python - How to train data using tensorflow ocr?

Question

I am new to tensorflow, so i am little bit confuse in tensorflow there are multiple model to perform OCR like

1. attention_ocr
2. street

I have below document which i have to perform OCR. I tried to use pytesseract to read image but not giving proper result.

I need below result from above image

• D MANIKANDAN

• DURAISAMY

• 16/07/1986

• BNZPM2501F

Please suggest me please tensorflow modal is useful to perform above OCR. I am using below code to get data from pytesseract

def getData(coordinate, image):
    (y1, y2, x1, x2, classification) = coordinate
    ts = int(time.time())
    height = y2-y1
    width = x2-x1
    crop = image[y1:y1+height, x1:x1+width]
    CROP_IMAGE_URL = EXPORT_PATH +"data.jpg"
    cv2.imwrite(CROP_IMAGE_URL, crop)
    img = cv2.imread(CROP_IMAGE_URL)
    text = pytesseract.image_to_string(img)
    os.remove(CROP_IMAGE_URL)
    return text

Answer 1

First you must create an object detection model to find the region of intrests as shown in the picture. Then you can pass the ROI image into the OCR model or PyTesseract.