对文件夹中子目录中分类的图像应用高斯模糊

问题描述

我有一个顶级目录 train，在其中我有子文件夹 motor1、motor2、motor3，其中包含用于训练的 .png 图像。我可以编写什么代码来读取子文件夹中的这些 .png 文件并将高斯模糊应用于图像并存储它们以进行处理？下面是我用来读取图像并创建训练集和标签的代码。但是如何对这些图像应用高斯模糊并保存它们以供处理？

path = "./train/*/*.png"                             
files = glob(path)

trainImg = []                                              
trainLabel = []                                            
j = 1
num = len(files)


for img in files:
'''
Append the image data to trainImg list.
Append the labels to trainLabel list.
'''
print(str(j) + "/" + str(num),end="\r")
trainImg.append(cv2.resize(cv2.imread(img),(128,128)))  
trainLabel.append(img.split('/')[-2])  
j += 1
trainImg = np.asarray(trainImg)  # Train images set
trainLabel = pd.DataFrame(trainLabel)  # Train labels set

解决方法

它会以某种方式类似于下面的内容。您需要做的就是创建新文件夹。

import cv2
import os
import numpy as np

root_folder = './root'
image_folders = ['folder1','folder2','folder3']
new_folders = ['new_folder1','new_folder2','new_folder3']

for i,j in zip(image_folders,new_folders):
    path = os.path.join(root_folder,i)
    dst_folder = os.path.join(root_folder,j)
    for img in os.listdir(path):
        img_array = cv2.imread(img)
        gaussian_blur = cv2.GaussianBlur(img_array,(5,5),0)
        cv2.imwrite(f'{dst_folder}/*.png',gaussian_blur)