Opencv+python 实战一:实现字符识别(附资料下载链接及代码)

素材来源:https://www.youtube.com/watch?v=0IqCOPlGBTs
运行环境:win10+vscode+python3.7.+opencv4.4.0

准备工作

1、下载tessdoc

网站:https://tesseract-ocr.github.io/tessdoc/
无法科学上网的朋友可以上百度云:
链接:https://pan.baidu.com/s/1fjvFBJDEicLrMtmlwOtrUg
提取码:9qe5

安装完后找到这个文件,记录一下路径:
Opencv+python 实战一:实现字符识别(附资料下载链接及代码)_第1张图片

2、安装pillow以及pytesseract库

pip install pillow
pip install pytesseract

3、准备一张字符图片

Opencv+python 实战一:实现字符识别(附资料下载链接及代码)_第2张图片

代码

import cv2
import pytesseract           # pip install pytesseract
import numpy as np 
from PIL import ImageGrab    # pip install pillow 
import time

pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files (x86)\\Tesseract-OCR\\tesseract.exe'   
#需要下载tessdoc找到该文件并保存路径,这个要换成自己的
img = cv2.imread('C:\\Users\\Administrator\\Desktop\\TextDetection\\1.png')                       #需要图片的绝对路径
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)                                                         #以RGB形式读取图片
################字符识别标记#####################
hImg, wImg,_ = img.shape
boxes = pytesseract.image_to_boxes(img)
for b in boxes.splitlines():
    print(b)
    b = b.split(' ')
    print(b)
    x, y, w, h = int(b[1]), int(b[2]), int(b[3]), int(b[4])
    cv2.rectangle(img, (x,hImg- y), (w,hImg- h), (50, 50, 255), 2)
    cv2.putText(img,b[0],(x,hImg- y+25),cv2.FONT_HERSHEY_SIMPLEX,1,(50,50,255),2)
################################################
cv2.imshow('img', img)
cv2.waitKey(0)

运行结果如下:

Opencv+python 实战一:实现字符识别(附资料下载链接及代码)_第3张图片

其他相关实例:图片转字符、检测单词、只检测数字、网络摄像头和屏幕截图示例

import cv2
import pytesseract
import numpy as np
from PIL import ImageGrab
import time


pytesseract.pytesseract.tesseract_cmd = 'C:\\Program Files\\Tesseract-OCR\\tesseract.exe'
img = cv2.imread('1.png')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
pytesseract
##############################################
##### 图片转字符   ######
##############################################
# print(pytesseract.image_to_string(img))

#############################################
#### 检测字符  ######
#############################################
hImg, wImg,_ = img.shape
boxes = pytesseract.image_to_boxes(img)
for b in boxes.splitlines():
    print(b)
    b = b.split(' ')
    print(b)
    x, y, w, h = int(b[1]), int(b[2]), int(b[3]), int(b[4])
    cv2.rectangle(img, (x,hImg- y), (w,hImg- h), (50, 50, 255), 2)
    cv2.putText(img,b[0],(x,hImg- y+25),cv2.FONT_HERSHEY_SIMPLEX,1,(50,50,255),2)


##############################################
##### 检测单词  ######
##############################################
# #[   0          1           2           3           4          5         6       7       8        9        10       11 ]
# #['level', 'page_num', 'block_num', 'par_num', 'line_num', 'word_num', 'left', 'top', 'width', 'height', 'conf', 'text']
# boxes = pytesseract.image_to_data(img)
# for a,b in enumerate(boxes.splitlines()):
#         print(b)
#         if a!=0:
#             b = b.split()
#             if len(b)==12:
#                 x,y,w,h = int(b[6]),int(b[7]),int(b[8]),int(b[9])
#                 cv2.putText(img,b[11],(x,y-5),cv2.FONT_HERSHEY_SIMPLEX,1,(50,50,255),2)
#                 cv2.rectangle(img, (x,y), (x+w, y+h), (50, 50, 255), 2)


##############################################
##### 只检测数字  ######
##############################################
# hImg, wImg,_ = img.shape
# conf = r'--oem 3 --psm 6 outputbase digits'
# boxes = pytesseract.image_to_boxes(img,config=conf)
# for b in boxes.splitlines():
#     print(b)
#     b = b.split(' ')
#     print(b)
#     x, y, w, h = int(b[1]), int(b[2]), int(b[3]), int(b[4])
#     cv2.rectangle(img, (x,hImg- y), (w,hImg- h), (50, 50, 255), 2)
#     cv2.putText(img,b[0],(x,hImg- y+25),cv2.FONT_HERSHEY_SIMPLEX,1,(50,50,255),2)


##############################################
##### 网络摄像头和屏幕截图示例 ######
##############################################
# cap = cv2.VideoCapture(0)
# cap.set(3,640)
# cap.set(4,480)
# def captureScreen(bbox=(300,300,1500,1000)):
#     capScr = np.array(ImageGrab.grab(bbox))
#     capScr = cv2.cvtColor(capScr, cv2.COLOR_RGB2BGR)
#     return capScr
# while True:
#     timer = cv2.getTickCount()
#     _,img = cap.read()
#     #img = captureScreen()
#     #DETECTING CHARACTERES
#     hImg, wImg,_ = img.shape
#     boxes = pytesseract.image_to_boxes(img)
#     for b in boxes.splitlines():
#         #print(b)
#         b = b.split(' ')
#         #print(b)
#         x, y, w, h = int(b[1]), int(b[2]), int(b[3]), int(b[4])
#         cv2.rectangle(img, (x,hImg- y), (w,hImg- h), (50, 50, 255), 2)
#         cv2.putText(img,b[0],(x,hImg- y+25),cv2.FONT_HERSHEY_SIMPLEX,1,(50,50,255),2)
#     fps = cv2.getTickFrequency() / (cv2.getTickCount() - timer);
#     #cv2.putText(img, str(int(fps)), (75, 40), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (20,230,20), 2);
#     cv2.imshow("Result",img)
#     cv2.waitKey(1)
#
#

cv2.imshow('img', img)
cv2.waitKey(0)

你可能感兴趣的:(Opencv实战,opencv,python)