OCR识别
项目概述
目标:对购物小票进行扫描并识别其上的文字
原图:
步骤:
①首先,因为小票拍摄角度任意,所以需要通过边缘检测,轮廓检测以及透视变换,将小票摆放成一个规整,平铺的位置,将图片周围的无用部分去除
②其次,对小票上的文字进行识别,并将扫描后的结果存储到txt文件中
项目实现
先实现第一步,将小票平铺
①边缘检测
代码
# 导入工具包
import numpy as np
import argparse
import cv2
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
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"])
image = cv2.imread('./images/receipt.jpg')
#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()
效果
②轮廓检测
代码
# 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()
效果
③透视变换
代码
# 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)
效果
实现第二步,识别文字
④识别文字
代码
from PIL import Image
import pytesseract
import cv2
from cv2 import cv2 as cv
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)
with open("result.txt","w+") as f:
f.write(text)
cv2.imshow("Image", image)
cv2.imshow("Output", gray)
cv2.waitKey(0)
效果
项目提醒
需配置tesseract
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 一定修改为绝对路径