prediction_MSE_Scout.py 6.06 KB
Newer Older
Nathaniel Callens's avatar
Nathaniel Callens committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
#!/usr/bin/env python
# coding: utf-8

# In[72]:


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
from time import time
from numpy import linalg as la
from scipy.stats import gaussian_kde, entropy
import seaborn as sns
import pywt
import math
#import cv2


# In[15]:


def file_extractor(dirname="images"):
    files = os.listdir(dirname)
    scenes = []
    for file in files:
        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:
            image_folder.append(os.path.join(scene, file))
    images = []
    for folder in image_folder:
        ims = os.listdir(folder)
        for im in ims:
            if im[-4:] == ".jp4" or im[-7:] == "_6.tiff":
                continue
            else:
                images.append(os.path.join(folder, im))
    return images #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


# In[16]:


def plot_hist(tiff_list, i):
    """
    This function is the leftovers from the first attempt to plot histograms.
    As it stands it needs some work in order to function again. We will
    fix this later. 1/25/22
    """
    
    image = tiff_list[i]
    image = Image.open(image)    #Open the image and read it as an Image object
    image = np.array(image)[1:,:]    #Convert to an array, leaving out the first row because the first row is just housekeeping data
    image = image.astype(int)
    A = np.array([[3,0,-1],[0,3,3],[1,-3,-4]]) # the matrix for system of equation
    z0 = image[0:-2,0:-2]   # get all the first pixel for the entire image
    z1 = image[0:-2,1:-1]   # get all the second pixel for the entire image
    z2 = image[0:-2,2::]    # get all the third pixel for the entire image
    z3 = image[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.linalg.solve(A,y)[-1]
    #predict = []
    # 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
    # calculate the difference
    diff = np.max(neighbor,axis = 1) - np.min(neighbor, axis=1)
    
    """for i in range(len(neighbor)):
        if neighbor[i][0] >= max(neighbor[i][3], neighbor[i][1]):
            predict.append(min(neighbor[i][3], neighbor[i][1]))
        elif neighbor[i][0] < min(neighbor[i][3], neighbor[i][1]):
            predict.append(max(neighbor[i][3], neighbor[i][1]))
        else:
            predict.append(neighbor[i][3] + neighbor[i][1] - neighbor[i][0])"""
            
    # flatten the image to a vector
    image_ravel = np.ravel(image[1:-1,1:-1])
    return image_ravel, predict, diff, image


# In[17]:


scenes = file_extractor()
images = image_extractor(scenes)
num_images = im_distribution(images, "_1")
error_mean = []
error_mean1 = []
diff_mean = []
times = []
times1 = []
all_error = []
for i in range(len(num_images)):
    """start1 = time()
    image_1, predict_1, difference_1, x_s_1 = plot_hist(num_images, i, "second")
    stop1 = time()
    times1.append(stop1-start1)
    error1 = np.abs(image_1-predict_1)
    error_mean1.append(np.mean(np.ravel(error1)))"""
    start = time()
    image, predict, difference, non_ravel = plot_hist(num_images, i)
    stop = time()
    times.append(stop-start)
    error = np.abs(image-predict)
    all_error.append(np.ravel(error))
    error_mean.append(np.mean(np.ravel(error)))
    diff_mean.append(np.mean(np.ravel(difference)))
    
#image, predict, difference = plot_hist(images, 0)


# In[18]:


print(f"Average Error: {np.mean(error_mean)}")
print(f"Standard Deviaiton of Mean Errors: {np.sqrt(np.var(error_mean))}")
print(f"Average Difference: {np.mean(diff_mean)}")
print(f"Average Time per Image for First: {np.mean(times)}")


# In[19]:


new_image, new_pred, new_diff, no_ravel = plot_hist(images, 10)


# In[21]:


new_error = new_image-new_pred
plt.hist(new_error, bins=20, density=True)
sns.kdeplot(new_error)
plt.xlabel("error")
plt.show()


# In[41]:


image = Image.open(images[0])    #Open the image and read it as an Image object
image = np.array(image)[1:,:]    #Convert to an array, leaving out the first row because the first row is just housekeeping data
image = image.astype(np.int64)
print("Std Deviation of E: ", np.std(new_error))
print("Normal bits: ", int(image[0][0]).bit_length())
H = np.log2(np.std(new_error)) + 1.943
print("Encoded Bits: ", H)


# In[47]:





# In[9]:


pred = new_pred.reshape((510,638))
real_pred = no_ravel.copy()
real_pred[1:-1, 1:-1] = pred


# In[10]:


coeffs = pywt.dwt2(no_ravel, 'bior1.3')
LL, (LH, HL, HH) = coeffs
print(HH.shape)
decompress = pywt.idwt2(coeffs, 'bior1.3')
"""print(decompress)
print(np.mean(np.abs(decompress-no_ravel)))"""