请建议如何使用python从手动填写的每框字符型表单中提取文本数据

import cv2
import pytesseract

# 加载表单图像
image = cv2.imread('form_image.jpg')

# 预处理图像
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
threshold = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# 提取每个字符型表单框的文本数据
boxes = pytesseract.image_to_boxes(threshold)
for box in boxes.splitlines():
    # 解析每个字符型表单框的坐标和文本
    x, y, w, h, text = box.split(' ')[1:]
    x, y, w, h = int(x), int(y), int(w), int(h)
    cropped_image = threshold[y:h, x:w]

    # 文本识别
    extracted_text = pytesseract.image_to_string(cropped_image, config='--psm 6')

    # 打印提取的文本数据
    print(extracted_text)