# 如何使用OpenCV进行发票的透视变换和二值化处理

www_pp_

已于 2025-05-08 21:28:00 修改

阅读量582

点赞数 4

文章标签： opencv 人工智能计算机视觉

于 2025-05-08 21:24:33 首次发布

本文链接：https://blog.csdn.net/www_pp_/article/details/147805092

版权

如何使用OpenCV进行发票的透视变换和二值化处理

引言

在自动化处理发票和其他文档时，图像预处理是一个关键步骤，它可以帮助提高OCR（光学字符识别）的准确性。透视变换用于校正图像中的透视失真，而二值化处理则可以简化图像，使其更适合OCR处理。本文将介绍如何使用OpenCV库进行这些操作。

环境准备

确保您的环境中安装了OpenCV库。如果尚未安装，可以通过以下命令安装：

pip install opencv-python

代码实现

以下是完整的代码实现，包括图像读取、透视变换、二值化处理和显示结果。

import numpy as np
import cv2

def cv_show(name, img):
    """简单的图像显示函数，用于显示图像窗口，参数name为窗口名称，img为要显示的图像"""
    cv2.imshow(name, img)
    cv2.waitKey(0)

def order_points(pts):
    """对四个点进行排序，以便于进行透视变换
    参数pts为四个检测到的点的坐标
    返回值rect为排序后的点的坐标"""
    rect = np.zeros((4, 2), dtype="float32")
    s = pts.sum(axis=1)  # 对pts矩阵的每一行进行求和操作（x+y）
    rect[0] = pts[np.argmin(s)]  # 选择坐标和最小的点为左上角
    rect[2] = pts[np.argmax(s)]  # 选择坐标和最大的点为右下角
    diff = np.diff(pts, axis=1)  # 对pts矩阵的每一行进行求差操作（y-x）
    rect[1] = pts[np.argmin(diff)]  # 选择差异最小的点为右上角
    rect[3] = pts[np.argmax(diff)]  # 选择差异最大的点为左下角
    return rect

def four_point_transform(image, pts):
    """根据四个点进行透视变换
    参数image为原始图像，pts为四个检测到的点的坐标
    返回值warped为变换后的图像"""
    rect = order_points(pts)
    (tl, tr, br, bl) = rect
    widthA = np.sqrt(((br[0] - bl[0]) ** 2) + ((br[1] - bl[1]) ** 2))
    widthB = np.sqrt(((tr[0] - tl[0]) ** 2) + ((tr[1] - tl[1]) ** 2))
    maxWidth = max(int(widthA), int(widthB))
    heightA = np.sqrt(((tr[0] - br[0]) ** 2) + ((tr[1] - br[1]) ** 2))
    heightB = np.sqrt(((tl[0] - bl[0]) ** 2) + ((tl[1] - bl[1]) ** 2))
    maxHeight = max(int(heightA), int(heightB))
    dst = np.array([[0, 0], [maxWidth - 1, 0],
                    [maxWidth - 1, maxHeight - 1], [0, maxHeight - 1]], dtype="float32")
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))
    return warped

def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
    """调整图像大小
    参数image为原始图像，width和height为调整后的宽度和高度，inter为插值方法
    返回值resized为调整大小后的图像"""
    dim = None
    (h, w) = image.shape[:2]
    if width is None and height is None:
        return image
    if width is None:
        r = height / float(h)
        dim = (int(w * r), height)
    else:
        r = width / float(w)
        dim = (width, int(h * r))
    resized = cv2.resize(image, dim, interpolation=inter)
    return resized

# 读取输入图像
image = cv2.imread('fapiao.jpg')
cv_show('image', image)

# 图片过大，进行缩小处理
ratio = image.shape[0] / 500.0  # 计算缩小比率
orig = image.copy()
image = resize(orig, height=500)  # 缩小图像
cv_show('1', image)

print('STEP 1: 轮廓检测')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)  # 转换为灰度图
edged = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]  # 二值化
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[-2]
image_contours = cv2.drawContours(image.copy(), cnts, -1, (0, 0, 255), 1)
cv_show("image_contours", image_contours)

print("STEP 2:获取最大轮廓")
screenCnt = sorted(cnts, key=cv2.contourArea, reverse=True)[0]  # 获取面积最大的轮廓
peri = cv2.arcLength(screenCnt, True)  # 计算轮廓周长
screenCnt = cv2.approxPolyDP(screenCnt, 0.05 * peri, True)  # 轮廓近似
print(screenCnt.shape)
image_contours = cv2.drawContours(image.copy(), [screenCnt], -1, (0, 255, 0), 2)
cv_show("image_contours", image_contours)
cv2.waitKey(0)

# 透视变换
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)
cv2.imwrite('invoice_new.jpg', warped)
cv2.namedWindow('xx', cv2.WINDOW_NORMAL)
cv2.imshow("xx", warped)
cv2.waitKey(0)

# 二值处理
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
ref = cv2.threshold(warped, 0, 255, cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]
cv_show('ref', ref)

kernel = np.ones((2, 2), np.uint8)  # 设置kernel大小
ref_new = cv2.morphologyEx(ref, cv2.MORPH_CLOSE, kernel)  # 闭运算
ref_new = resize(ref_new.copy(), width=500)
cv_show('ref_new', ref_new)
rotated_image = cv2.rotate(ref_new, cv2.ROTATE_90_COUNTERCLOCKWISE)
cv2.imshow("result", rotated_image)
cv2.waitKey(0)