OpenCV-文档扫描OCR识别-04

# 导入工具包
import numpy as np
import argparse
import cv2

def order_points(pts):
    # 初始化4个坐标点的矩阵
    rect = np.zeros((4, 2), dtype = "float32")

    # 按顺序找到对应坐标0123分别是 左上，右上，右下，左下
    # 计算左上，右下
    print("pts :\n ",pts)
    s = pts.sum(axis = 1)# 沿着指定轴计算第N维的总和
    print("s : \n",s)
    rect[0] = pts[np.argmin(s)]# 即pts[1]
    rect[2] = pts[np.argmax(s)]# 即pts[3]
    print("第一次rect : \n",rect)
    # 计算右上和左下
    diff = np.diff(pts, axis = 1)# 沿着指定轴计算第N维的离散差值
    print("diff : \n",diff)
    rect[1] = pts[np.argmin(diff)]# 即pts[0]
    rect[3] = pts[np.argmax(diff)]# 即pts[2]
    print("第二次rect :\n ",rect)
    return rect

def four_point_transform(image, pts):
    # 获取输入坐标点
    rect = order_points(pts)
    (tl, tr, br, bl) = rect

    # 计算输入的w和h值
    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))

    # 变换后对应坐标位置
    dst = np.array([# 目标点
        [0, 0],
        [maxWidth - 1, 0],# 防止出错,-1
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype = "float32")

    # 计算变换矩阵	(平移+旋转+翻转),其中
    M = cv2.getPerspectiveTransform(rect, dst)# (原坐标,目标坐标)
    print("M:",M)
    print("M.shape:",M.shape)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # 返回变换后结果
    return warped

def resize(image, width=None, height=None, inter=cv2.INTER_AREA):
    dim = None
    (h, w) = image.shape[:2]
    if width is None and height is None:
        return image
    if width is None:# 无w有h时
        r = height / float(h)# 新h与旧h的比例为r
        dim = (int(w * r), height)# 让w也乘以这个比例,得到新w
    else:
        r = width / float(w)
        dim = (width, int(h * r))
    resized = cv2.resize(image, dim, interpolation=inter)
    return resized

if __name__ == "__main__":
    # 读取输入
    image = cv2.imread("receipt.jpg")
    # resize 坐标也会相同变化
    ratio = image.shape[0] / 500.0
    orig = image.copy()

    image = resize(orig, height = 500)# 同比例变化：h指定500,w也会跟着变化

    # 预处理
    gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
    gray = cv2.GaussianBlur(gray, (5, 5), 0)
    edged = cv2.Canny(gray, 75, 200)

    # 展示预处理结果
    print("STEP 1: 边缘检测")
    cv2.imshow("Image", image)
    cv2.imshow("Edged", edged)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

    # 轮廓检测
    cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[1]
    # cnts中可检测到许多个轮廓,取前5个最大面积的轮廓
    cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5]

    # 遍历轮廓
    for c in cnts:# C表示输入的点集
        # 计算轮廓近似
        peri = cv2.arcLength(c, True)
        # epsilon表示从原始轮廓到近似轮廓的最大距离，它是一个准确度参数
        # True表示封闭的
        approx = cv2.approxPolyDP(c, 0.02 * peri, True)
        print("approx：\n",approx)
        print("approx.shape",approx.shape)
        # 4个点的时候就拿出来,screenCnt是这4个点的坐标
        if len(approx) == 4:# 近似轮廓得到4个点,意味着可能得到的是矩形
            screenCnt = approx# 并且最大的那个轮廓是很有可能图像的最大外围
            break

    # 展示结果
    print("STEP 3: 变换")
    cv2.imshow("Original", resize(orig, height = 650))
    cv2.imshow("Scanned", resize(ref, height = 650))
    cv2.waitKey(0)

安装工具包

https://digi.bib.uni-mannheim.de/tesseract/
配置环境变量如E:\Program Files (x86)\Tesseract-OCR
tesseract -v进行测试
tesseract XXX.png 得到结果
pip install pytesseract
anaconda lib site-packges pytesseract pytesseract.py
tesseract_cmd 修改为绝对路径即可

from PIL import Image
import pytesseract
import cv2
import os

preprocess = 'blur' #thresh

image = cv2.imread('scan.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

if preprocess == "thresh":
    gray = cv2.threshold(gray, 0, 255,cv2.THRESH_BINARY | cv2.THRESH_OTSU)[1]

if preprocess == "blur":
    gray = cv2.medianBlur(gray, 3)
    
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
    
text = pytesseract.image_to_string(Image.open(filename))
print(text)
os.remove(filename)

cv2.imshow("Image", image)
cv2.imshow("Output", gray)
cv2.waitKey(0)