Hi I am trying to read car permits area but tesseract doens’t read some areas completely.
Here is my code and processes;

1. I firstly align image with template. (I will add the template.)
2. set image dpi with below code;

Code;

def set_image_dpi(file_path):
    IMAGE_SIZE = 1800
    im = Image.open(file_path)
    length_x, width_y = im.size
    factor = max(1, int(IMAGE_SIZE / length_x))
    size = factor * length_x, factor * width_y
    # size = (1800, 1800)
    im_resized = im.resize(size, Image.ANTIALIAS)
    temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.jpg')
    temp_filename = temp_file.name
    im_resized.save(temp_filename, dpi=(300, 300))
    return temp_filename

3. Then I remove noise and crop the confident boxes;

code;

def remove_noise(image):
return cv2.fastNlMeansDenoisingColored(image, None, 10, 10, 7, 15)

if box.conf[0] > 0.20:
    class_name = classes_names[int(box.cls[0])]
    custom = False
    custom_config_str = ""
    [x1, y1, x2, y2] = box.xyxy[0]
    # convert to int
    x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
    cropped = frame[y1:y2, x1:x2]

    cropped = remove_noise(cropped)
    cropped = cv2.cvtColor(cropped, cv2.COLOR_BGR2GRAY)
    # blur
    blur = cv2.GaussianBlur(cropped, (0, 0), sigmaX=99, sigmaY=99)

    # divide
    cropped = cv2.divide(cropped, blur, scale=255)

Then tesseract code;

    text = pytesseract.image_to_string(
        cropped,
        config=None if custom != True else "-psm 6,
        lang="tur")

here is the saved results that I can share and raw text results. What Can cause the misrecognizing text and what processes I can add to get more clear results? Because the images are really clean but many sometimes I can not get any data from them.

text: DJTICARIADI n

text: DIMARKASI nRENALLI

text: /Y.3/KULLANIMAMACI n YOLCUNAKLİ-HUSUSİİ