如何像给定图像一样检测和识别答案键中的数字？

Question

I have this image and I have to detect and store the answers and the corresponding question number. I tried using OCR but it wasn't recognising anything properly. Is there any other way?

import cv2
from imutils import contours
import numpy as np
import pytesseract

config = '-l eng+equ --oem 3 --psm 8'

# Load image, grayscale, and adaptive threshold
image = cv2.imread('answerkey.png')
original = image.copy()
original1= image.copy()
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)[1]
cv2.imshow("thresh",thresh)
cv2.waitKey(0)

# Filter out all numbers and noise to isolate only boxes
cnts = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]

(cnts,_) = contours.sort_contours(cnts, method="top-to-bottom")
(cnts,_) = contours.sort_contours(cnts, method="left-to-right")
print(cnts)
completetext=[]
for c in cnts:
    area = cv2.contourArea(c)
    if 500 < area <5000:
        # cv2.imshow("cnt", original)
        # cv2.waitKey(0)
        x,y,w,h = cv2.boundingRect(c)
        crop = original1[y:y+h, x:x+w]
        gray1 = cv2.cvtColor(crop, cv2.COLOR_BGR2GRAY)
        # cv2.imshow("cropp",crop)
        # cv2.waitKey(0)
        kernel = np.zeros((2,2), np.uint8)
        erode = cv2.erode(gray1, kernel,iterations=2)

        cv2.imshow("cropp erode", erode)
        cv2.waitKey(0)
        text = pytesseract.image_to_string(erode, config=config)
        print(text)

The Input Image

I am getting blunder texts using the ocr directly on the complete image. Then I tried cropping each block and then feeding into OCR still I am not getting good results. If someone knows better way please help me with this

Answer 1

try to:

1. remove all the lines.
2. connect the components(numbers) vertically.
3. find contours(columns of text) and sort them from left to right.
4. slice the image according to the column contours.
5. pass individual slices to tesseract with appropriate psm value whitelisting digits.

hope this solves your problem.