searchanddisplace-ingest/resources/python/ocr/localize_text_tesseract.py

import cv2

image = cv2.imread("logo.jpg", 1)

img = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

cv2.threshold(img, 0, 255, cv2.THRESH_BINARY+cv2.THRESH_OTSU, img)
cv2.bitwise_not(img, img)

rect_kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (30, 5))

img = cv2.morphologyEx(img, cv2.MORPH_CLOSE, rect_kernel)
contours, hier = cv2.findContours(img, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_NONE)

if len(contours) != 0:
    ROI_number = 0
    for c in contours:
        x,y,w,h = cv2.boundingRect(c)

        # Depends on text size, so the greater the value the less objects we get.
        if (h > 50):
            cv2.rectangle(image, (x,y), (x+w,y+h), (0,0,255), 1)

            ROI = image[y:y+h, x:x+w]
            cv2.imwrite('results/ROI_{}.png'.format(ROI_number), ROI)
            ROI_number += 1

cv2.imshow("Result", image)
cv2.waitKey(0)