Created
April 19, 2024 06:37
-
-
Save priyanlc/05c4cee417352b7047b6c572668f7131 to your computer and use it in GitHub Desktop.
Delete Images with characters with easyocr
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import os | |
import easyocr | |
class EasyOCRProcessor: | |
def __init__(self, languages=None): # Default to Japanese | |
if languages is None: | |
languages = ['ja'] | |
self.reader = easyocr.Reader(languages) | |
def process_image(self, filename): | |
try: | |
results = self.reader.readtext(filename, detail=0, paragraph=True) | |
japanese_text_detected = len(results) > 0 | |
if japanese_text_detected: | |
os.remove(filename) | |
return f"Deleted '{filename}' as Japanese text was detected." | |
else: | |
return f"Kept '{filename}', no Japanese text detected." | |
except Exception as e: | |
return f"Error processing '{filename}': {e}, kept the file." |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment