opencv实战-文档扫描

一、文档扫描步骤

1、原图操作-边缘检测
2、原图操作-获取轮廓
3、原图操作-变换方正
4、OCR识别

二、原图操作

import numpy as np
import cv2

def cv_show(name, img):
    cv2.imshow(name, img)
    cv2.waitKey(0)
    cv2.destroyAllWindows()

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:
        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

def order_points(pts):
    # 一共4个坐标点
    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
    s = pts.sum(axis = 1)
    rect[0] = pts[np.argmin(s)]
    rect[2] = pts[np.argmax(s)]

    # 计算右上和左下
    diff = np.diff(pts, axis = 1)
    rect[1] = pts[np.argmin(diff)]
    rect[3] = pts[np.argmax(diff)]
    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))

    # 计算输入的h值
    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([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype = "float32")

    # 计算变换矩阵，rect原始近视轮廓和目标轮廓的计算值
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # 返回变换后结果
    return warped

image = cv2.imread('receipt.jpg')
# 得到比例供透视变换使用
ratio = image.shape[0] /500
orig  = image.copy()
# 将原图进行resize处理
image = resize(orig, height= 500)
# 将图片进行预处理,转为灰度图
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# 高斯滤波去除噪声
gray = cv2.GaussianBlur(gray, (5, 5), 0)
# 进行边缘检测
edged = cv2.Canny(gray, 75, 100)
# 轮廓检测
cnts = cv2.findContours(edged.copy(),cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)[0]
# 对检测的轮廓进行按照面积排序,并取出前五个
cnts = sorted(cnts,key=cv2.contourArea,reverse=True)[:5]
# 遍历轮廓
for c in cnts:
    # 计算轮廓近似长度
    # C表示输入的点集
    # 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
    peri = cv2.arcLength(c, True)
    # 算出近似轮廓
    approx = cv2.approxPolyDP(c, 0.02 * peri, True)
    # 4个点的时候就拿出来(即是遍历的第一次)
    if len(approx) == 4:
        screenCnt = approx
# 画出轮廓
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
# 透视变换，转为方正的图像；输入原图，近似图，
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)
# 转为灰度图
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
# 阈值处理
ref = cv2.threshold(warped, 100, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite('scan.jpg', ref)
cv2.waitKey(0)

三、调用OCR识别

# 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)