Hi all, I'm learning tesseract in python and I'm trying to detect all the text regions using pytesseract.image_to_data() and then extract the text from each region one by one. My code below attempts to do this: import cv2 import pytesseract from pytesseract import Output pytesseract.pytesseract.tesseract_cmd = r'C:\Program Files\Tesseract-OCR\tesseract.exe'
img = cv2.imread('cocacola_19.png') d = pytesseract.image_to_data(img, output_type=Output.DICT) n_boxes = len(d['text']) img_rect = img.copy() c=0 for i in range(n_boxes): if int(d['conf'][i]) > 50: (x1, y1, w1, h1) = (d['left'][i], d['top'][i], d['width'][i], d[ 'height'][i]) img_rect = cv2.rectangle(img_rect, (x1, y1), (x1 + w1, y1 + h1), (0, 255, 0), 2) # cv2.imwrite('rect.jpg', img[y1:y1+h1, x1:x1+w1]) out = pytesseract.image_to_string(img[y1:y1+h1, x1:x1+w1]) if(len(out)==0): out = pytesseract.image_to_string(img[y1:y1+h1, x1:x1+w1], config='--psm 3') c+=1 However, it does not work. For example, the first region of text contains 'THE'. But pytesseract.image_to_string() returns an empty string. Why does this happen? My input image is attached. Thanks in advance -- You received this message because you are subscribed to the Google Groups "tesseract-ocr" group. To unsubscribe from this group and stop receiving emails from it, send an email to tesseract-ocr+unsubscr...@googlegroups.com. To view this discussion on the web visit https://groups.google.com/d/msgid/tesseract-ocr/99a956f6-ff6b-4c4b-b12b-880e74f44844o%40googlegroups.com.