class7-字幕提取

一、安装准备

用brew Install安装tesseract

路径：/usr/local/Cellar/tesseract/4.1.1

把语言文件复制到tessdata里

/usr/local/Cellar/tesseract/4.1.1/share/tessdata

安装pytesseract：pip3 install pytesseract

二、配置tesseract环境

在终端输入：

export TESSDATA_PREFIX=/usr/local/Cellar/tesseract/4.1.1/share/tessdata
export PATH=$PATH:$TESSDATA_PREFIX

import pytesseract
import cv2
import numpy as np
from scipy import stats
import os
import matplotlib.pyplot as plt
 
 
if __name__=='__main__':
    path="20210701.mp4"
    print(path)
    cap=cv2.VideoCapture(path)
    frame_count=int(cap.get(cv2.CAP_PROP_FRAME_COUNT))
    print(frame_count)
    i=0
    while i<frame_count:
        cap.set(cv2.CAP_PROP_POS_FRAMES, i)
        _, frame = cap.read(i)
        if i==48:
            cv2.imwrite('20210701.jpg',frame)
        shape = frame.shape
        print(shape)
        #cv2.imshow("Frame-1", frame[580:630, 10:1270])
        #plt.imshow(frame)
        #plt.axis("off")
        #plt.show()
        img=frame[630:680, 50:1270]
        plt.imshow(img)
        plt.axis("off")
        plt.show()
        i=i+24*2

img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
        cv2.imshow("Frame-2:Gray", img)
        _,img=cv2.threshold(img,220,225,cv2.THRESH_BINARY)
        tessdata_dir_config='--tessdata-dir "/usr/local/Cellar/tesseract/4.1.1/share/tessdata" --psm 7 -c preserve_interword_spaces=1'
        word=pytesseract.image_to_string(img,lang='chi_sim',config=tessdata_dir_config)
        print(word)
        
        if cv2.waitKey(10)&0xff==ord("q"):
            break
        
    cap.release()
    cv2.destroyAllWindows()