python - 如何遍历文件并保存使用 OpenCV 应用的转换？

Question

我正在使用 python 进行我的第一个真正的个人项目，我在其中使用边缘检测来创建“扫描”图像，并最终将扫描图像转换为 pdf。所以我能够让我的扫描图像代码在单个文件上工作，但我尝试在目录中的文件上使用 for 循环，但它似乎没有保存每个扫描图像。它只保存第一个。但是，由于我的控制台日志，很明显 for 循环正在完成。我似乎无法弄清楚文件在哪里没有改变。任何指导将不胜感激。谢谢。

# import packages
from pyimagesearch.transform import four_point_transform
from skimage.filters import threshold_local
import numpy as np
import argparse
import cv2
import imutils
import glob




# Iterate through file and make them into scanned versions
for filepath in glob.iglob('images/*.jpg'):

    image = cv2.imread(filepath)
    ratio = image.shape[0] / 500.0
    orig = image.copy()
    image = imutils.resize(image, height = 500)


    # convert the image to grayscale, blur it, and find edges
    # in the image
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(gray, 75, 200)

    # show the original image and the edge detected image
    print("Applying Edge Detection")
    cv2.imshow("Image", image)
    cv2.imshow("Edged", edged)
    cv2.destroyAllWindows()

    # find the contours in the edged image, keeping only the
    # largest ones, and initialize the screen contour
    cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)
    cnts = imutils.grab_contours(cnts)
    cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5]

    # loop over the contours
    for c in cnts:
        # approximate the contour
        peri = cv2.arcLength(c, True)
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)

        # if our approximated contour has four points, then we
        # can assume that we have found our screen
        if len(approx) == 4:
            screenCnt = approx
            break

    # show the contour (outline) of the piece of paper
    print("Finding contours of pages")
    cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
    cv2.imshow("Outline", image)
    cv2.destroyAllWindows()

    # apply the four point transform to obtain a top-down
    # view of the original image
    warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)

    # convert the warped image to grayscale, then threshold it
    # to give it that 'black and white' paper effect
    warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
    T = threshold_local(warped, 11, offset = 10, method = "gaussian")
    warped = (warped > T).astype("uint8") * 255

    # show the original and scanned images
    print("Applying perspective transform")
    cv2.imshow("Original", imutils.resize(orig, height = 650))
    cv2.imshow("Scanned", imutils.resize(warped, height = 650))

    # Save scanned image

    page_num = 1

    print("Saving scanned image")
    cv2.imwrite('scanned' + str(page_num) + '.jpg', warped)
    page_num += 1

Answer 1

你应该移动

page_num = 1

之前

for filepath in glob.iglob('images/*.jpg'):

否则在每个 cv2.imwrite 上它将是 1:

# Iterate through file and make them into scanned versions
for filepath in glob.iglob('images/*.jpg'):

    # <<< SNIPP lots of code >>>

    page_num = 1   # this will reset it to 1 _every single time_

    print("Saving scanned image")
    cv2.imwrite('scanned' + str(page_num) + '.jpg', warped)
    page_num += 1