无法在 tesseract 中提取白色文本

Question

我正在开发一个应用程序来使用 OpenCV 和 Tesseract 从图像中提取文本。我被困在一个地方当图像包含白色文本时以及图像混合了白色和其他颜色的情况。

如果文本不是白色，我可以轻松提取文本，但在文本为白色的情况下它不起作用。我正在使用 Tesseract 从文本中提取数据。 以下是我在传递给 tesseract 之前的图像处理代码：

image = cv2.imread(imgPath)
filename = getFileName()

img2gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
#cv2.imwrite('python_scripts/temp/img2gray_' + filename, img2gray)

""" below removing shadow from image """
rgb_planes = cv2.split(img2gray)

result_planes = []
result_norm_planes = []
for plane in rgb_planes:
    dilated_img = cv2.dilate(plane, np.ones((1, 1), np.uint8))
    bg_img = cv2.medianBlur(dilated_img, 21)
    diff_img = 255 - cv2.absdiff(plane, bg_img)
    norm_img = diff_img
    norm_img = cv2.normalize(diff_img, norm_img, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_8UC1)
    result_planes.append(diff_img)
    result_norm_planes.append(norm_img)

result = cv2.merge(result_planes)
result_norm = cv2.merge(result_norm_planes)
img2gray = result


origImage = image.copy()

_, new_img = cv2.threshold(img2gray, 80, 255, cv2.THRESH_BINARY)  # for black text , cv.THRESH_BINARY_INV

# to manipulate the orientation of dilution , large x means horizonatally dilating  more, large y means vertically dilating more
kernel = cv2.getStructuringElement(cv2.MORPH_CROSS, (13, 13))
dilated = cv2.dilate(new_img, kernel, iterations=9)  # dilate , more the iteration more the dilation
cv2.imwrite('python_scripts/temp/dilated_' + filename, dilated)

_, contours, _ = cv2.findContours(dilated, cv2.RETR_LIST, cv2.CHAIN_APPROX_NONE)  # get contours

(imgH, imgW) = img2gray.shape[:2]
#logger.info("imgH: " + str(imgH) + ", imgW: " + str(imgW))
ctr = 0


contoursSort = {}

for contour in contours:
    # to sort contours from top to bottom
    [x, y, w, h] = cv2.boundingRect(contour)
    contoursSort[y] = contour

orderedContours = collections.OrderedDict(sorted(contoursSort.items()))

for key, contour in orderedContours.items():
    # get rectangle bounding contour
    (x, y, w, h) = cv2.boundingRect(contour)

    # Don't plot small false positives that aren't text
    if w < 35 and h < 35:
        continue

    length = x + w
    breadth = y + h
    area = length * breadth
    cv2.rectangle(origImage, (x, y), (x + w, y + h), (255, 255, 0), 2)
    # don't consider contour which is touching the border
    if x != 0 and y != 0 and x != imgW and y != imgH:
        #logger.info("x: " + str(x) + ", y: " + str(y) + ", length: " + str(length)
        #   + ", breadth: " + str(breadth) + ", area: " + str(area))

        croppedImg = origImage[y:(y + h), x:(x + w)]
        croppedGray = cv2.cvtColor(croppedImg, cv2.COLOR_BGR2GRAY)

        ctr = ctr + 1

        th3 = cv2.adaptiveThreshold(croppedGray,255,cv2.ADAPTIVE_THRESH_GAUSSIAN_C, cv2.THRESH_BINARY,75,10)
        #th3_height, th3_width = th3.shape[:2]
        #th3 = cv2.resize(th3,(2*th3_width, 2*th3_height), interpolation = cv2.INTER_CUBIC)
        th3 = cv2.GaussianBlur(th3,(5,5),0)

        tessImgPath = 'python_scripts/temp/th3_' + str(ctr) + "_" + filename
        cv2.imwrite(tessImgPath, th3)

        tessText = runTesseract(tessImgPath)
        os.remove(tessImgPath)
        logger.info("tess text: " + str(tessText))

请指导我如何通过 OpenCV 处理图像，以便两者 可以单次提取白色和其他颜色的文本。

我现在尝试的一种方法是获取图像中的白色部分，如果它小于其他颜色，则执行图像的bitwise_xor，然后将其传递给 Tesseract。

提前致谢

Answer 1

我也在研究文本提取，其中 tesseract 无法提取具有多种颜色的文本。

白色不是问题。我尝试提取您的图像。由于文本仅包含单一颜色，因此 Tesseract 给出了第二张图像的准确输出。

但是第一张图片的效果并不好，因为一半的文字是黑色的，另一半是白色的，轮廓是灰色的。所以试试这个以获得完整的黑白图像：

import cv2
import numpy as np

# read image
img = cv2.imread("XDJFq.jpg")

# convert img to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# do adaptive threshold on gray image
thresh = cv2.adaptiveThreshold(gray, 250, cv2.ADAPTIVE_THRESH_MEAN_C, cv2.THRESH_BINARY, 11, 11)

# write results to disk
cv2.imwrite("Full_white.jpg", thresh)

# display it
cv2.imshow("thresh", thresh)
cv2.waitKey(0)

因此，在从中提取文本之后，它将白色文本的灰色轮廓变为黑色。 最终结果是

Coming together is a

BEGINNING...

. ‘keeping together is

PROGRESS...

working together is

SUCCESS...