OpenCV: Smoothing color images and black and white text images for OCR

I have implemented OCR to recognize numbers in documents and later I will hide the number like National Security Number/Resident registration number. The folder contains different types of color and black white images (passport, business documents).

The problem is that sometimes OCR could not detect the number and skip the number like in image "Resident Registration Number". OCR skip the "Resident Registration Number" while it is clear.

How to solve this problem?

Code

import glob
import re
import string
from itertools import chain

# import self as self

from paddleocr import PaddleOCR, draw_ocr, PPStructure
import cv2
import os
import regex

pattern_8 = r'-\d{8}'
pattern_4 = r'-\d{4}'
my_path = "/media/cvpr/CM_1/COREMAX/testing/"


ocr = PaddleOCR(rec=True, use_angle=True, lang='korean', use_gpu=True)
face_cascade = cv2.CascadeClassifier('/media/cvpr/CM_1/pytesseract/haarcascade_frontalface_default.xml')

save_path = '/media/cvpr/CM_1/COREMAX/paddle/'

# Regex
passport_pattern = '^[A-Z0-9<]{9}[0-9]{1}[A-Z]{3}[0-9]{7}[A-Z]{1}[0-9]{7}[A-Z0-9<]{14}[0-9]{2}$'

for img in glob.glob(my_path + '*.*'):
    img_bgr_rgb = cv2.imread(img)
    file_Name = os.path.basename(img)
    #image = img_bgr_rgb[:, :, ::-1]

    # Not Good results
    #thresh, im_bw = cv2.threshold(image, 210, 230, cv2.THRESH_BINARY)
    #cv2.imwrite("bw_image.jpg", im_bw)

    face_data = face_cascade.detectMultiScale(img_bgr_rgb, 1.3, 5)
    for (x, y, w, h) in face_data:
        roi = img_bgr_rgb[y:y + h, x:x + w]
        roi = cv2.GaussianBlur(roi, (25, 25), cv2.BORDER_ISOLATED)
        img_bgr_rgb[y:y + roi.shape[0], x:x + roi.shape[1]] = roi

    result = ocr.ocr(img_bgr_rgb, cls=True)

    for x in result:
        if regex.search(r'\.[0-9.]+', str(x[1][0])):
            #print(x[1][0])
            x1 = int(x[0][0][0])
            y1 = int(x[0][0][1])
            x2 = int(x[0][2][0])
            y2 = int(x[0][2][1])
            cv2.rectangle(img_bgr_rgb, (x1, y1), (x2, y2), (255, 255, 224), cv2.FILLED)
            cv2.imwrite(os.path.join(save_path, file_Name), img_bgr_rgb)
        elif '-' in str(x[1][0]):
            print(x[1][0])
            x1 = int(x[0][0][0])
            y1 = int(x[0][0][1])
            x2 = int(x[0][2][0])
            y2 = int(x[0][2][1])
            cv2.rectangle(img_bgr_rgb, (x1, y1), (x2, y2), (255, 255, 224), cv2.FILLED)
            cv2.imwrite(os.path.join(save_path, file_Name), img_bgr_rgb)

Output of OCR

5318-864-2206-293
21i-87-50168
서울득벌시 강납구 논현로 149 길 67-7
57-7 Noihyeou-r0149-Bi
Gangnam-gu Seoull Korea
니1sd O -ilg s- [iSlticl 7a8 0016

Output Image

Original Image