深度学习实现零件缺陷检测源代码(1)_深度学习vgg_深度残差网络_深度学习检测_resnet缺陷检测_vgg

import numpy as np import keras from keras.models import Sequential from keras.layers import Dense, Dropout, Flatten from keras.layers import Conv2D, MaxPooling2D import matplotlib.pyplot as plt from keras.optimizers import SGD import tensorflow as tf from PIL import Image,ImageFilter from image_handle import * import os import cv2 #高通滤波 img1=cv2.imread('C:/Users/18301/Desktop/1.jpg',0) f=np.fft.fft2(img1) fshift=np.fft.fftshift(f) rows,cols=img1.shape crow,ccol=np.ceil(rows/2),np.ceil(cols/2) crow,ccol=np.int(crow),np.int(ccol) #注意fshift是用来与原图像进行掩模操作的但是具体的，我也看着很抽象。这一部分与低通的有些相对的意思。 fshift[crow-30:crow+30,ccol-30:ccol+30]=0 f_ishift=np.fft.ifftshift(fshift) img_back=np.fft.ifft2(fshift) img_back=np.abs(img_back) plt.subplot(1,2,1),plt.imshow(img1) plt.title('input image'),plt.xticks([]),plt.yticks([]) plt.subplot(1,2,2),plt.imshow(img_back) plt.title('image after HPF'),plt.xticks([]),plt.yticks([]) plt.show() # def highPassFilter(image,d): # f = np.fft.fft2(image) # fshift = np.fft.fftshift(f) # s1 = np.log(np.abs(fshift)) # def make_transform_matrix(d): # transfor_matrix = np.zeros(image.shape) # center_point = tuple(map(lambda x:(x-1)/2,s1.shape)) # for i in range(transfor_matrix.shape[0]): # for j in range(transfor_matrix.shape[1]): # def cal_distance(pa,pb): # from math import sqrt # dis = sqrt((pa[0]-pb[0])**2+(pa[1]-pb[1])**2) # return dis # dis = cal_distance(center_point,(i,j)) # if dis <= d: # transfor_matrix[i,j]=0 # else: # transfor_matrix[i,j]=1 # return transfor_matrix # d_matrix = make_transform_matrix(d) # new_img = np.abs(np.fft.ifft2(np.fft.ifftshift(fshift*d_matrix))) # return new_img # # image_dir='C:/Users/18301/Desktop/' # image = Image.open(image_dir+'0.jpg')#原始图片过大 # image_down=image.resize((500, 500), Image.ANTIALIAS) # image_np=np.array(image_down) # new_image=highPassFilter(image_np,0) # plt.imshow(new_image),plt.show() # image_down.show() # image_np=np.array(image_down) #傅里叶正变换 # f = np.fft.fft2(image_down) # fshift = np.fft.fftshift(f) # #取绝对值：将复数变化成实数 # #取对数的目的为了将数据变化到较小的范围（比如0-255） # s1 = np.log(np.abs(fshift)) # # 傅里叶逆变换 # f1shift = np.fft.ifftshift(fshift) # img_back = np.fft.ifft2(f1shift) # #出来的是复数，无法显示 # img_back = np.abs(img_back) # # plt.imshow(img_back),plt.show() # # plt.imshow(f) # # print("cuiwei")