【數據處理（一）】python，opencv和PIL，自己製作數據集的處理腳本：圖像尺寸調整、重命名、裁剪、格式轉換、尺寸測試和標籤測試

目錄

引言

程序介紹

程序1：批量調整圖像尺寸

代碼：

程序2：批量圖像尺寸調整

代碼:

程序3：批量圖像重命名

代碼：

程序4：圖像裁剪

代碼：

程序5：圖像格式轉換

代碼：

程序6：測試圖像尺寸是否是指定大小

代碼：

程序7：測試圖像的ground truth

代碼：

注意事項

---

引言

最近在做自己的數據集，發現採集到的圖像尺寸很大（大部分是手機拍攝的）、圖片格式不統一。

我們在做深度學習和機器學習的時候，自己製作數據集格式應該是統一的，本文的腳本的功能就是對數據集中的圖像進行統一式整理。

功能包括：

批量圖像重命名、批量圖像尺寸轉換、批量圖像剪切、批量圖像格式轉換、測試圖像大小、測試標籤情況。

 

程序介紹

程序1：批量調整圖像尺寸

功能：在編輯器內運行，批量resize圖像，並另保存。

函數輸入：image_path=image_path, save_path=save_path, x=1920, y=1080, quality=95, dpi_x=72, dpi_y=72

對應：輸入圖像路徑、輸出圖像路徑、x，y，質量、dpi的x值，dpi的y值；若沒有輸入某些參數，將按默認值運行

示例：

resize(image_path=image_path, save_path=save_path, x=1920, y=1080, quality=95, dpi_x=72, dpi_y=72)

代碼：

import cv2
import os
from PIL import Image

image_path = './image/'  # 圖像輸入路徑
save_path = './resize/'  # 圖像輸出路徑
# 路徑不要有中文


def resize(image_path, save_path, x=256, y=256, quality=95, dpi_x=72.0, dpi_y=72.0):
    # 設置圖像的輸入、輸出、需要resize的大小，質量、和dpi值
    im_name = os.listdir(image_path)
    paths = []
    for name in im_name:
        path = os.path.join(image_path, name)
        paths += [path]

    for i, path in enumerate(paths):
        im = cv2.imread(path)  # 讀取圖像
        print("Extract %s image, %d of %d images" % (im_name[i], i + 1, len(paths)))
        im_resize = cv2.resize(im, (x, y))  # resize圖像大小
        im_dpi = Image.fromarray(cv2.cvtColor(im_resize, cv2.COLOR_BGR2RGB))
        im_dpi.save(save_path + im_name[i], quality=quality, dpi=(dpi_x, dpi_y))  # 保存


resize(image_path=image_path, save_path=save_path, x=1920, y=1080, quality=95, dpi_x=72, dpi_y=72)

運行結果，以其中一個圖像爲例：

 

程序2：批量圖像尺寸調整

功能：使用命令行運行，批量resize圖像，並另保存。

函數輸入：image_path=image_path, save_path=save_path, x=1920, y=1080, quality=95, dpi_x=72, dpi_y=72

對應：輸入圖像路徑、輸出圖像路徑、x，y，質量、dpi的x值，dpi的y值；若沒有輸入某些參數，將按默認值運行。

示例：在命令行輸入

python image_resize_args.py --image_path ./image/ --save_path ./resize/ -x 1024 -y 720 -quality 95 -dpi_x 72 -dpi_y 72

代碼:

import cv2
import os
from PIL import Image
import argparse as ap

# Get the path of the training set
parser = ap.ArgumentParser()
parser.add_argument("--image_path", help='輸入圖片來源路徑', required="True")
parser.add_argument("--save_path", help='輸入圖片存儲路徑', required="True")
parser.add_argument("-x", type=int, help='輸入圖像的長度', default=256, required="True")
parser.add_argument("-y", type=int, default=256, help='輸入圖像的寬度', required="True")
parser.add_argument("-quality", type=int, default=95, help='輸入圖像存儲質量', required = "True")
parser.add_argument("-dpi_x", type=int, default=72, help='輸入圖像dpi_x', required="True")
parser.add_argument("-dpi_y", type=int, default=72, help='輸入圖像dpi_y', required="True")

args = vars(parser.parse_args())

image_path = args["image_path"]
save_path = args["save_path"]
x = args["x"]
y = args["y"]
quality = args["quality"]
dpi_x = args["dpi_x"]
dpi_y = args["dpi_y"]


def resize(image_path, save_path, x=256, y=256, quality=95, dpi_x=72, dpi_y=72):
    im_name = os.listdir(image_path)
    paths = []
    for name in im_name:
        path = os.path.join(image_path, name)
        paths += [path]

    for i, path in enumerate(paths):
        im = cv2.imread(path)
        print("Extract %s image, %d of %d images" % (im_name[i], i + 1, len(paths)))
        im_resize = cv2.resize(im, (x, y))
        im_dpi = Image.fromarray(cv2.cvtColor(im_resize, cv2.COLOR_BGR2RGB))
        im_dpi.save(save_path + im_name[i], quality=quality, dpi=(dpi_x, dpi_y))


print(image_path, save_path, x, y, quality, dpi_x, dpi_y)
print(type(image_path), type(save_path), type(x), type(y), type(quality), type(dpi_x), type(dpi_y))
resize(image_path=image_path, save_path=save_path, x=x, y=y, quality=quality, dpi_x=dpi_x, dpi_y=dpi_y)

運行結果，以其中一個圖像爲例：

 

程序3：批量圖像重命名

功能：對文件夾內的圖像進行重名，

函數輸入：無，只需調整腳本里的path和Newdir = os.path.join(path, str(count).zfill(4) + filetype)中的4這個位置，換成你想要的位數。

代碼：

#  按順序修改圖片的名字
# 修改一個文件夾下所有圖片的名字，修改成000000.jpg格式
import os

path = './image'
filelist = os.listdir(path)
# filelist.sort()
count = 0

for file in filelist:
    print(file)
    Olddir = os.path.join(path, file)
    if os.path.isdir(Olddir):
        continue
    filename = os.path.splitext(file)[0]
    filetype = os.path.splitext(file)[1]
    Newdir = os.path.join(path, str(count).zfill(4) + filetype)
    os.rename(Olddir, Newdir)
    count += 1

zfill(5)的運行結果

 

程序4：圖像裁剪

功能：將原先圖像裁剪成自定義的尺寸

函數輸入：res = cut(image_path, save_path, 832, 832)，注意修改路徑和尺寸

對應：圖像路徑，裁剪後的保存路徑，需要得到的x，需要得到的y

代碼：

# -*- coding:utf-8 -*-
from PIL import Image
import os


def cut(image_path, save_path, vx, vy):
    count = 0

    im_name = os.listdir(image_path)
    paths = []
    for name in im_name:
        path = os.path.join(image_path, name)
        paths += [path]
    for i, path in enumerate(paths):

        name = (path.split('/')[-1]).split('.')[0]
        name2 = save_path + name + '_'

        im = Image.open(path)
        w = im.size[0]
        h = im.size[1]

        # print(w, h)
        # 偏移量
        dx = 300
        dy = 300
        n = 1

        # 左上角切割
        x1 = 0
        y1 = 0
        x2 = vx
        y2 = vy
        # 縱向
        while x2 <= h:
            while y2 <= w:
                name3 = name2 + '%06d' % (n) + ".jpg"
                # print(n, x1, y1, x2, y2)
                im2 = im.crop((y1, x1, y2, x2))
                im2.save(name3)
                y1 = y1 + dy
                y2 = y1 + vy
                n = n + 1
            if y2 >= w:
                name3 = name2 + '%06d' % (n) + ".jpg"
                # print(n, x1, y1, x2, y2)
                y1 = w - vy
                y2 = w
                im2 = im.crop((y1, x1, y2, x2))
                im2.save(name3)
                # print n, x1, y1, x2, y2
                n = n + 1
            x1 = x1 + dx
            x2 = x1 + vx
            y1 = 0
            y2 = vy
        x1 = h - vx
        x2 = h
        y1 = 0
        y2 = vy
        while y2 <= w:
            name3 = name2 + '%06d' % (n) + ".jpg"
            # print(n, x1, y1, x2, y2)
            im2 = im.crop((y1, x1, y2, x2))
            im2.save(name3)
            y1 = y1 + dy
            y2 = y1 + vy
            n = n + 1
        if y2 >= w:
            name3 = name2 + '%06d' % (n) + ".jpg"
            # print(n, x1, y1, x2, y2)
            y1 = w - vy
            y2 = w
            im2 = im.crop((y1, x1, y2, x2))
            im2.save(name3)
            n = n + 1

        print(path + "切割成功，切割得到的子圖片數爲", n - 1, ':', i + 1, '/', len(paths))
        count += n
    return count


if __name__ == "__main__":
    image_path = './image/'
    save_path = './image_cut/'

    # 切割圖片的面積 vx,vy
    # 大
    res = cut(image_path, save_path, 832, 832)

    # 中
    # res = cut(id,120,120)

    # 小
    # res = cut(id,80,80)

    print('all sub image:', res)

 

程序5：圖像格式轉換

功能：圖像的格式有png jpg等，把路徑裏的png轉成jpg或者 JPEG轉成jpg等，需要怎麼轉換，可以自己定義。

注意：dirName是圖像存在的路徑，newname[-1] == "png"是需要轉換的格式（轉換之前），newname[-1] = "jpg"是想要轉換的格式（轉換之後）

下面腳本實現的是把,png轉成.jpg格式。

代碼：

# 把某種類型的圖片改爲.jpg格式
import os
import string

dirName = './image/'
li = os.listdir(dirName)
for filename in li:
    newname = filename
    newname = newname.split(".")
    if newname[-1] == "png":  # 這裏是你圖片的原格式的後綴
        newname[-1] = "jpg"
        newname = str.join(".", newname)  # 這裏要用str.join
        filename = dirName + filename
        newname = dirName + newname
        os.rename(filename, newname)
        print(newname, "updated successfully")

 

程序6：測試圖像尺寸是否是指定大小

功能：測試文件下圖像尺寸是否是指定大小，將尺寸不正確的圖像名輸出

代碼：

import os
import cv2

im_path = 'myData/VOC2007/JPEGImages'
x = 1920
y = 1080

ims = os.listdir(im_path)
ims.sort()

for i, name in enumerate(ims):
    im = cv2.imread(im_path + '/' + name)
    n, m, r = im.shape
    if n != y:
        print(name)
    elif m != x:
        print(name)
    else:
        continue
print('over')

 

程序7：測試圖像的ground truth

功能：測試使用LabelImg打過標籤後的標註情況，查看標籤是否正確，程序運行後，按空格繼續查看。

代碼：

# -*- coding: utf-8 -*-

import os
import random
import cv2 as cv
import matplotlib.pyplot as plt

labels = ["TA"]
color_list = [(0, 0, 255), (255, 0, 0), (0, 255, 0), (0, 255, 255)]
img_dir = "myData/VOC2007/JPEGImages"
yolo_txt_dir = "myData/VOC2007/labels"
# result_dst_dir = "/home/youyheng/DJIdata/robomaster_Final_Tournament/check_label_result"
scale_percent = 80
# rates that represent the imgs of all datasets
# 1 for all imgs, 0.5 for half of the imgs
check_rate = 1
random_check = False


def cv_imread(file_path):
    img = plt.imread(file_path)
    img_rgb = cv.cvtColor(img, cv.COLOR_BGR2RGB)
    return img_rgb


def my_line(img, start, end):
    thickness = 2
    line_type = 8
    cv.line(img,
            start,
            end,
            (0, 0, 0),
            thickness,
            line_type)


# draw rectangle with the data caught in the data file
# And set the name of the label to it
def draw_label_rec(img, label_index, label_info_list, img_name):
    global labels

    img_height = img.shape[0]
    img_width = img.shape[1]

    x = float(label_info_list[0])
    y = float(label_info_list[1])
    w = float(label_info_list[2])
    h = float(label_info_list[3])

    x_center = x * img_width
    y_center = y * img_height

    xmax = int(x_center + w * img_width / 2)
    xmin = int(x_center - w * img_width / 2)
    ymax = int(y_center + w * img_height / 2)
    ymin = int(y_center - w * img_height / 2)

    # Set font
    font = cv.FONT_HERSHEY_SIMPLEX
    global color_list

    # draw_rectangle
    cv.rectangle(img,  # img to paint on
                 (xmin, ymin),  # bottom top
                 (xmax, ymax),  # bottom right
                 color_list[int(label_index)],  # bgr color
                 2)  # line thickness

    ###########need perfection
    cv.putText(img, str(img_name), (5, 50), cv.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2)


def main():
    global img_dir, yolo_txt_dir, labels, random_check

    origin_window = "Origin Window"

    # Load all imgs with label info
    img_name_list = os.listdir(img_dir)
    img_name_list.sort()
    if random_check is True:
        random.shuffle(img_name_list)

    check_max_times = int(check_rate * len(img_name_list))
    for index, img_name in enumerate(img_name_list):
        if not img_name.endswith('jpg'):
            continue

        # Checked for max_times and quit
        if index >= check_max_times:
            return
        print("**check img : {0} **".format(os.path.join(img_dir, img_name)))
        # Open IMG
        src_image = cv_imread(os.path.join(img_dir, img_name))

        # Open yolo label txt
        if os.path.exists(os.path.join(yolo_txt_dir, img_name.rpartition(".")[0] + ".txt")):
            file_reader = open(os.path.join(yolo_txt_dir, img_name.rpartition(".")[0] + ".txt"), "r")
        else:
            continue

        ## Dada loaded ##
        if src_image is None:
            print("Open image Error")
            return

        if file_reader is None:
            print("Open txt error")
            return

        # Pre-handling for Img
        src_height = src_image.shape[0]
        src_width = src_image.shape[1]

        # percent of original size
        global scale_percent
        width = int(src_width * scale_percent / 100)
        height = int(src_height * scale_percent / 100)
        dim = (width, height)

        # Decode the data
        while True:
            line = file_reader.readline()
            if not line:
                break
            label_info_list = line.split()
            # Get 5 nums in labeled_obj_info_list:
            # labels[label_info_list[0]] obj type : 0 ArmorBlue, 1 ArmorRed, 2 Base, 3 Watcher
            # label_info_list[1] x
            # label_info_list[2] y
            # label_info_list[3] w
            # label_info_list[4] h
            label_index = int(label_info_list[0])
            x = label_info_list[1]
            y = label_info_list[2]
            w = label_info_list[3]
            h = label_info_list[4]

            ########################
            # need perfection
            draw_label_rec(src_image, label_index, [x, y, w, h], img_name)

        resized_src = cv.resize(src_image, dim, interpolation=cv.INTER_CUBIC)

        # show the result
        cv.imshow(origin_window, resized_src)
        cv.waitKey(0)

        # Debug
        # print("src_height = {0}".format(src_height))
        # print("src_width = {0}".format(src_width))
        cv.destroyAllWindows()

        file_reader.close()
        print("**check over**")


if __name__ == "__main__":
    main()

 

注意事項

首先要安裝需要的庫，其次注意在命令行輸入時不要多輸入、漏輸入空格。

這些腳本可以二次開發，只需按照自己的要求修改，就可以實現對其他文件的類似操作

 

------------------------------------------------------------------------------------------------------------------------------------

2020-6-11更新：增加圖像剪切、圖像重命名、圖像格式轉換功能、尺寸測試、xml測試，同時修改標題、引言部分。