I want rectangles to be painted over the original words and put new words on top of them, but when i do that the main rectangle is painted full screen, how to exclude it from painting?
https://i.stack.imgur.com/SmUca.jpg - before painting
https://i.stack.imgur.com/1KGqF.jpg - after painting
img = cv2.imread('C:\\Users\\booba\\PycharmProjects\\MySchoolProject\\21.png')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
config = r'--oem 3 --psm 4'
data = pytesseract.image_to_data(img, config=config, lang='eng')
for i, el in enumerate(data.splitlines()):
if i == 0:
continue
el = el.split()
try:
x, y, w, h = int(el[6]), int(el[7]), int(el[8]), int(el[9])
a = cv2.rectangle(img, (x,y), (w x, h y), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_COMPLEX
print(el[11])
cv2.putText(img, el[11], (x, y), font, 1, (0,0,0), 3)
cv2.putText(img, el[11], (x, y), font, 1, (255, 255, 255), 2)
except IndexError:
continue
CodePudding user response:
You can check if a text is included in the line data:
import cv2
import pytesseract
img = cv2.imread('test-ocr.png')
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
config = r'--oem 3 --psm 4'
data = pytesseract.image_to_data(img, config=config, lang='eng')
print(data)
for i, line in enumerate(data.splitlines()):
if i == 0:
# ignore header line
continue
el = line.split()
x, y, w, h = int(el[6]), int(el[7]), int(el[8]), int(el[9])
if len(el) > 11:
text = el[11]
if text:
# only draw box if text was found
a = cv2.rectangle(img, (x,y), (w x, h y), (0, 0, 255), 2)
font = cv2.FONT_HERSHEY_COMPLEX
cv2.putText(img, text, (x, y), font, 1, (0,0,0), 3)
cv2.putText(img, text, (x, y), font, 1, (255, 255, 255), 2)
cv2.imwrite('boxes.png', img)