有什么方法可以更准确地从图像中提取文本吗？

Question

我正在尝试从图像中提取文本，但是对于手写图像，我无法获得正确的结果。另外，我想从图像中提取一些印地语文字。

我已使用tesseract库从图像中提取文本。它适用于数字文本，但不适用于手写文本。

输入图片

输出图像

def get_string(path):

    #read image with openCV
    img = cv2.imread(path)

    #convert image to grayscale
    img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

    # Define config parameters.
    # '-l eng'  for using the English language
    # '--oem 1' for using LSTM OCR Engine
    config = ('-l eng --oem 1 --psm 3')

    #apply dilation and erosion to remove some noise
    kernel = np.ones((1,1), np.uint8)
    img = cv2.dilate(img, kernel, iterations = 1)
    img = cv2.erode(img, kernel, iterations = 1)

    #write the image after performing preprocessing
    cv2.imwrite("threshold.png", img)

    #extracting text from image using tesseract
    cv2.imshow("threshold.png", img)
    cv2.waitKey(4000)
    result = pytesseract.image_to_string(Image.open("threshold.png"), config = config)

    #writing the extracted data to file
    f = open("sample.txt","w+")
    f.write(result) 
    f.close()