用于 OCR 的 Python OpenCV 歪斜校正

Question

目前，我正在从事一个 OCR 项目，我需要从标签中读取文本（请参见下面的示例图像）。我遇到了图像倾斜问题，我需要帮助修复图像倾斜，以便文本水平而不是倾斜。目前，我正在尝试从给定范围内对不同角度进行评分（下面包含代码）的过程，但这种方法不一致，有时过度校正图像歪斜或平坦无法识别歪斜并纠正它。请注意，在倾斜校正之前，我将所有图像旋转 270 度以使文本直立，然后我通过下面的代码传递图像。传递给函数的图像已经是二进制图像。

代码：

def findScore(img, angle):
    """
    Generates a score for the binary image recieved dependent on the determined angle.\n
    Vars:\n
    - array <- numpy array of the label\n
    - angle <- predicted angle at which the image is rotated by\n
    Returns:\n
    - histogram of the image
    - score of potential angle
    """
    data = inter.rotate(img, angle, reshape = False, order = 0)
    hist = np.sum(data, axis = 1)
    score = np.sum((hist[1:] - hist[:-1]) ** 2)
    return hist, score

def skewCorrect(img):
    """
    Takes in a nparray and determines the skew angle of the text, then corrects the skew and returns the corrected image.\n
    Vars:\n
    - img <- numpy array of the label\n
    Returns:\n
    - Corrected image as a numpy array\n
    """
    #Crops down the skewImg to determine the skew angle
    img = cv2.resize(img, (0, 0), fx = 0.75, fy = 0.75)

    delta = 1
    limit = 45
    angles = np.arange(-limit, limit+delta, delta)
    scores = []
    for angle in angles:
        hist, score = findScore(img, angle)
        scores.append(score)
    bestScore = max(scores)
    bestAngle = angles[scores.index(bestScore)]
    rotated = inter.rotate(img, bestAngle, reshape = False, order = 0)
    print("[INFO] angle: {:.3f}".format(bestAngle))
    #cv2.imshow("Original", img)
    #cv2.imshow("Rotated", rotated)
    #cv2.waitKey(0)

    #Return img
    return rotated

校正前和校正后的标签示例图像

• 更正前：https : //imgur.com/CO32WLn
• 更正后：https : //imgur.com/XRaJ9Bz

如果有人能帮我解决这个问题，那将会有很大帮助。

Answer 1

这是用于确定偏斜的投影轮廓方法的实现。获得二值图像后，想法是以各种角度旋转图像并在每次迭代中生成像素的直方图。为了确定倾斜角度，我们比较峰值之间的最大差异并使用此倾斜角度，旋转图像以校正倾斜

左（原始），右（更正）

import cv2
import numpy as np
from scipy.ndimage import interpolation as inter

def correct_skew(image, delta=1, limit=5):
    def determine_score(arr, angle):
        data = inter.rotate(arr, angle, reshape=False, order=0)
        histogram = np.sum(data, axis=1)
        score = np.sum((histogram[1:] - histogram[:-1]) ** 2)
        return histogram, score

    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1] 

    scores = []
    angles = np.arange(-limit, limit + delta, delta)
    for angle in angles:
        histogram, score = determine_score(thresh, angle)
        scores.append(score)

    best_angle = angles[scores.index(max(scores))]

    (h, w) = image.shape[:2]
    center = (w // 2, h // 2)
    M = cv2.getRotationMatrix2D(center, best_angle, 1.0)
    rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, \
              borderMode=cv2.BORDER_REPLICATE)

    return best_angle, rotated

if __name__ == '__main__':
    image = cv2.imread('1.png')
    angle, rotated = correct_skew(image)
    print(angle)
    cv2.imshow('rotated', rotated)
    cv2.imwrite('rotated.png', rotated)
    cv2.waitKey()

Answer 2

要添加@nathancy答案，对于 Windows 用户，如果您遇到额外的偏差，只需添加 dtype=float. 每当您创建 numpy 数组时。Windows 存在整数溢出问题，因为与其他系统不同，它分配 int(32) 位作为数据类型。

参见下面的代码；添加到方法dtype=float中np.sum()：

import cv2
import numpy as np
from scipy.ndimage import interpolation as inter

def correct_skew(image, delta=1, limit=5):
    def determine_score(arr, angle):
        data = inter.rotate(arr, angle, reshape=False, order=0)
        histogram = np.sum(data, axis=1, dtype=float)
        score = np.sum((histogram[1:] - histogram[:-1]) ** 2, dtype=float)
        return histogram, score

    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1] 

    scores = []
    angles = np.arange(-limit, limit + delta, delta)
    for angle in angles:
        histogram, score = determine_score(thresh, angle)
        scores.append(score)

    best_angle = angles[scores.index(max(scores))]

    (h, w) = image.shape[:2]
    center = (w // 2, h // 2)
    M = cv2.getRotationMatrix2D(center, best_angle, 1.0)
    rotated = cv2.warpAffine(image, M, (w, h), flags=cv2.INTER_CUBIC, \
          borderMode=cv2.BORDER_REPLICATE)

    return best_angle, rotated

if __name__ == '__main__':
    image = cv2.imread('1.png')
    angle, rotated = correct_skew(image)
    print(angle)
    cv2.imshow('rotated', rotated)
    cv2.imwrite('rotated.png', rotated)
    cv2.waitKey()