Skip to content

I
image-compression
Commit b9905013 authored by Kelly Chang's avatar Kelly Chang
Browse files
Options

kelly push

parent 20af6366
Hide whitespace changes
Inline Side-by-side
Showing with 827 additions and 4 deletions
.DS_Store
View file @ b9905013
No preview for this file type
Compression_Rate_Kelly.ipynb 0 → 100644
View file @ b9905013
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "8868bc30",
"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": "76317b02",
"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": "be1ff8a1",
"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",
" predict = np.round(np.round((np.linalg.solve(A,y)[-1]),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": "8483903e",
"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": "markdown",
"id": "c7104fbf",
"metadata": {},
"source": [
"### Huffman without dividing into bins"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "a43f3f1c",
"metadata": {},
"outputs": [],
"source": [
"scenes = file_extractor()\n",
"images = image_extractor(scenes)\n",
"def huffman_nb(image):\n",
" origin, predict, diff, error, A = plot_hist(image)\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",
" 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",
" new_error = np.ravel(new_error)\n",
" \n",
" \n",
" \n",
" #ab_error = np.abs(new_error)\n",
" #string = [str(i) for i in ab_error]\n",
" string = [str(i) for i in new_error.astype(int)]\n",
" freq = dict(Counter(string))\n",
" \n",
" freq = sorted(freq.items(), key=lambda x: x[1], reverse=True)\n",
" node = make_tree(freq)\n",
" encoding = huffman_code_tree(node)\n",
" #encoded = [\"1\"+encoding[str(-i)] if i < 0 else \"0\"+encoding[str(i)] for i in error]\n",
" \n",
" # return the huffman dictionary\n",
" return encoding, new_error, image.reshape(-1)\n",
" \n",
" \n",
"def compress_rate_nb(image, error, encoding):\n",
" #original = original.reshape(-1)\n",
" #error = error.reshape(-1)\n",
" o_len = 0\n",
" c_len = 0\n",
" for i in range(0, len(original)):\n",
" o_len += len(bin(original[i])[2:])\n",
" c_len += len(encoding[str(int(error[i]))])\n",
"\n",
" \n",
" return c_len/o_len\n",
"\n"
]
},
{
"cell_type": "markdown",
"id": "eac2f456",
"metadata": {},
"source": [
"### Huffman with dividing into non-uniform bins"
]
},
{
"cell_type": "markdown",
"id": "3a3f06a5",
"metadata": {},
"source": [
"### Huffman with dividing into uniform bins"
]
},
{
"cell_type": "code",
"execution_count": 57,
"id": "14075c94",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"325380\n",
"325380\n"
]
},
{
"data": {
"text/plain": [
"0.4432273356119792"
]
},
"execution_count": 57,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def huffman_u(image):\n",
" origin, predict, diff, error, A = plot_hist(image)\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",
" print(len(diff))\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 <= 100\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 > 100\n",
" #new_error = error[mask]\n",
" #mask2 = diff[mask] <= 200\n",
" #string = [str(i) for i in new_error[mask2].astype(int)]\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",
" encode3 = huffman_code_tree(node)\n",
" \n",
"\n",
" '''mask = diff > 200\n",
" new_error = error[mask]\n",
" mask2 = diff[mask] <= 300\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 > 300\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",
" \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",
" new_error = np.ravel(new_error)\n",
" \n",
" # return the huffman dictionary\n",
" #return encode1, encode2, encode3, encode4, encode5, np.ravel(image), error, diff, boundary\n",
" print(len(diff))\n",
" return encode1, encode2, encode3, np.ravel(image), error, diff, boundary\n",
"\n",
"#def compress_rate_u(image, error, diff, bound, encode1, encode2, encode3, encode4, encode5):\n",
"def compress_rate_u(image, error, diff, bound, encode1, encode2, encode3):\n",
" #original = original.reshape(-1)\n",
" #error = error.reshape(-1)\n",
" o_len = 0\n",
" c_len = 0\n",
" im = np.reshape(image,(512, 640))\n",
" real_b = np.hstack((im[0,:],im[-1,:],im[1:-1,0],im[1:-1,-1]))\n",
" original = im[1:-1,1:-1].reshape(-1)\n",
"\n",
" for i in range(0,len(bound)):\n",
" o_len += len(bin(real_b[i])[2:])\n",
" c_len += len(encode1[str(bound[i])])\n",
" \n",
" for i in range(0, len(original)):\n",
" o_len += len(bin(original[i])[2:])\n",
" if diff[i] <= 100:\n",
" c_len += len(encode2[str(int(error[i]))])\n",
" \n",
" if diff[i] > 100:\n",
" c_len += len(encode3[str(int(error[i]))])\n",
"\n",
" '''if diff[i] <= 200 and diff[i] > 100:\n",
" c_len += len(encode3[str(int(error[i]))])'''\n",
" \n",
" '''if diff[i] <= 300 and diff[i] > 200:\n",
" c_len += len(encode4[str(int(error[i]))])\n",
" \n",
" if diff[i] > 300:\n",
" c_len += len(encode5[str(int(error[i]))])'''\n",
" \n",
" return c_len/o_len\n",
"scenes = file_extractor()\n",
"images = image_extractor(scenes)\n",
"encode1, encode2, encode3, image, error, diff, boundary = huffman_u(images[0])\n",
"compress_rate_u(image, error, diff, boundary, encode1, encode2, encode3)\n"
]
},
{
"cell_type": "code",
"execution_count": 55,
"id": "207b0bd2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"325380\n"
]
},
{
"data": {
"text/plain": [
"0.44205322265625"
]
},
"execution_count": 55,
"metadata": {},
"output_type": "execute_result"
}
],
"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, predict\n",
" \n",
"\n",
"\n",
"def compress_rate(image, error, diff, bound, encode1, encode2, encode3, encode4, encode5):\n",
" #original = original.reshape(-1)\n",
" #error = error.reshape(-1)\n",
"\n",
" o_len = 0\n",
" c_len = 0\n",
" im = np.reshape(image,(512, 640))\n",
" real_b = np.hstack((im[0,:],im[-1,:],im[1:-1,0],im[1:-1,-1]))\n",
" original = im[1:-1,1:-1].reshape(-1)\n",
"\n",
" for i in range(0,len(bound)):\n",
" o_len += len(bin(real_b[i])[2:])\n",
" c_len += len(encode1[str(bound[i])])\n",
" \n",
" for i in range(0, len(original)):\n",
" o_len += len(bin(original[i])[2:])\n",
" if diff[i] <= 25:\n",
" c_len += len(encode2[str(int(error[i]))])\n",
"\n",
" if diff[i] <= 40 and diff[i] > 25:\n",
" c_len += len(encode3[str(int(error[i]))])\n",
" \n",
" if diff[i] <= 70 and diff[i] > 40:\n",
" c_len += len(encode4[str(int(error[i]))])\n",
" \n",
" if diff[i] > 70:\n",
" c_len += len(encode5[str(int(error[i]))])\n",
" \n",
" return c_len/o_len\n",
"scenes = file_extractor()\n",
"images = image_extractor(scenes)\n",
"encode1, encode2, encode3, encode4, encode5, image, error, diff, boundary, bins = huffman(images[0])\n",
"compress_rate(image, error, diff, boundary, encode1, encode2, encode3, encode4, encode5)\n"
]
},
{
"cell_type": "markdown",
"id": "816764c9",
"metadata": {},
"source": [
"## Huffman Divide into 6 bins"
]
},
{
"cell_type": "code",
"execution_count": 430,
"id": "15eecad3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"0.4421759033203125"
]
},
"execution_count": 430,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def huffman6(image):\n",
" origin, predict, diff, error, A = plot_hist(image)\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",
" \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 <= 5\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 > 5\n",
" new_error = error[mask]\n",
" mask2 = diff[mask] <= 15\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 > 15\n",
" new_error = error[mask]\n",
" mask2 = diff[mask] <= 30\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 > 30\n",
" new_error = error[mask]\n",
" mask2 = diff[mask] <= 50\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",
" encode5 = huffman_code_tree(node)\n",
" \n",
" \n",
" mask = diff > 50\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",
" encode6 = huffman_code_tree(node)\n",
"\n",
" \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",
" new_error = np.ravel(new_error)\n",
" \n",
" # return the huffman dictionary\n",
" return encode1, encode2, encode3, encode4, encode5, encode6, np.ravel(image), error, diff, boundary\n",
"\n",
"def compress_rate6(image, error, diff, bound, encode1, encode2, encode3, encode4, encode5, encode6):\n",
" #original = original.reshape(-1)\n",
" #error = error.reshape(-1)\n",
" o_len = 0\n",
" c_len = 0\n",
" im = np.reshape(image,(512, 640))\n",
" real_b = np.hstack((im[0,:],im[-1,:],im[1:-1,0],im[1:-1,-1]))\n",
" original = im[1:-1,1:-1].reshape(-1)\n",
"\n",
" for i in range(0,len(bound)):\n",
" o_len += len(bin(real_b[i])[2:])\n",
" c_len += len(encode1[str(bound[i])])\n",
" \n",
" for i in range(0, len(original)):\n",
" o_len += len(bin(original[i])[2:])\n",
" if diff[i] <= 5:\n",
" c_len += len(encode2[str(int(error[i]))])\n",
"\n",
" if diff[i] <= 15 and diff[i] > 5:\n",
" c_len += len(encode3[str(int(error[i]))])\n",
" \n",
" if diff[i] <= 30 and diff[i] > 15:\n",
" c_len += len(encode4[str(int(error[i]))])\n",
" \n",
" if diff[i] <= 50 and diff[i] > 30:\n",
" c_len += len(encode5[str(int(error[i]))])\n",
" \n",
" if diff[i] > 50:\n",
" c_len += len(encode6[str(int(error[i]))])\n",
" \n",
" return c_len/o_len\n",
"scenes = file_extractor()\n",
"images = image_extractor(scenes)\n",
"encode1, encode2, encode3, encode4, encode5, encode6, image, error, diff, boundary = huffman(images[0])\n",
"compress_rate(image, error, diff, boundary, encode1, encode2, encode3, encode4, encode5, encode6)\n"
]
},
{
"cell_type": "code",
"execution_count": 431,
"id": "f8a8c717",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Compression rate of huffman with different bins: 0.448723882039388\n"
]
}
],
"source": [
"scenes = file_extractor()\n",
"images = image_extractor(scenes)\n",
"num_images = im_distribution(images, \"_9\")\n",
"rate = []\n",
"\n",
"for i in range(len(num_images)):\n",
" encode1, encode2, encode3, encode4, encode5, encode6, image, error, diff, bound = huffman6(num_images[i])\n",
" r = compress_rate6(image, error, diff, bound, encode1, encode2, encode3, encode4, encode5, encode6)\n",
" rate.append(r)\n",
" \n",
" \n",
"print(f\"Compression rate of huffman with different bins: {np.mean(rate)}\")\n"
]
},
{
"cell_type": "code",
"execution_count": 417,
"id": "6abed5da",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Compression rate of huffman with different bins: 0.44946919759114584\n",
"Compression rate of huffman without bins: 0.4513634314749933\n",
"Compression rate of huffman with uniform bins: 0.44956921895345053\n"
]
}
],
"source": [
"num_images = file_extractor('im')\n",
"\n",
"rate = []\n",
"rate_nb = []\n",
"rate_u = []\n",
"for i in range(len(num_images)):\n",
" encode1, encode2, encode3, encode4, encode5, image, error, diff, bound = huffman(num_images[i])\n",
" r = compress_rate(image, error, diff, bound, encode1, encode2, encode3, encode4, encode5)\n",
" rate.append(r)\n",
" encoding, error, image = huffman_nb(num_images[i])\n",
" r = compress_rate_nb(image, error, encoding)\n",
" rate_nb.append(r)\n",
" encode1, encode2, encode3, image, error, diff, bound = huffman_u(num_images[i])\n",
" r = compress_rate_u(image, error, diff, bound, encode1, encode2, encode3)\n",
" rate_u.append(r)\n",
" \n",
"print(f\"Compression rate of huffman with different bins: {np.mean(rate)}\")\n",
"print(f\"Compression rate of huffman without bins: {np.mean(rate_nb)}\")\n",
"print(f\"Compression rate of huffman with uniform bins: {np.mean(rate_u)}\")"
]
},
{
"cell_type": "code",
"execution_count": 238,
"id": "992dd8bb",
"metadata": {},
"outputs": [],
"source": [
"origin, predict, diff, error, A = plot_hist(images[0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9200fa53",
"metadata": {},
"outputs": [],
"source": [
"\n",
"for "
]
}
],
"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
}
Encoding_decoding.ipynb
View file @ b9905013
......@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 288,
"execution_count": 2,
"id": "14f74f21",
"metadata": {},
"outputs": [],
......@@ -24,7 +24,7 @@
},
{
"cell_type": "code",
"execution_count": 289,
"execution_count": 3,
"id": "c16af61f",
"metadata": {},
"outputs": [],
......@@ -405,13 +405,61 @@
"output_type": "execute_result"
}
],
"source": []
"source": [
"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))"
]
},
{
"cell_type": "code",
"execution_count": null,
"execution_count": 4,
"id": "7bc6e808",
"metadata": {},
"outputs": [
{
"ename": "NotADirectoryError",
"evalue": "[Errno 20] Not a directory: 'im/1640840453_605947_0.tiff'",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mNotADirectoryError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m/var/folders/z2/plvrsqjs023g1cmx7k19mhzr0000gn/T/ipykernel_3109/413509388.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0mscenes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfile_extractor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'im'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mimages\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mimage_extractor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscenes\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[0;32m/var/folders/z2/plvrsqjs023g1cmx7k19mhzr0000gn/T/ipykernel_3109/3921095921.py\u001b[0m in \u001b[0;36mimage_extractor\u001b[0;34m(scenes)\u001b[0m\n\u001b[1;32m 9\u001b[0m \u001b[0mimage_folder\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 10\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mscene\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mscenes\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 11\u001b[0;31m \u001b[0mfiles\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mlistdir\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscene\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 12\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mfile\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mfiles\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 13\u001b[0m \u001b[0mimage_folder\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mos\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mscene\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfile\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNotADirectoryError\u001b[0m: [Errno 20] Not a directory: 'im/1640840453_605947_0.tiff'"
]
}
],
"source": [
"scenes = file_extractor('im')\n",
"for "
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "4e6cad9c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"['im/1640840453_605947_0.tiff', 'im/1640843156_846487_11.tiff', 'im/1628259417_495716_13.tiff', 'im/1640840448_738307_14.tiff', 'im/1628260288_519886_14.tiff', 'im/1640840458_606947_14.tiff']\n"
]
}
],
"source": [
"print(scenes)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "26bd3666",
"metadata": {},
"outputs": [],
"source": []
}
......
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