cropper固定宽高裁剪_深度学习图像预处理-python缩放裁剪

「爱情、让人受尽委屈。」 2023-01-05 12:39 196阅读 0赞

使用深度学习进行图像类任务时，通常网络的输入大小是固定的，最近在进行涉及到文字检测的工作中，由于预处理resize缩小了原图，导致字体变模糊，从而检测失败，后来想到使用overlap来对图像进行缩放裁剪，即先将原图缩放到一定尺寸，再裁剪得到网络的输入。

好了，来说正题，使用yolov3，网络的输入是352x352x3，而输入图像大小为几百上千不等，因此需对原图进行resize，起初直接进行缩放 + 填充，检测的map很低，后来分析发现有些352x352的输入图像中的文字已经很模糊，因此直接缩放的方案不可行，改进后方案如下：

1.  原图最大尺寸大于1000，则resize到800x800，再裁剪为9个352x352，overlap为128个像素
2.  原图最大尺寸大小500且小于1000，则resize到600x600，再裁剪为4个352x352，overlap为96个像素
3.  原图最大尺寸小于500，则resize到352x352。

python实现代码如下，使用了PIL、opencv库，将整个目录下的图像全部做缩放裁剪处理，代码包含如下功能：

1.  遍历某一目录的文件
2.  opencv进行图像载入及保存
3.  opencv进行缩放裁剪
4.  PIL进行图像显示

import numpy as np
    from PIL import Image
    import cv2
    import os
    
    #输入bgr通道，并显示图像
    def img_show(img):
        img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)      #生成numpy数组
        print(type(img_rgb), img_rgb.shape)
        pil_img = Image.fromarray(img_rgb)
        pil_img.show()
    
    #完成图像的等比缩放及黑色填充
    def img_resize(cvImageSrc, net_size, width, height):
        if (width != net_size or height != net_size):
            #宽高的缩放比非常接近时直接进行缩放
            if ((net_size / height - net_size / height) < 0.001):
                det_mat = cv2.resize(cvImageSrc, (net_size, net_size))
                return det_mat
            else:
                new_w = width
                new_h = height
            if (net_size / width < net_size / height):
                new_w = net_size
                new_h = max(1, (height * net_size) / width)
            else:
                new_h = net_size
                new_w = max(1, (width * net_size) / height)
            det_mat = np.zeros((net_size, net_size, 3), dtype="uint8")
            if (new_w == width and new_h == height):
                cvImageSrc.copyTo(det_mat)
            else:
                net_w = int(new_w + 0.5)
                net_h = int(new_h + 0.5)
                if (net_w % 2 == 1):
                    net_w = net_w - 1
                if (net_h % 2 == 1):
                    net_h = net_h - 1
                #print(net_w, net_h)
                det_matROI = cv2.resize(cvImageSrc, (net_w, net_h))
    
                base_w = int((net_size - new_w) / 2 + 0.5)
                base_h = int((net_size - new_h) / 2 + 0.5)
                #print(base_h, base_w)
                for c in range(3):
                    for j in range(net_h):
                        for i in range(net_w):
                            #print(c, j, i)
                            det_mat[j + base_h - 1, i + base_w - 1, :] = det_matROI[j - 1, i - 1, :]
        else:
            det_mat = cvImageSrc
        return det_mat
    
    baseRoot = "/Users/lemonhe/Documents/CNN/dataset/01-data/"
    rootdir = baseRoot + "dataset_test"
    list = os.listdir(rootdir)  #列出文件夹下所有的目录与文件
    print(len(list))
    count = 0
    
    threshold1 = 1000
    threshold2 = 500
    
    for i in range(0,len(list)):
        path = os.path.join(rootdir, list[i])
        print(path)
        if os.path.isfile(path):
            img = cv2.imread(path)
            if(img is None):
                print("this is nonetype")
            else:
                height, width, channel = img.shape      #获取图像信息
                print(height, width, channel)
                max_dim = max(height, width)
                #img_show(img)
                if(max_dim > threshold1):
                    det_mat = img_resize(img, 800, width, height)
                    #img_show(det_mat)
                    img11 = np.uint8(det_mat[0:352, 0:352, :])
                    img12 = np.uint8(det_mat[0:352, 223:575, :])
                    img13 = np.uint8(det_mat[0:352, 447:799, :])
                    img21 = np.uint8(det_mat[223:575, 0:352, :])
                    img22 = np.uint8(det_mat[223:575, 223:575, :])
                    img23 = np.uint8(det_mat[223:575, 447:799, :])
                    img31 = np.uint8(det_mat[447:799, 0:352, :])
                    img32 = np.uint8(det_mat[447:799, 223:575, :])
                    img33 = np.uint8(det_mat[447:799, 447:799, :])
                    #print(img13.shape)
                    path11 = baseRoot + "test1/img" + str(count) + "_11.jpg"
                    path12 = baseRoot + "test1/img" + str(count) + "_12.jpg"
                    path13 = baseRoot + "test1/img" + str(count) + "_13.jpg"
                    path21 = baseRoot + "test1/img" + str(count) + "_21.jpg"
                    path22 = baseRoot + "test1/img" + str(count) + "_22.jpg"
                    path23 = baseRoot + "test1/img" + str(count) + "_23.jpg"
                    path31 = baseRoot + "test1/img" + str(count) + "_31.jpg"
                    path32 = baseRoot + "test1/img" + str(count) + "_32.jpg"
                    path33 = baseRoot + "test1/img" + str(count) + "_33.jpg"
                    cv2.imwrite(path11, img11)
                    cv2.imwrite(path12, img12)
                    cv2.imwrite(path13, img13)
                    cv2.imwrite(path21, img21)
                    cv2.imwrite(path22, img22)
                    cv2.imwrite(path23, img23)
                    cv2.imwrite(path31, img31)
                    cv2.imwrite(path32, img32)
                    cv2.imwrite(path33, img33)
                elif(max_dim > threshold2):
                    det_mat = img_resize(img, 608, width, height)
                    img11 = np.uint8(det_mat[0:352, 0:352, :])
                    img12 = np.uint8(det_mat[0:352, 255:607, :])
                    img21 = np.uint8(det_mat[255:607, 0:352, :])
                    img22 = np.uint8(det_mat[255:607, 255:607, :])
                    #img_show(img11)
                    #img_show(img12)
                    #img_show(img21)net_size
                    #img_show(img22)
                    path11 = baseRoot + "test1/img" + str(count) + "_11.jpg"
                    path12 = baseRoot + "test1/img" + str(count) + "_12.jpg"
                    path21 = baseRoot + "test1/img" + str(count) + "_21.jpg"
                    path22 = baseRoot + "test1/img" + str(count) + "_22.jpg"
                    cv2.imwrite(path11, img11)
                    cv2.imwrite(path12, img12)
                    cv2.imwrite(path21, img21)
                    cv2.imwrite(path22, img22)
                else:
                    det_mat = img_resize(img, 352, width, height)
                    img_show(det_mat)
                    path_352 = baseRoot + "test1/img" + str(count) + ".jpg"
                    cv2.imwrite(path_352, np.uint8(det_mat))
    
        count = count + 1
        print(count)

执行python脚本，结果如下：

![451477b4bb8904cd37488f2aaa2c24dd.png][]

输入图片如下，分辨率为719x1280，裁剪后输出9幅352x352的子图，这样就完成了图像的预处理。

![3883bf6eb5914f4f10c1afa5b5a80326.png][]

[451477b4bb8904cd37488f2aaa2c24dd.png]: /images/20221119/0f3451f5572e4c46b6c97850c69bc342.png
[3883bf6eb5914f4f10c1afa5b5a80326.png]: /images/20221119/e4b9f8df1a3e4a9cbb6f250496adcf10.png