how can I speed up my python code?

It's a program of import multiple images and extract feature using dct and histogram. 1) Import multiple images from folder

2) Make image size 256*256

3) Use image of 64*64 block unit with stride = 32

4) Do dct(8*8 size)

5) make histogram of dct

6) Extract features from dct coefficient histogram

The problem is that it's too slow. I think it's because there's so many "for loop".

This is my full-code in python. How can I change my code to speed up?

I am not familiar with python. Please help me

import numpy as np
from scipy.fftpack import dct
from PIL import Image
import glob
import matplotlib.pyplot as plt

def find_index(x,key):
    for i in range(0,len(x)):
        if x[i] == key :
            return i
        else:
            i = i+1

def image_open(path):
    image_list = []
    #for filename in glob.glob('path/*.jpg'): 
    for filename in glob.glob(path+'/*.jpg'):  
     im=Image.open(filename)
     image_list.append(im)

    return image_list

def dct_2(img):  
    #Get 2D Cosine Transform of Image
    return dct(dct(np.asarray(img).T, norm='ortho').T, norm='ortho')


def return_array(array):
    zero = [0.0, 0.0, 0.0, 0.0, 0.0]

    range = int((max(array)) - min(array))
    x, bins, patch = plt.hist(array, bins=range)
    x = list(zero) + list(x) + list(zero)
    return x


path = 'C:\\Users\\LG\\PycharmProjects\\photo' #folder that contains many images

images = image_open(path)


row = 0
array_matrix = []
label_matrix = []

for i in range(0, len(images)): #access image    
 box3 = (0,0,256,256)
 a = images[i].crop(box3)

 (y,cb,cr) = a.split()  #ycbcr 
 width , height = y.size  
 y.show()

 for q in range(0, height-32 , 32):  #use image 64*64 block unit
  for w in range(0 , width-32 ,32):
     box1 =(q,w,q+64,w+64)
     block = y.crop(box1)
     array1 , array2 , array3 , array4 , array5 , array6 , array7 , array8 ,array9 = [],[],[],[],[],[],[],[],[]



     for j in range(0,64,8):        #dct
       for n in range(0,64,8):
         box2 = (j,n,j+8,n+8)
         temp = block.crop(box2)
         dct_temp = dct_2(temp)


         array1.append(dct_temp[0,1])
         array2.append(dct_temp[1,0])
         array3.append(dct_temp[0,2])
         array4.append(dct_temp[1,1])
         array5.append(dct_temp[2,0])
         array6.append(dct_temp[0,3])
         array7.append(dct_temp[1,2])
         array8.append(dct_temp[2,1])
         array9.append(dct_temp[3,0])


     x1 = return_array(array1)   #extract feature from dct histogram
     index = find_index(x1, max(x1))
     u = [index - 5, index + 5, 1]
     array_matrix.append(x1[u[0]:u[1] + 1:u[2]])

     x2 = return_array(array2)
     index = find_index(x2, max(x2))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x2[u[0]:u[1] + 1:u[2]])

     x3 = return_array(array3)
     index = find_index(x3, max(x3))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x3[u[0]:u[1] + 1:u[2]])

     x4 = return_array(array4)
     index = find_index(x4, max(x4))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x4[u[0]:u[1] + 1:u[2]])

     x5 = return_array(array5)
     index = find_index(x5, max(x5))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x5[u[0]:u[1] + 1:u[2]])

     x6 = return_array(array6)
     index = find_index(x6, max(x6))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x6[u[0]:u[1] + 1:u[2]])

     x7 = return_array(array7)
     index = find_index(x7, max(x7))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x7[u[0]:u[1] + 1:u[2]])

     x8 = return_array(array8)
     index = find_index(x8, max(x8))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x8[u[0]:u[1] + 1:u[2]])

     x9 = return_array(array9)
     index = find_index(x9, max(x9))
     u = [index - 5, index + 5, 1]
     array_matrix[row].extend(x9[u[0]:u[1] + 1:u[2]])

     print(w/32)

     row = row+1

print(array_matrix)