【项目实战】用python的opencv库和pytesseract库实现OCR文字识别

前言

文字OCR识别一直是计算机视觉领域的一大重点话题，python作为主流语言，已经将该功能整合成为一个特定的库，从而可以便捷的实现文档OCR识别。本文中使用opencv库实现了输入任何视角与低清晰度的图片，将视角化为垂直纸面视角以及将图片清晰度提高输出，然后利用pytesseract库识别图片中文字并且进行打印输出。

程序框架

具体实现代码

scan.py

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

# 设置参数
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
                help="Path to the image to be scanned")
args = vars(ap.parse_args())


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([
        [0, 0],
        [maxWidth - 1, 0],
        [maxWidth - 1, maxHeight - 1],
        [0, maxHeight - 1]], dtype="float32")

    # 计算变换矩阵
    M = cv2.getPerspectiveTransform(rect, dst)
    warped = cv2.warpPerspective(image, M, (maxWidth, maxHeight))

    # 返回变换后结果
    return warped

# 给定长度或者宽度对图片进行等比例缩放
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


# 读取输入
image = cv2.imread(args["image"])
# 坐标也会相同变化
ratio = image.shape[0] / 500.0
orig = image.copy()

image = resize(orig, height=500)

# 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)[0]
cnts = sorted(cnts, key=cv2.contourArea, reverse=True)[:5]

# 遍历轮廓
for c in cnts:
    # 计算轮廓近似
    peri = cv2.arcLength(c, True)
    # 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
    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

# 展示结果
print("STEP 2: 获取轮廓")
cv2.drawContours(image, [screenCnt], -1, (0, 255, 0), 2)
cv2.imshow("Outline", image)
cv2.waitKey(0)
cv2.destroyAllWindows()

# 透视变换
warped = four_point_transform(orig, screenCnt.reshape(4, 2) * ratio)

# 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)
# 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)

test.py

# 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.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)

总结

以上就是这篇文章的全部内容，pytesseract库的安装请借鉴这篇博客: pytesseract安装和基本使用,本篇专栏会持续更新用python实现经典计算机视觉的小项目，欢迎喜欢的uu们持续关注!