-
-
Save cryzed/8874f9cc2a4ccf7b10ca78bc115982cc to your computer and use it in GitHub Desktop.
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 argparse | |
import os | |
import subprocess | |
import tempfile | |
import PIL.Image | |
import imagehash | |
DATA_OFFSET = 270, 0 | |
DATA_PADDING_RIGHT = 211 | |
FONT_PADDING = 1 | |
FONT_WIDTH = 19 | |
FONT_HEIGHT = 39 | |
CHARACTERS_PATH = 'characters' | |
HASH_SIZE = 8 | |
argument_parser = argparse.ArgumentParser() | |
argument_parser.add_argument('path') | |
_character_hashes = {} | |
def recognize_character(character_image): | |
hash = imagehash.average_hash(character_image, HASH_SIZE) | |
result = list(sorted(_character_hashes.items(), key=lambda item: item[1] - hash)) | |
return result[0][0] | |
def extract_frames(path): | |
destination = tempfile.mkdtemp() | |
subprocess.run(['ffmpeg', '-i', path, '-r', '1/1', os.path.join(destination, '%05d.png')], stdout=subprocess.DEVNULL, | |
stderr=subprocess.DEVNULL) | |
return destination | |
def extract_frame_characters(frame): | |
x, y = DATA_OFFSET | |
max_width, max_height = frame.size | |
max_width -= DATA_PADDING_RIGHT | |
index = 0 | |
characters = [] | |
while y <= max_height: | |
character_image = frame.crop((x, y, x + FONT_WIDTH, y + FONT_HEIGHT)) | |
character = recognize_character(character_image) | |
characters.append(character) | |
index += 1 | |
x += FONT_WIDTH + FONT_PADDING | |
if x >= max_width: | |
x = DATA_OFFSET[0] | |
y += FONT_HEIGHT + FONT_PADDING | |
return ''.join(characters).replace(' ', '') | |
def initialize_data(): | |
for filename in os.listdir(CHARACTERS_PATH): | |
path = os.path.join(CHARACTERS_PATH, filename) | |
character = os.path.splitext(filename)[0] | |
image = PIL.Image.open(path) | |
_character_hashes[character] = imagehash.average_hash(image, HASH_SIZE) | |
_character_hashes['/'] = _character_hashes['slash'] | |
del _character_hashes['slash'] | |
def main(arguments): | |
initialize_data() | |
frame_destination = extract_frames(arguments.path) | |
for filename in sorted(os.listdir(frame_destination)): | |
path = os.path.join(frame_destination, filename) | |
image = PIL.Image.open(path) | |
characters = extract_frame_characters(image) | |
print(filename, len(characters)) | |
if __name__ == '__main__': | |
arguments = argument_parser.parse_args() | |
argument_parser.exit(main(arguments)) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment