使用 OpenCV 预处理图像以进行 pytesseract OCR

Question

我想使用 OCR (pytesseract) 来识别图像中的文本，如下所示：

我有数千支这样的箭头。到目前为止，过程如下：我首先调整图像大小（用于另一个过程）。然后我裁剪图像以去除箭头的大部分。接下来，我绘制一个白色矩形作为框架以消除更多噪音，但文本和图像边框之间仍然有距离，以便更好地识别文本。我再次调整图像大小，以确保大写字母的高度达到约 30 像素，

最后我用阈值 150 对图像进行二值化。

完整代码：

import cv2

image_file = '001.jpg'

# load the input image and grab the image dimensions

image = cv2.imread(image_file, cv2.IMREAD_GRAYSCALE)

(h_1, w_1) = image.shape[:2]

# resize the image and grab the new image dimensions

image = cv2.resize(image, (int(w_1*320/h_1), 320))

(h_1, w_1) = image.shape

# crop image

image_2 = image[70:h_1-70, 20:w_1-20]

# get image_2 height, width

(h_2, w_2) = image_2.shape

# draw white rectangle as a frame around the number -> remove noise

cv2.rectangle(image_2, (0, 0), (w_2, h_2), (255, 255, 255), 40)

# resize image, that capital letters are ~ 30 px in height

image_2 = cv2.resize(image_2, (int(w_2*50/h_2), 50))

# image binarization

ret, image_2 = cv2.threshold(image_2, 150, 255, cv2.THRESH_BINARY)

# save image to file

cv2.imwrite('processed_' + image_file, image_2)

# tesseract part can be commented out

import pytesseract

config_7 = ("-c tessedit_char_whitelist=0123456789AB --oem 1 --psm 7")

text = pytesseract.image_to_string(image_2, config=config_7)

print("OCR TEXT: " + "{}\n".format(text))

问题在于箭头中的文本永远不会居中。有时我会使用上述方法删除部分文本（例如在图像 50A 中）。

图像处理中是否有一种方法可以以更优雅的方式消除箭头？例如使用轮廓检测和删除？我对 OpenCV 部分比识别文本的 tesseract 部分更感兴趣。

任何帮助表示赞赏。

Answer 1

如果您查看图片，您会发现图像中有一个白色箭头，这也是最大的轮廓（特别是如果您在图像上绘制黑色边框）。如果您制作一个空白蒙版并绘制箭头（图像上最大的轮廓），然后稍微腐蚀它，您可以对实际图像和腐蚀蒙版执行每个元素的按位连接。如果不清楚，请查看底部代码和注释，您会发现它实际上非常简单。# importsimport cv2import numpy as npimg = cv2.imread("number.png")  # read image# you can resize the image here if you like - it should still work for both sizesh, w = img.shape[:2]  # get the actual images height and widthimg = cv2.resize(img, (int(w*320/h), 320))h, w = img.shape[:2]gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)  # transform to grayscalethresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU)[1]  # perform OTSU threholdcv2.rectangle(thresh, (0, 0), (w, h), (0, 0, 0), 2)contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)[0]  # search for contoursmax_cnt = max(contours, key=cv2.contourArea)  # select biggest onemask = np.zeros((h, w), dtype=np.uint8)  # create a black maskcv2.drawContours(mask, [max_cnt], -1, (255, 255, 255), -1)  # draw biggest contour on the maskkernel = np.ones((15, 15), dtype=np.uint8)  # make a kernel with appropriate values - in both cases (resized and original) 15 is okerosion = cv2.erode(mask, kernel, iterations=1)  # erode the mask with given kernelreverse = cv2.bitwise_not(img.copy())  # reversed image of the actual image 0 becomes 255 and 255 becomes 0img = cv2.bitwise_and(reverse, reverse, mask=erosion)  # per-element bit-wise conjunction of the actual image and eroded mask (erosion)img = cv2.bitwise_not(img)  # revers the image again# save image to file and displaycv2.imwrite("res.png", img)cv2.imshow("img", img)cv2.waitKey(0)cv2.destroyAllWindows()结果：

Answer 2

你可以尝试简单的Python脚本：import cv2import numpy as npimg = cv2.imread('mmubS.png', cv2.IMREAD_GRAYSCALE)thresh = cv2.threshold(img, 200, 255, cv2.THRESH_BINARY_INV )[1]im_flood_fill = thresh.copy()h, w = thresh.shape[:2]im_flood_fill=cv2.rectangle(im_flood_fill, (0,0), (w-1,h-1), 255, 2)mask = np.zeros((h + 2, w + 2), np.uint8)cv2.floodFill(im_flood_fill, mask, (0, 0), 0)im_flood_fill = cv2.bitwise_not(im_flood_fill)cv2.imshow('clear text', im_flood_fill)cv2.imwrite('text.png', im_flood_fill)结果：