為什么 tesseract 不會在圖像中找到這個簡單的文本？

Question

我已經嘗試了幾個小時來調整這個圖像的大小和顏色，但沒有什么能始終如一地得到正確的字母。 請看下圖。 這是我正在使用的測試圖像。 目標是將其用於自動化目的。 謝謝！ 更大的樣本

import numpy as np
import pytesseract
from PIL import ImageGrab
import win32gui
import time

toplist, winlist = [], []

#time.sleep(3)

def enum_cb(hwnd, results):
    if 'FPS:' in win32gui.GetWindowText(hwnd):
        print(hex(hwnd), win32gui.GetWindowText(hwnd))
        winlist.append(hwnd)


win32gui.EnumWindows(enum_cb, None)

win32gui.SetForegroundWindow(winlist[0])
bbox = win32gui.GetWindowRect(winlist[0])
print(bbox)
img = np.array(ImageGrab.grab(bbox=(130, 810, 800, 1080)))


#percent by which the image is resized
scale_percent = 400

#calculate the 50 percent of original dimensions
width = int(img.shape[1] * scale_percent / 100)
height = int(img.shape[0] * scale_percent / 100)

# dsize
dsize = (width, height)

# resize image
output = cv2.resize(img, dsize)

#img.show()

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

# img = cv2.imread(r"L:\MGO2PC\MGO2 UNOFFICIAL PC\RPCS3 EMU\screenshots\screenshot-2021_04_06_17_13_03.png", 0)
#crop_img = img[800:900, 260:800]
#cv2.imshow("cropped", crop_img)
#cv2.waitKey(0)

i = cv2.imwrite("test.png",output)
text = pytesseract.image_to_string(output, lang='eng')
print(text)

Answer 1

最終發現我可以隔離文本顏色，之后tesseract閱讀沒有問題。

def cv2_from_screen(self):
   boundaries = [
        ([0, 179, 105], [38, 255, 167])  # BGR
    ]

    pytesseract.pytesseract.tesseract_cmd = r"L:\Program Files\Tesseract- 
    OCR\tesseract.exe"
    def enum_cb(hwnd, results):
        if 'FPS:' in win32gui.GetWindowText(hwnd):
            print(hex(hwnd), win32gui.GetWindowText(hwnd))
            self.winlist.append(hwnd)

    win32gui.EnumWindows(enum_cb, None)
    win32gui.EnumWindows(enum_cb, None)
    win32gui.SetForegroundWindow(self.winlist[0])

    image = pyautogui.screenshot()
    image = cv2.cvtColor(np.array(image.crop(box=[0, 800, 1000, 1080])), cv2.COLOR_RGB2BGR) #COLOR_RGB2BGR and COLOR_BGR2GRAY