Pytesseract really slow

Question

so I'm trying to read out text from MS Teams and use that text to make inputs on the keyboard. Right now, I work with the threading module to have one thread for the input and one thread for the image_to_string. Following is the function for the image_to_string.

def imToString():
    global message
    print("Image getting read")
    pytesseract.pytesseract.tesseract_cmd ='C:\\Users\\gornicec\\AppData\\Local\\Programs\\Tesseract-OCR\\tesseract.exe'
    while(True):
        print("preIMGgrab")
        
        cap = ImageGrab.grab(bbox=(177, 850, 283, 881))   
        grayCap = cv2.cvtColor(np.array(cap), cv2.COLOR_BGR2GRAY)
        
        print("postIMGgrab")
        t = time.perf_counter()
        print("preMSG" + str(t))

        message = pytesseract.image_to_string(
                grayCap,
                lang ='deu',config='--psm 6')
   
        print(str(message) + "was read" + str(time.perf_counter() - t))

I don't know how but it takes about 8 seconds to read an image thats 1000 pixels big. I need this to be at highest 2 seconds. I'll add the whole code at the end. If there is any way to make it faster or to do it differently please tell me so.

WHOLE CODE:

import numpy as np
import time
import pytesseract
from win32gui import GetWindowText, GetForegroundWindow
import win32api
import cv2
import pyautogui
from PIL import ImageGrab
import threading
from ahk import AHK
import keyboard

message = ""
ahk = AHK(executable_path='C:\\Program Files\\AutoHotkey\\AutoHotkey.exe')

def Controls():
    global message
    while True:
        booleanVal = True
        if booleanVal:
            #imToString()
            print("message")
            #print("rechts" in message.lower())
            #print(f'LÄNGE: {len(message)}')
            if "vorne" in message.lower():
                # Control(message, 'w')
                ahk.key_press('w')
                #message = ""

            if "hinten" in message.lower():
                # Control(message, 's')
                ahk.key_press('s')
                #message = ""

            if "links" in message.lower():
                # Control(message, 'a')
                ahk.key_press('a')
                #message = ""

            if "rechts" in message.lower():
                # Control(message, 'd')
                #print("HAHAHA")
                ahk.key_press('d')
                #message = ""

            if "greif" in message.lower():
                ahk.key_press('space')
                #message = ""
            time.sleep(0.5)

#IMGTOSTRING---

controls = threading.Thread(target=Controls)
controls.start()
grab = threading.Thread(target=imToString)
grab.start()

Answer 1

pytesseract is not suit for large amount of images or images that are already in memory, its write them to a file and then pass the file path to tesseract cli, if you want to improve the performance of you script try using library that works directly with tesseract api.

like this: https://pypi.org/project/tess-py-api/