How to detect subscript numbers in an image using OCR?

Question

I am using tesseract for OCR, via the pytesseract bindings. Unfortunately, I encounter difficulties when trying to extract text including subscript-sty

Answer 1

I think this way can be more suitable for the general situation.

import cv2
import pytesseract
from pathlib import Path

image = cv2.imread('test.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]  # (suitable for sharper black and white pictures
contours = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contours = contours[0] if len(contours) == 2 else contours[1]  # is OpenCV2.4 or OpenCV3
result_list = []
for c in contours:
    x, y, w, h = cv2.boundingRect(c)
    area = cv2.contourArea(c)
    if area > 200:
        detect_area = image[y:y + h, x:x + w]
        # detect_area = cv2.GaussianBlur(detect_area, (3, 3), 0)
        predict_char = pytesseract.image_to_string(detect_area, lang='eng', config='--oem 0 --psm 10')
        result_list.append((x, predict_char))
        cv2.rectangle(image, (x, y), (x + w, y + h), (0, 255, 0), thickness=2)

result = ''.join([char for _, char in sorted(result_list, key=lambda _x: _x[0])])
print(result)  # CH3


output_dir = Path('./temp')
output_dir.mkdir(parents=True, exist_ok=True)
cv2.imwrite(f"{output_dir/Path('image.png')}", image)
cv2.imwrite(f"{output_dir/Path('clean.png')}", thresh)

MORE REFERENCE

I strongly suggest you refer to the following examples, which is a useful reference for OCR.

1. Get the location of all text present in image using opencv
2. Using YOLO or other image recognition techniques to identify all alphanumeric text present in images