Image compression using PCA

face_recog.py

from sklearn.decomposition import PCA
import scipy.io as sio
import matplotlib.image as image
import matplotlib.image as mpimg
import pandas as pd
import matplotlib.pyplot as plt
import cv2
import numpy as np
import math
import operator
from PIL import Image
import eval_conf_mat 
from sklearn.metrics import confusion_matrix, classification_report, accuracy_score

def plot_dict(dict, ax=None):
    if ax == None:
        fig, ax = plt.subplots(figsize=(10,8))
    lists = sorted(dict.items()) # sorted by key, return a list of tuples
    x, y = zip(*lists) # unpack a list of pairs into two tuples
    ax.plot(x, y)

def readImages(path, type, n):
    list_ = list()
    for i in range(1, n+1):
        img = cv2.imread(path + type +'/' + str(i) + '.png')
        list_.append(img)

    data_size = len(list_)
    labels=[]
    temp = 1
    if(type=='Train'):
        temp = 2
    for i in range(0, data_size):
        class_label = math.floor(i/temp)
        labels.append(class_label)
    return np.array(list_), np.array(labels)

def compress(im, r):
    img_r = np.reshape(im, (100, 90*3))
    img_norm = img_r/255 #normalize(img_r)
    pca = PCA(r)
    #Run PCA on normalized image data
    lower_dimension_img = pca.fit_transform(img_norm)
    expl_var = np.round(np.sum(pca.explained_variance_ratio_),2)
    # print(lower_dimension_img.size)
    comp_rate = np.round(im.size/lower_dimension_img.size,3)
    # comp_rate = pca.explained_variance_
    # print("explained var:",comp_rate)
    #Lower dimension data is 5000x353 instead of 5000x1024
    lower_dimension_img.shape
    reconstructed_img = pca.inverse_transform(lower_dimension_img) 
    # print("reconstructed", reconstructed_img.shape)
    reconstructed_img = np.reshape(reconstructed_img, (100, 90, 3))

    return reconstructed_img, expl_var, comp_rate


path = 'drive/My Drive/FACES/'

train_data, train_label = readImages(path, 'Train',28)
test_data, test_label = readImages(path, 'Test',14)

#Image is stored in dataset
im = test_data[0,:,:,:]

#################################### PART A
print("a) compressing and reconstructing a sample picture....")
fig, axes = plt.subplots(2,2, figsize=(10,10))
k = 0
CR = [0.4,0.6,0.8,0.99]
for i in range(2):
  for j in range(2):
    r=CR[k]
    k+=1
    # print("R=",r )
    reconstructed_img,expl_var, comp_rate = compress(im, r)
    axes[i,j].imshow(reconstructed_img)
    axes[i,j].set_title(f"Explained Var= {expl_var}  Compr. Rate: "+str(comp_rate))

fig.savefig('pic.png')


####################################### Part B
print("b) reconition rate....")
import scipy.spatial.distance as dist
acc_rate = {}
for r in range(1, 14):#np.linspace(0.1,0.99, num=10):
    y_pred = []
    for test_item in range(len(test_data)):
        im = test_data[test_item,:,:,:]
        # print("R=",r )
        # plt.imshow(im)
        # plt.title("test image")
        # plt.show()
        #Run PCA on normalized image data
        compressed_test_img, expl_var,_ = compress(im, r)  
        # plt.imshow(lower_dimension_img)    
        # plt.title("lower dimension")
        # plt.show()  
        min_d,min_index = -1,-1
        for index, train_img in enumerate(train_data[:,:,:,:]):
          compressed_train_img,_,_ = compress(train_img, r)  
          # mse = np.sum((compressed_train_img - compressed_test_img)**2)
          d = dist.euclidean(compressed_train_img.flatten(), compressed_test_img.flatten())
          # print("d=", d)
          if (min_d < 0):
            min_d = d
            min_index = 0
          if d < min_d:
            min_d = d  
            min_index = index
        
        pred_label = train_label[min_index]
        y_pred.append(pred_label)
    acc = accuracy_score(test_label, y_pred)
    # print(f"r: {expl_var.round(2)} acc: {acc}")
    acc_rate[expl_var] = acc.round(2)

print("acc_rate:", acc_rate)
plot_dict(acc_rate)
plt.savefig("acc_rate")

################## PART C
print("c) MSE ....")
rate_comp = {}
for r in range(1, 20):
  mse_all = 0
  for index, train_img in enumerate(train_data[:,:,:,:]):
      compressed_train_img,_,_ = compress(train_img, r)  
      # print(train_img.shape)
      mse = np.sum((train_img - compressed_train_img)**2)/(train_img.shape[0]*train_img.shape[1])
      mse_all+=mse
  # print(len(train_data))
  avg_mse = mse_all/len(train_data)
  rate_comp[r] = avg_mse

plot_dict(rate_comp)
plt.xlabel("# of PCA components")
plt.ylabel("MSE between compressed and original image")
plt.savefig("rate_comp.png")