Use opencv to recognize text

hello

First install pycharm, the language I use is python, and use Tesseract, the installation tutorial Tesseract OCR installation process_Qingdu Xianke's blog-CSDN blog first select the website Tesseract User Manual | tessdocTesseract documentationhttps://tesseract-ocr .github.io/tessdoc/Home.html Because what I need is windows, I choose the following. You can arrange your own download content according to your actual situation: Then select the version: install it yourself after downloading. The author works with pycharm and will add text recognition project exercises later... https://blog.csdn.net/qq_41059950/article/details/122890276 First create a folder in pycharm, click settings in File

Here we install opencv-python, and pytesseract. At this point, the preparation activities are basically completed.

 Then create a .py file and start our project.

I assume that you have a little basic knowledge of opencv and python.

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"
#添加的是你的tesseract的绝对路径，还要加上他的exe执行文件

 Read a photo below. As long as it contains English letters and numbers, it’s up to you. This is mine.

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"

img = cv2.imread('Rescources/textone.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
print(pytesseract.image_to_string(img))

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

First, you can use the pytesseract.image_to_string() function to detect the English letters and numbers on the picture

 Secondly, we can print out the coordinates of each number or letter through the function pytesseract.image_to_boxes() to prepare for the subsequent steps.

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"

img = cv2.imread('Rescources/textone.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#print(pytesseract.image_to_string(img))
print(pytesseract.image_to_boxes(img))


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

 Next, complete character detection first. We need to add a box to the recognized English and numbers.

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"

img = cv2.imread('Rescources/textone.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#print(pytesseract.image_to_string(img))
#print(pytesseract.image_to_boxes(img))


### Detecting Characters  检测字符
Himg,Wimg,_ = img.shape
boxes = pytesseract.image_to_boxes(img)
for box in boxes.splitlines():
    #print(box)
    box = box.split(' ')
    #print(box)
    x,y,w,h = int(box[1]),int(box[2]),int(box[3]),int(box[4])#坐标是以左下角为中心，所以下面计算坐标要换算
    cv2.rectangle(img,(x,Himg-y),(w,Himg-h),(0,0,255),2)
    cv2.putText(img,box[0],(x,Himg-y+20),cv2.FONT_HERSHEY_DUPLEX,1,(0,50,255),2)


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

This step is basically not difficult, it's just about making a fuss about the obtained coordinates.

 Of course, it is not enough for us to just complete this operation. We need to recognize words.

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"

img = cv2.imread('Rescources/textone.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#print(pytesseract.image_to_string(img))
#print(pytesseract.image_to_boxes(img))


### Detecting Words 检测单词
Himg,Wimg,_ = img.shape
boxes = pytesseract.image_to_data(img)
print(boxes)
for x,b in enumerate(boxes.splitlines()):#如果是单词被识别出来，会返回12个参数
    if x!=0:
        b = b.split()
        if len(b)==12:#判断是否返回的是单词，利用是否是十二个参数
            x,y,w,h = int(b[6]),int(b[7]),int(b[8]),int(b[9])
            cv2.rectangle(img, (x,y), (w+x, h+y), (0, 0, 255), 2)
            cv2.putText(img, b[11], (x,y), cv2.FONT_HERSHEY_DUPLEX, 1, (0, 50, 255), 2)


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

 You can also change the configuration to freely choose what you recognize, for example, only recognize numbers. This is what the specific parameters of ome and psm represent.

 

cong = r'--oem 3 --psm 6 outputbase digits'#添加命令
boxes = pytesseract.image_to_data(img,config=cong)

Just add and modify these in the above program

import cv2
import pytesseract

pytesseract.pytesseract.tesseract_cmd = "C:\\Program Files\\Tesseract-OCR\\tesseract.exe"

img = cv2.imread('Rescources/textone.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2RGB)
#print(pytesseract.image_to_string(img))
#print(pytesseract.image_to_boxes(img))


### Detecting Words 检测单词
Himg,Wimg,_ = img.shape
cong = r'--oem 3 --psm 6 outputbase digits'#添加命令
boxes = pytesseract.image_to_data(img,config=cong)
print(boxes)
for x,b in enumerate(boxes.splitlines()):
    if x!=0:
        b = b.split()
        if len(b)==12:#判断是否返回的是单词，利用是否是十二个参数
            x,y,w,h = int(b[6]),int(b[7]),int(b[8]),int(b[9])
            cv2.rectangle(img, (x,y), (w+x, h+y), (0, 0, 255), 2)
            cv2.putText(img, b[11], (x,y), cv2.FONT_HERSHEY_DUPLEX, 1, (0, 50, 255), 2)


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

 

ok, that’s it for this small project, see you next time.