OpenCV MSER detect text areas - Python

Question

I have an invoice image, and I want to detect the text on it. So I plan to use 2 steps: first is to identify the text areas, and then using OCR to recognize the text.

<

Answer 1

This is an old post, yet I'd like to contribute that if you are trying to extract all the texts out of an image, here is the code to get that text in an array.

import cv2
import numpy as np
import re
import pytesseract
from pytesseract import image_to_string
pytesseract.pytesseract.tesseract_cmd = r"C:\Program Files\Tesseract-OCR\tesseract.exe"
from PIL import Image

image_obj = Image.open("screenshot.png")

rgb = cv2.imread('screenshot.png')
small = cv2.cvtColor(rgb, cv2.COLOR_BGR2GRAY)

#threshold the image
_, bw = cv2.threshold(small, 0.0, 255.0, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)

# get horizontal mask of large size since text are horizontal components
kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (20, 1))
connected = cv2.morphologyEx(bw, cv2.MORPH_CLOSE, kernel)

# find all the contours
contours, hierarchy,=cv2.findContours(connected.copy(),cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)
#Segment the text lines
counter=0
array_of_texts=[]
for idx in range(len(contours)):
    x, y, w, h = cv2.boundingRect(contours[idx])
    cropped_image = image_obj.crop((x-10, y, x+w+10, y+h ))
    str_store = re.sub(r'([^\s\w]|_)+', '', image_to_string(cropped_image))
    array_of_texts.append(str_store)
    counter+=1

print(array_of_texts)

Answer 2

Below is the code

# Import packages 
import cv2
import numpy as np

#Create MSER object
mser = cv2.MSER_create()

#Your image path i-e receipt path
img = cv2.imread('/home/rafiullah/PycharmProjects/python-ocr-master/receipts/73.jpg')

#Convert to gray scale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

vis = img.copy()

#detect regions in gray scale image
regions, _ = mser.detectRegions(gray)

hulls = [cv2.convexHull(p.reshape(-1, 1, 2)) for p in regions]

cv2.polylines(vis, hulls, 1, (0, 255, 0))

cv2.imshow('img', vis)

cv2.waitKey(0)

mask = np.zeros((img.shape[0], img.shape[1], 1), dtype=np.uint8)

for contour in hulls:

    cv2.drawContours(mask, [contour], -1, (255, 255, 255), -1)

#this is used to find only text regions, remaining are ignored
text_only = cv2.bitwise_and(img, img, mask=mask)

cv2.imshow("text only", text_only)

cv2.waitKey(0)