如何为 Tesseract 提高此图像的质量？

Question

我有这张图片：

而且，我以这种方式处理它，以便以尽可能最好的方式将其传递给 Tesseract：

sharpened = unsharp_mask(img, amount=1.5)
cv2.imwrite(TEMP_FOLDER + 'sharpened.png', sharpened)

thr = cv2.threshold(sharpened, 220, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]
# im = cv2.resize(thr, None, fx=2, fy=2, interpolation=cv2.INTER_AREA)
os.makedirs(TEMP_FOLDER, exist_ok=True)
cv2.imwrite(TEMP_FOLDER + 'inverted.png', thr)
inverted = cv2.imread(TEMP_FOLDER + 'inverted.png')

filtered_inverted = remove_black_boundaries(inverted)
filtered_inverted = cv2.resize(filtered_inverted, None, fx=2, fy=2, interpolation=cv2.INTER_LINEAR)
# kernel = np.ones((2, 2), np.uint8)
# filtered_inverted = cv2.dilate(filtered_inverted, kernel)
cv2.imwrite(TEMP_FOLDER + 'filtered.png', filtered_inverted)

median = cv2.medianBlur(filtered_inverted, 5)
# median = cv2.cvtColor(median, cv2.COLOR_RGB2GRAY)
# median = cv2.threshold(median, 127, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite(TEMP_FOLDER + 'median.png', median)

函数unsharp_mask定义为：

def unsharp_mask(image: np.ndarray, kernel_size: Tuple[int] = (5, 5),
             sigma: float = 1.0, amount: float = 1.0, threshold: float = 0) -> np.ndarray:
    """Return a sharpened version of the image, using an unsharp mask."""
    blurred = cv2.GaussianBlur(image, kernel_size, sigma)
    sharpened = float(amount + 1) * image - float(amount) * blurred
    sharpened = np.maximum(sharpened, np.zeros(sharpened.shape))
    sharpened = np.minimum(sharpened, 255 * np.ones(sharpened.shape))
    sharpened = sharpened.round().astype(np.uint8)
    if threshold > 0:
        low_contrast_mask = np.absolute(image - blurred) < threshold
        np.copyto(sharpened, image, where=low_contrast_mask)
    return sharpened

并且，函数remove_black_boundaries（在这种情况下它是无用的，因为图像中没有黑色边界）定义为：

def remove_black_boundaries(img: np.ndarray) -> np.ndarray:
    hh, ww = img.shape[:2]
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    _, thresh = cv2.threshold(gray, 1, 255, cv2.THRESH_BINARY)
    thresh = cv2.erode(thresh, np.ones((3, 3), np.uint8))

    contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
    contours = contours[0] if len(contours) == 2 else contours[1]
    cnt = max(contours, key=cv2.contourArea)
    # draw white contour on black background as mask
    mask = np.zeros((hh, ww), dtype=np.uint8)
    cv2.drawContours(mask, [cnt], 0, (255, 255, 255), cv2.FILLED)

    # invert mask so shapes are white on black background
    mask_inv = 255 - mask

    # create new (white) background
    bckgnd = np.full_like(img, (255, 255, 255))

    # apply mask to image
    image_masked = cv2.bitwise_and(img, img, mask=mask)

    # apply inverse mask to background
    bckgnd_masked = cv2.bitwise_and(bckgnd, bckgnd, mask=mask_inv)

    # add together
    result = cv2.add(image_masked, bckgnd_masked)
    return result

所以我得到sharpened 为：

而且，我得到反转（和过滤）为：

所以，传递给 Tesseract 的图像是：

但是，我从 Tesseract 得到的是Conteggio: 2900，没有第一行。我也尝试调整图像大小，但得到相同的输出。关于如何改进发送到 Tesseract 的图像的任何想法？

Answer 1

您没有显示您的实际pytesseract 代码，但没有任何（预处理）处理，我只切换到page segmentation method 6 得到正确结果，即：

假设一个统一的文本块。

import cv2
import pytesseract

img = cv2.imread('KQ49Y.png', cv2.IMREAD_GRAYSCALE)
text = pytesseract.image_to_string(img, config='--psm 6')
print(text.replace('\f', ''))
# Facebook
# Conteggio: 2900

----------------------------------------
System information
----------------------------------------
Platform:      Windows-10-10.0.19042-SP0
Python:        3.9.6
PyCharm:       2021.2
OpenCV:        4.5.3
pytesseract:   5.0.0-alpha.20201127
----------------------------------------