python批量预处理图片(CascadeCNN训练前期预处理)

1、create_negative.py

#功能描述:在每个负样本图片中,选择若干个小块,并存入相应的文件夹中。

import numpy as np   #numpy:提供矩阵运算功能的库
import cv2     #cv2:opencv库
import os      #os:操作系统相关的信息模块

data_base_dir = "/home/xiao/code/CNN_face_detection/face_pictures/image-noface"   #存放原始图片地址
start_neg_dir = 1
end_neg_dir = 50
file_list = []      #建立新列表,用于存放图片名
for file in os.listdir(data_base_dir):   #指定目录:data_base_dir中内容
    if file.endswith(".jpg"):      #文件以‘.jpg',结尾
        file_list.append(file)     #将jpg图片文件全部全部存入file_list列表中

number_of_pictures = len(file_list)     #len(a):列表a长度
print "number_of_pictures:", number_of_pictures   #输出图片个数
# ============== create directories ==================================
directory = '/home/xiao/code/CNN_face_detection/face_pictures/negatives/negative_'  #开始路径
for cur_file in range(1, 50):   #range(1, 50)表示cur_file从1循环取到49
    path = directory + str(cur_file).zfill(2)  #str,zfill(2),字符串宽度为2
    if not os.path.exists(path):    #如果路径path不存在
        os.makedirs(path)           #创建path路径
# ============== create negatives =====================================
for current_neg_dir in range(start_neg_dir, end_neg_dir + 1): #current_neg_dir从1循环取到50
    save_image_number = 0
	#存储图片地址,相对文件名从negative_1 ~~ negative_50
    save_dir_neg = "/home/xiao/code/CNN_face_detection/face_pictures/negatives/negative_" + str(current_neg_dir).zfill(2)
    #取300个图片,(0,300),(300,600),(600,900).....
    for current_image in range((current_neg_dir - 1)*300, (current_neg_dir - 1)*300 + 300): 
        if current_image % 10 == 0:      #每处理100张,显示1次
            print "Processing image number " + str(current_image)
        read_img_name = data_base_dir + '/' + file_list[current_image].strip() #strip():移除字符串开头和结尾处空格
        img = cv2.imread(read_img_name)      #读取图片
        height, width, channels = img.shape  #取长宽,通道数

        crop_size = min(height, width) / 2  #从短边中间开始

        while crop_size >= 12:
            for start_height in range(0, height, 100):   #从0开始到'height-1'结束,步长100
                for start_width in range(0, width, 100):
                    if (start_width + crop_size) > width:
                        break
                    cropped_img = img[start_height : start_height + crop_size, start_width : start_width + crop_size]
                    file_name = save_dir_neg + "/neg" + str(current_neg_dir).zfill(2) + "_" + str(save_image_number).zfill(6) + ".jpg"
                    cv2.imwrite(file_name, cropped_img)
                    save_image_number += 1
            crop_size *= 0.5

        if current_image == (number_of_pictures - 1):
            break    #跳出本层循环体,从而提前结束本层循环




2、create_positive.py

#功能描述:在每个正样本图片中,选择指定区域,并存入相应的文件夹中。

import numpy as np   #numpy:提供矩阵运算功能的库
import cv2       #cv2:opencv库
import os        #os:操作系统相关的信息模块
#/home/xiao...:绝对地址,/home/xiao...:相对地址;
data_base_dir = "/home/xiao/code/CNN_face_detection/face_pictures"     #存放原始图片地址
save_dir = "/home/xiao/code/CNN_face_detection/face_pictures/positives"         #保存生成图片地址
#存放图片名及人脸区域(x,y,w,h)的txt文件地址
read_file_name_rect = "/home/xiao/code/CNN_face_detection/face_pictures/pos.txt"  

# =========== read rect file ===============
with open(read_file_name_rect, "r") as ins:  #以只读方式打开文件read_file_name_rect,并将其赋值给ins
    array_rect = []    #定义一个空列表,读文件中每行,作为其一个元素
    for line in ins:   #依次读ins中每个元素
        array_rect.append(line)      #将line元素,添加到列表array_rect最后
array_rect = array_rect[1:]   # 切片,舍弃第0个,从第1个取到最后一个
number_of_lines = len(array_rect)  #取列表长度,即列表中有多少个元素。
print "number_of_lines:", number_of_lines  #输出列表元素个数

# =========== Start processing ===============
save_file_number = 0    #定义变量,表示保存图片的个数

for current_rect in range(0, number_of_lines): #current_rect依次取值0,1,2.....number_of_lines-1
    if current_rect % 10 == 0:       #每10次输出一次
        print "Processing rect number " + str(current_rect)
    current_info = array_rect[current_rect].split()    #在列表中,以空格为界,对字符串进行切片处理
    current_image_name = current_info[0]      #图片名
    #(x,y)表示图片左上角坐标,w表示宽,h表示高
    x = max(0, int(current_info[1]))
    y = max(0, int(current_info[2]))
    w = int(current_info[3])
    h = int(current_info[4])

    if current_image_name is None:   #检查图片名是否存在
        continue          #continue:结束本次循环,break:结束当前整个循环
    read_img_name = data_base_dir + '/' + current_image_name   #右边进行拼接,得到左边文件名
    if not os.path.exists(read_img_name):     #检查文件是否存在
        continue
    img = cv2.imread(read_img_name)     #调用opencv读取图片
    cropped_img = img[y : y + h, x : x + w] #取原图片(y:y+h,x:x+w)区域,作为裁剪新图片
    #将新图片文件名和地址写入file_name中,zfill(width),width:最后的字符串宽度
    file_name = save_dir + "/pos_" + str(save_file_number).zfill(6) + ".jpg"
    save_file_number += 1
    cv2.imwrite(file_name, cropped_img)  #保存图片(cropped_img)到指定位置(file_name) 


3、shuffle_write_negatives.py

#功能描述:给定存放负样本图片的文件夹地址,将其图片路径、图片名和标签写入txt文件中。

import os          #os:操作系统相关的信息模块
import random      #导入随机函数

trainingNet = 48   #选择网络模型型号
#存放原始图片地址
data_base_dir = "/home/xiao/code/CNN_face_detection/face_pictures/negatives" 

if trainingNet == 12:
    start_neg_dir = 1   #用于选择相对文件夹
    end_neg_dir = 6
    # 读取图片文件,并将图片地址、图片名和标签写到txt文件中
    write_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_negatives.txt'
elif trainingNet == 24:
    start_neg_dir = 4
    end_neg_dir = 9
    # load and open files to read and write
    write_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_negatives_24c.txt'
elif trainingNet == 48:
    start_neg_dir = 7
    end_neg_dir = 13
    # load and open files to read and write
    write_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_negatives_48c.txt'

write_file = open(write_file_name, "w")   #以只写方式打开write_file_name文件
file_list = []      #建立列表,用于保存图片信息

for current_neg_dir in range(start_neg_dir, end_neg_dir + 1):
    current_dir = data_base_dir + '/negative_' + str(current_neg_dir).zfill(2)

    for file in os.listdir(current_dir):   #file为current_dir当前目录下图片名
        if file.endswith(".jpg"):          #如果file以jpg结尾
            write_name = current_dir + '/' + file + ' ' + str(0)  #图片路径 + 图片名 + 标签
            file_list.append(write_name)   #将write_name添加到file_list列表最后

random.shuffle(file_list)   #将列表中所有元素随机排列
number_of_lines = len(file_list)  #列表中元素个数
print number_of_lines

#将图片信息写入txt文件中,逐行写入
for current_line in range(number_of_lines):
    write_file.write(file_list[current_line] + '\n')

write_file.close()   #关闭文件


4、shuffle_write_positives.py

#功能描述:给定存放正样本图片的文件夹地址,将其图片路径、图片名和标签写入txt文件中。

import os          #os:操作系统相关的信息模块
import random      #导入随机函数
#存放原始图片地址
data_base_dir = "/home/xiao/code/CNN_face_detection/face_pictures/positives"   
file_list = []      #建立列表,用于保存图片信息
#读取图片文件,并将图片地址、图片名和标签写到txt文件中
write_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_positives.txt'
write_file = open(write_file_name, "w")   #以只写方式打开write_file_name文件

for file in os.listdir(data_base_dir):  #file为current_dir当前目录下图片名
    if file.endswith(".jpg"):      #如果file以jpg结尾
        write_name = data_base_dir + '/' + file + ' ' + str(1)  #图片路径 + 图片名 + 标签
        file_list.append(write_name)    #将write_name添加到file_list列表最后

random.shuffle(file_list)   #将列表中所有元素随机排列
number_of_lines = len(file_list)  #列表中元素个数
#将图片信息写入txt文件中,逐行写入
for current_line in range(number_of_lines):
    write_file.write(file_list[current_line] + '\n')
#关闭文件
write_file.close()   

5、write_train_val.py

#功能描述:读取正样本和负样本图片,分别取其一部分作为验证集,剩余部分作为训练集。
#将用于验证的图片拷贝到val文件夹下,其图片名和标签写入val.txt文件中,训练集同上。

import os       #os:操作系统相关的信息模块
import cv2      #cv2:opencv库
import shutil   #shutil:一种高层次的文件操作工具,有较强文件复制和删除功能
import random   #导入随机函数

trainingNet = 48   #选择网络模型型号
# 打开文件进行读写
# =================== face_12c =================================
if trainingNet == 12:
    pos_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_positives.txt' #读取正样本路径
    neg_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_negatives.txt' #读取负样本路径
    train_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/train_12c' #训练图片存放地址
    val_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/val'    #验证图片存放地址
    write_train_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/train_12c.txt' #写入训练样本路径
    write_train = open(write_train_name, "w")   #以只写方式打开txt文件,写入训练样本相关信息
    write_val_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/val.txt'
    write_val = open(write_val_name, "w")

# =================== face_24c =================================
elif trainingNet == 24:
    pos_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_positives.txt'
    neg_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_negatives_24c.txt'
    train_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/train_val/train_24c'
    val_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/train_val/val_24c'
    write_train_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/train_24c.txt'
    write_train = open(write_train_name, "w")
    write_val_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/val_24c.txt'
    write_val = open(write_val_name, "w")

# =================== face_48c =================================
elif trainingNet == 48:
    pos_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_positives.txt'
    neg_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/all_negatives_48c.txt'
    train_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/train_val/train_48c'
    val_file_name = '/home/xiao/code/CNN_face_detection/face_pictures/train_val/val_48c'
    write_train_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/train_48c.txt'
    write_train = open(write_train_name, "w")
    write_val_name = '/home/xiao/code/CNN_face_detection/face_pictures/data/val_48c.txt'
    write_val = open(write_val_name, "w")

pos = []
with open(pos_file_name, "r") as ins:   #以只读方式打开文件pos_file_name,并将其赋值给ins
    for line in ins:          #依次读ins中每个元素
        pos.append(line)      #将line元素,添加到列表pos最后

neg = []
with open(neg_file_name, "r") as ins:
    for line in ins:
        neg.append(line) 

number_of_pos = len(pos)
number_of_neg = len(neg)

#分别取正负样本前500个图片,作为验证集
val = []
val[0:500] = pos[0:500] #切片,取正样本前500个图片,作为验证集前500个
val[500:1000] = neg[0:500] #取负样本前500个图片,作为验证集后500个
random.shuffle(val)    #将列表中所有元素随机排列
for current_image in range(1000):
    source = val[current_image][0:-3]   #从val中取图片文件名
    image_file_name = val[current_image][48:-3]     #取图片文件名
    label = int(val[current_image][-2:-1])   #取图片标签
    destination = val_file_name     #目标地址
    shutil.copy(source, destination)    #将图片拷贝到val文件夹中
    image_file_complete = destination + '/' + image_file_name
	#将图片信息写入txt文件中,逐行写入
    write_val.write(image_file_name + ' ' + str(label) + '\n')   
write_val.close()

#训练数据
train = []
train[0:number_of_pos - 500] = pos[500:]  #将剩余正样本作为训练集
train[number_of_pos - 500:] = neg[500:]   #将剩余负样本作为训练集
random.shuffle(train)
number_of_train_data = len(train)

#将训练图片信息写入train.txt
for current_image in range(number_of_train_data):
    if current_image % 1000 == 0:  #每处理1000张,显示1次
        print 'Processing training data : ' + str(current_image)
    source = train[current_image][0:-3]   
    image_file_name = train[current_image][48:-3]    
    label = train[current_image].strip()[-1:]  
    destination = train_file_name
    shutil.copy2(source, destination)    #将图片拷贝到train文件夹中
    write_content = image_file_name + ' ' + label + '\n'
    write_train.write(write_content)      #写入训练图片信息到txt
write_train.close()




评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值