Skip to content

I
image-compression
Commit 96e7a95d authored by Bryce Hepner's avatar Bryce Hepner
Browse files
Options

midday_check

parent c6dfe9f2
Expand all Show whitespace changes
Inline Side-by-side
Showing with 894 additions and 23 deletions
NoBinsDemo.ipynb 0 → 100644
View file @ 96e7a95d
This diff is collapsed.
SameTableEncoder.ipynb
View file @ 96e7a95d
......@@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 115,
"metadata": {},
"outputs": [],
"source": [
......@@ -20,7 +20,7 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 116,
"metadata": {},
"outputs": [],
"source": [
......@@ -72,7 +72,7 @@
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": 117,
"metadata": {},
"outputs": [],
"source": [
......@@ -147,7 +147,7 @@
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": 118,
"metadata": {},
"outputs": [],
"source": [
......@@ -194,8 +194,6 @@
" node = NodeTree(key1, key2)\n",
" nodes.append((node, c1 + c2))\n",
" #reverse True, decending order\n",
"\n",
" #There is a huge memory leak here, no idea how or why\n",
" nodes = sorted(nodes, key=lambda x: x[1], reverse=True)\n",
" return nodes[0][0]\n",
"def decode_string(huffman_string, the_keys, the_values):\n",
......@@ -208,7 +206,7 @@
},
{
"cell_type": "code",
"execution_count": 9,
"execution_count": 138,
"metadata": {},
"outputs": [],
"source": [
......@@ -245,7 +243,8 @@
"\n",
" # sort the difference and create the bins\n",
" sorted_diff = np.sort(diff.copy())\n",
" bins = [12,60,180]\n",
" # bins = [12,60,180]\n",
" bins = [21,31,48]\n",
" # get the boundary \n",
" boundary = np.hstack((image_array[0,:],image_array[-1,:],image_array[1:-1,0],image_array[1:-1,-1]))\n",
" \n",
......@@ -309,7 +308,7 @@
},
{
"cell_type": "code",
"execution_count": 10,
"execution_count": 139,
"metadata": {},
"outputs": [],
"source": [
......@@ -341,7 +340,8 @@
" # sort the difference and create the bins\n",
" sorted_diff = np.sort(diff.copy())\n",
" # bins = [sorted_diff[i*data_points_per_bin] for i in range(1,num_bins)]\n",
" bins = [12,60,180]\n",
" # bins = [12,60,180]\n",
" bins = [21,31,48]\n",
" # get the boundary \n",
" boundary = np.hstack((image_array[0,:],image_array[-1,:],image_array[1:-1,0],image_array[1:-1,-1]))\n",
" \n",
......@@ -417,7 +417,7 @@
},
{
"cell_type": "code",
"execution_count": 11,
"execution_count": 140,
"metadata": {},
"outputs": [],
"source": [
......@@ -456,7 +456,7 @@
},
{
"cell_type": "code",
"execution_count": 97,
"execution_count": 141,
"metadata": {},
"outputs": [],
"source": [
......@@ -486,7 +486,7 @@
},
{
"cell_type": "code",
"execution_count": 98,
"execution_count": 142,
"metadata": {},
"outputs": [],
"source": [
......@@ -576,7 +576,7 @@
},
{
"cell_type": "code",
"execution_count": 99,
"execution_count": 143,
"metadata": {},
"outputs": [],
"source": [
......@@ -587,7 +587,7 @@
},
{
"cell_type": "code",
"execution_count": 106,
"execution_count": 146,
"metadata": {},
"outputs": [],
"source": [
......@@ -597,7 +597,7 @@
"oglist_dic, ogbins = make_dictionary(images[:10], 4, False)\n",
"file_size_ratios = []\n",
"np.save(\"first_dic.npy\", oglist_dic)\n",
"for i in range(10):\n",
"for i in range(10,30):\n",
" list_dic, image, new_error, diff, bound, predict, bins = huffman(images[i], 4, False)\n",
" encoded_string1 = encoder(new_error, oglist_dic, diff, bound, ogbins)\n",
" # reconstruct_image = decoder(A, encoded_string, list_dic, bins, False)\n",
......@@ -615,14 +615,14 @@
},
{
"cell_type": "code",
"execution_count": 107,
"execution_count": 145,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"0.3953878365239038\n"
"0.3955133696593259\n"
]
}
],
......@@ -635,7 +635,9 @@
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
"source": [
"0.39535481750525336"
]
},
{
"cell_type": "markdown",
......@@ -663,9 +665,19 @@
},
{
"cell_type": "code",
"execution_count": 108,
"execution_count": 127,
"metadata": {},
"outputs": [],
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"True\n",
"True\n",
"True\n"
]
}
],
"source": [
"def bytes_to_bitstring(input_bytearray):\n",
" end_string = \"\"\n",
......@@ -676,14 +688,73 @@
"oglist_dic = np.load(\"first_dic.npy\", allow_pickle=\"TRUE\")\n",
"\n",
"\n",
"ogbins = [12,60,180]\n",
"for i,item in enumerate(newnamesforlater[0:10]):\n",
"# ogbins = [12,60,180]\n",
"ogbins = [21,31,48]\n",
"for i,item in enumerate(newnamesforlater[0:3]):\n",
" list_dic, image, new_error, diff, bound, predict, bins = huffman(images[i], 4, False)\n",
" encoded_string2 = bytes_to_bitstring(read_from_file(item))\n",
" reconstruct_image = decoder(encoded_string2, oglist_dic, ogbins, False)\n",
" print(np.allclose(image, reconstruct_image))"
]
},
{
"cell_type": "code",
"execution_count": 113,
"metadata": {},
"outputs": [],
"source": [
"def check_bin_size(tiff_image_path_list, num_bins=4, difference = True):\n",
" \"\"\"\n",
" This function is used to encode the error based on the difference\n",
" and split the difference into different bins\n",
" \n",
" Input:\n",
" tiff_image_path (string): path to the tiff file\n",
" num_bins (int): number of bins\n",
" \n",
" Return:\n",
" huffman_encoding_list list (num_bins + 1): a list of dictionary\n",
" image_array ndarray (512, 640): original image\n",
" new_error ndarray (512, 640): error that includes the boundary\n",
" diff ndarray (510, 638): difference of min and max of the 4 neighbors\n",
" boundary ndarray (2300,): the boundary values after subtracting the very first pixel value\n",
" predict ndarray (325380,): the list of predicted values\n",
" bins list (num_bins - 1,): a list of threshold to cut the bins\n",
" A ndarray (3 X 3): system of equation\n",
" \n",
" \"\"\"\n",
" all_bins = []\n",
" for i, tiff_image_path in enumerate(tiff_image_path_list):\n",
" # get the image_array, etc\n",
" image_array, predict, diff, error= predict_pix(tiff_image_path, difference)\n",
" \n",
" # calculate the number of points that will go in each bin\n",
" data_points_per_bin = diff.size // num_bins\n",
"\n",
" # sort the difference and create the bins\n",
" sorted_diff = np.sort(diff.copy())\n",
" bins = [sorted_diff[i*data_points_per_bin] for i in range(1,num_bins)]\n",
" all_bins.append(bins)\n",
" return np.mean(all_bins,axis = 0)\n"
]
},
{
"cell_type": "code",
"execution_count": 114,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[21.00404858 31.92712551 48.06477733]\n"
]
}
],
"source": [
"print(check_bin_size(images))"
]
},
{
"cell_type": "code",
"execution_count": null,
......
WorkingPyDemo.py 0 → 100644
View file @ 96e7a95d
import numpy as np
from matplotlib import pyplot as plt
from itertools import product
import os
import sys
from PIL import Image
from scipy.optimize import minimize,linprog
from sklearn.neighbors import KernelDensity
from collections import Counter
import numpy.linalg as la
def file_extractor(dirname="images"):
files = os.listdir(dirname)
scenes = []
for file in files:
if file == '.DS_Store':
continue
else:
scenes.append(os.path.join(dirname, file))
return scenes
def image_extractor(scenes):
image_folder = []
for scene in scenes:
files = os.listdir(scene)
for file in files:
if file[-5:] != ".tiff" or file[-7:] == "_6.tiff":
continue
else:
image_folder.append(os.path.join(scene, file))
return image_folder #returns a list of file paths to .tiff files in the specified directory given in file_extractor
def im_distribution(images, num):
"""
Function that extracts tiff files from specific cameras and returns a list of all
the tiff files corresponding to that camera. i.e. all pictures labeled "_7.tiff" or otherwise
specified camera numbers.
Parameters:
images (list): list of all tiff files, regardless of classification. This is NOT a list of directories but
of specific tiff files that can be opened right away. This is the list that we iterate through and
divide.
num (str): a string designation for the camera number that we want to extract i.e. "14" for double digits
of "_1" for single digits.
Returns:
tiff (list): A list of tiff files that have the specified designation from num. They are the files extracted
from the 'images' list that correspond to the given num.
"""
tiff = []
for im in images:
if im[-7:-5] == num:
tiff.append(im)
return tiff
def predict_pix(tiff_image_path, difference = True):
"""
This function predict the pixel values excluding the boundary.
Using the 4 neighbor pixel values and MSE to predict the next pixel value
(-1,1) (0,1) (1,1) => relative position of the 4 other given values
(-1,0) (0,0) => (0,0) is the one we want to predict
take the derivative of mean square error to solve for the system of equation
A = np.array([[3,0,-1],[0,3,3],[1,-3,-4]])
A @ [a, b, c] = [-z0+z2-z3, z0+z1+z2, -z0-z1-z2-z3] where z0 = (-1,1), z1 = (0,1), z2 = (1,1), z3 = (-1,0)
and the predicted pixel value is c.
Input:
tiff_image_path (string): path to the tiff file
Return:
image ndarray(512 X 640): original image
predict ndarray(325380,): predicted image excluding the boundary
diff. ndarray(325380,): IF difference = TRUE, difference between the min and max of four neighbors exclude the boundary
ELSE: the residuals of the four nearest pixels to a fitted hyperplane
error ndarray(325380,): difference between the original image and predicted image
A ndarray(3 X 3): system of equation
"""
image_obj = Image.open(tiff_image_path) #Open the image and read it as an Image object
image_array = np.array(image_obj)[1:,:].astype(int) #Convert to an array, leaving out the first row because the first row is just housekeeping data
# image_array = image_array.astype(int)
A = np.array([[3,0,-1],[0,3,3],[1,-3,-4]]) # the matrix for system of equation
# where z0 = (-1,1), z1 = (0,1), z2 = (1,1), z3 = (-1,0)
z0 = image_array[0:-2,0:-2] # get all the first pixel for the entire image
z1 = image_array[0:-2,1:-1] # get all the second pixel for the entire image
z2 = image_array[0:-2,2::] # get all the third pixel for the entire image
z3 = image_array[1:-1,0:-2] # get all the forth pixel for the entire image
# calculate the out put of the system of equation
y0 = np.ravel(-z0+z2-z3)
y1 = np.ravel(z0+z1+z2)
y2 = np.ravel(-z0-z1-z2-z3)
y = np.vstack((y0,y1,y2))
# use numpy solver to solve the system of equations all at once
#predict = np.floor(np.linalg.solve(A,y)[-1])
predict = np.round(np.round((np.linalg.solve(A,y)[-1]),1))
#Matrix system of points that will be used to solve the least squares fitting hyperplane
points = np.array([[-1,-1,1], [-1,0,1], [-1,1,1], [0,-1,1]])
# flatten the neighbor pixlels and stack them together
z0 = np.ravel(z0)
z1 = np.ravel(z1)
z2 = np.ravel(z2)
z3 = np.ravel(z3)
neighbor = np.vstack((z0,z1,z2,z3)).T
if difference:
# calculate the difference
diff = np.max(neighbor,axis = 1) - np.min(neighbor, axis=1)
else:
#Compute the best fitting hyperplane using least squares
#The res is the residuals of the four points used to fit the hyperplane (summed distance of each of the
#points to the hyperplane), it is a measure of gradient
f, diff, rank, s = la.lstsq(points, neighbor.T, rcond=None)
diff = diff.astype(int)
# calculate the error
error = np.ravel(image_array[1:-1,1:-1])-predict
return image_array, predict, diff, error
"""
this huffman encoding code is found online
https://favtutor.com/blogs/huffman-coding
"""
class NodeTree(object):
def __init__(self, left=None, right=None):
self.left = left
self.right = right
def children(self):
return self.left, self.right
def __str__(self):
return self.left, self.right
def huffman_code_tree(node, binString=''):
'''
Function to find Huffman Code
'''
if type(node) is str:
return {node: binString}
(l, r) = node.children()
d = dict()
d.update(huffman_code_tree(l, binString + '0'))
d.update(huffman_code_tree(r, binString + '1'))
return d
def make_tree(nodes):
'''
Function to make tree
:param nodes: Nodes
:return: Root of the tree
'''
while len(nodes) > 1:
(key1, c1) = nodes[-1]
(key2, c2) = nodes[-2]
nodes = nodes[:-2]
node = NodeTree(key1, key2)
nodes.append((node, c1 + c2))
#reverse True, decending order
nodes = sorted(nodes, key=lambda x: x[1], reverse=True)
return nodes[0][0]
def decode_string(huffman_string, the_keys, the_values):
for i in range(len(huffman_string)):
try:
return (int(the_keys[the_values.index(huffman_string[:i+1])]),huffman_string[i+1:])
except:
pass
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