一、图片变换
0、导入模块
导入相关函数，遇到报错的话，直接pip install 函数名。
import numpy as np import argparse import cv2
参数初始化
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required = True,
help = "Path to the image to be scanned")
args = vars(ap.parse_args())
Parameters:
--image images\page.jpg
1、重写resize函数
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
2、预处理
读取图片后进行重置大小，并计算缩放倍数；进行灰度化、高斯滤波以及Canny轮廓提取
image = cv2.imread(args["image"]) ratio = image.shape[0] / 500.0 orig = image.copy() image = resize(orig, height = 500) gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY) gray = cv2.GaussianBlur(gray, (5, 5), 0) edged = cv2.Canny(gray, 75, 200)
3、边缘检测
检测轮廓并排序，遍历轮廓。
cnts = cv2.findContours(edged.copy(), cv2.RETR_LIST, cv2.CHAIN_APPROX_SIMPLE)[0]# 轮廓检测 cnts = sorted(cnts, key = cv2.contourArea, reverse = True)[:5]#保留前5个轮廓 # 遍历轮廓 for c in cnts: # 计算轮廓近似 peri = cv2.arcLength(c, True)# 计算轮廓长度，C表示输入的点集，True表示轮廓是封闭的 #(C表示输入的点集，epslion判断点到相对应的line segment 的距离的阈值,曲线是否闭合的标志位) approx = cv2.approxPolyDP(c, 0.02 * peri, True) # 4个点的时候就拿出来 if len(approx) == 4: screenCnt = approx break
4、透视变换
画出近似轮廓，透视变换，二值处理
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)#透视变换
# 二值处理
warped = cv2.cvtColor(warped, cv2.COLOR_BGR2GRAY)
ref = cv2.threshold(warped, 100, 255, cv2.THRESH_BINARY)[1]
cv2.imwrite('scan.jpg', ref)
二、OCR识别
0、安装tesseract-ocr
链接: 下载
在环境变量、系统变量的Path里面添加安装路径，例如：E:\Program Files (x86)\Tesseract-OCR
tesseract -v#打开命令行，进行测试 tesseract XXX.png result#得到结果 pip install pytesseract#安装依赖包
打开python安装路径里面的python文件，例如C:\ProgramData\Anaconda3\Lib\site-packages\pytesseract\pytesseract.py
将tesseract_cmd 修改为绝对路径即可，例如：tesseract_cmd = ‘C:/Program Files (x86)/Tesseract-OCR/tesseract.exe'
1、导入模块
from PIL import Image import pytesseract import cv2 import os
2、预处理
读取图片、灰度化、滤波
image = cv2.imread('scan.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
gray = cv2.medianBlur(gray, 3)
3、输出结果
filename = "{}.png".format(os.getpid())
cv2.imwrite(filename, gray)
text = pytesseract.image_to_string(Image.open(filename))
print(text)
os.remove(filename)