [],
"source": [
"def decoder(A, encoded_matrix, encoding_dict):\n",
" \"\"\"\n",
" Function that accecpts the prediction matrix A for the linear system,\n",
" the encoded matrix of error values, and the encoding dicitonary.\n",
" \"\"\"\n",
" the_keys = list(encode_dict.keys())\n",
" the_values = list(encode_dict.values())\n",
" error_matrix = encoded_matrix.copy()\n",
" \n",
" for i in range(error_matrix.shape[0]):\n",
" for j in range(error_matrix.shape[1]):\n",
" if i == 0 and j == 0:\n",
" error_matrix[i][j] = int(the_keys[the_values.index(error_matrix[i,j])])\n",
" \n",
" elif i == 0 or i == error_matrix.shape[0]-1 or j == 0 or j == error_matrix.shape[1]-1:\n",
" error_matrix[i][j] = int(the_keys[the_values.index(error_matrix[i,j])]) + error_matrix[0][0]\n",
" else:\n",
" \"\"\"z0, z1, z2, z3 = error_matrix[i-1][j-1], error_matrix[i-1][j], \\\n",
" error_matrix[i-1][j+1], error_matrix[i][j-1]\n",
" y = np.vstack((-z0+z2-z3, z0+z1+z2, -z0-z1-z2-z3))\"\"\"\n",
" \n",
" error_matrix[i][j] = int(the_keys[the_values.index(error_matrix[i,j])])\n",
" \n",
" return error_matrix.astype(int)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "3e0e9742",
"metadata": {},
"outputs": [],
"source": [
"encode1, encode2, encode3, encode4, encode5, image, error, new_error, diff, bound, bins = huffman(images[0])\n",
"encoded_matrix = encoder(np.reshape(new_error,(512,640)), [encode1, encode2, encode3, encode4, encode5], diff, bound, bins)\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "e6ea4f99",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[['01100010001' '11000110' '100101010' ... '101110011' '00010100'\n",
" '1111000100']\n",
" ['10011100' '100001' '111000' ... '10111011' '00111' '1111001101']\n",
" ['10101111' '100100' '100000' ... '111100' '111000' '00010100']\n",
" ...\n",
" ['110001000' '100001' '111011' ... '1010010' '100000' '10011000']\n",
" ['0100011101' '111010' '00110' ... '1000101' '1100100' '10011010']\n",
" ['00100010' '110111101' '110110100' ... '00010010' '10100000'\n",
" '110110101']]\n"
]
}
],
"source": [
"print(encoded_matrix)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0c07a23e",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.9.1"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment