Last active
February 13, 2024 08:19
-
-
Save companje/32c95f431d2e389a3ba5f97f063b2267 to your computer and use it in GitHub Desktop.
Mac OCR for crops
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
#!/usr/bin/env python3 | |
import shutil,os,cv2,sys,glob | |
from tqdm import tqdm | |
from PIL import Image | |
from pathlib import Path | |
from joblib import Parallel, delayed | |
crop_width = 200 | |
crop_height = 100 | |
output_scale = .33 | |
input_folder = "crops_small/" | |
output_folder = "crops_nummers_small/" | |
if not os.path.exists(output_folder): | |
os.makedirs(output_folder) | |
def do_crop(input_filepath, output_folder, progress): | |
print(str(int(progress*1000)/10.)+"%") | |
filename = input_filepath.strip() | |
basename = os.path.basename(filename) | |
output_filename = output_folder + basename | |
img = Image.open(input_filepath) | |
img = img.crop((0, 0, crop_width, crop_height)) | |
img.save(output_filename) | |
file_paths = glob.glob(input_folder+"*.jpg", recursive=False) | |
print("totaal",len(file_paths)) | |
results = Parallel(n_jobs=1, prefer="threads")( | |
delayed(do_crop)(image_file_path,output_folder, i/len(file_paths)) | |
for i,image_file_path in enumerate(file_paths) | |
) |
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
#!/usr/bin/env python3 | |
import csv,json | |
from tqdm import tqdm | |
from rapidfuzz import fuzz | |
import rapidfuzz.process as fuzzy | |
def fuzzy_extract(input_str, compare_strs): #(result, match_pct, idx) | |
return fuzzy.extractOne(input_str, compare_strs, scorer=fuzz.ratio) | |
header = ["filename","text","corrected"] | |
corrected = csv.DictWriter(open("corrected.csv", 'w', encoding='utf8'), header) | |
corrected.writeheader() | |
count = json.load(open("count_fixed.json")) | |
dictionary = count.keys() | |
for row in tqdm(list(csv.DictReader(open("per-scan.csv")))): | |
result,score,_ = fuzzy_extract(row['text'], dictionary) | |
row['corrected'] = result | |
corrected.writerow(row) |
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
#!/usr/bin/env python3 | |
import shutil,os,cv2,sys | |
from tqdm import tqdm | |
from PIL import Image | |
from pathlib import Path | |
import json,os,subprocess | |
from tqdm import tqdm | |
from joblib import Parallel, delayed | |
import glob,csv | |
import Quartz,Vision | |
from Cocoa import NSURL | |
from Foundation import NSDictionary | |
from wurlitzer import pipes # needed to capture system-level stderr | |
def ocr(image_filename): | |
input_url = NSURL.fileURLWithPath_(image_filename) | |
with pipes() as (out, err): | |
input_image = Quartz.CIImage.imageWithContentsOfURL_(input_url) | |
(width,height) = input_image.extent().size | |
vision_options = NSDictionary.dictionaryWithDictionary_({}) | |
vision_handler = Vision.VNImageRequestHandler.alloc().initWithCIImage_options_( | |
input_image, vision_options | |
) | |
request = Vision.VNRecognizeTextRequest.alloc().init().autorelease() | |
request.setRecognitionLevel_(Vision.VNRequestTextRecognitionLevelAccurate) #VNRequestTextRecognitionLevelFast | |
request.setRecognitionLanguages_(["nl-NL"]) | |
error = vision_handler.performRequests_error_([request], None) | |
results = [] | |
for item in request.results(): | |
bbox = item.boundingBox() | |
w, h = bbox.size.width, bbox.size.height | |
x, y = bbox.origin.x, bbox.origin.y | |
results.append({ | |
"x":int(x*width), | |
"y":int(height - y*height - h*height), | |
"w":int(w*width), | |
"h":int(h*height), | |
"conf":item.confidence(), | |
"text":item.text() | |
}) | |
return results | |
def do_ocr(input_filepath, output_folder, progress): | |
output_filepath = output_folder + os.path.basename(input_filepath) + ".csv" | |
if not os.path.exists(output_filepath): | |
data = ocr(input_filepath) | |
if data and len(data)>0: | |
with open(output_filepath, 'w', encoding='utf8') as file: | |
writer = csv.DictWriter(file, data[0].keys()) | |
writer.writeheader() | |
writer.writerows(data) | |
print(output_filepath,str(int(progress*1000)/10.)+"%") | |
input_folder = "crops_small/" | |
output_folder = "ocr/" | |
if not os.path.exists(output_folder): | |
os.makedirs(output_folder) | |
file_paths = glob.glob(input_folder+"*.jpg", recursive=False) | |
results = Parallel(n_jobs=1, prefer="threads")( | |
delayed(do_ocr)(image_file_path,output_folder, i/len(file_paths)) | |
for i,image_file_path in enumerate(file_paths) | |
) |
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
#!/usr/bin/env python3 | |
from tqdm import tqdm | |
import glob,csv,re,os,json | |
from collections import defaultdict | |
input_folder = "ocr/" | |
counter = defaultdict(int) | |
file_paths = glob.glob(input_folder+"*.csv", recursive=False) | |
file_paths.sort() | |
header = ["filename","text","x","y","w","h","conf"] | |
boxes = csv.DictWriter(open("boxes.csv", 'w', encoding='utf8'), header) | |
boxes.writeheader() | |
header = ["filename","text"] | |
scans = csv.DictWriter(open("per-scan.csv", 'w', encoding='utf8'), header) | |
scans.writeheader() | |
for file_path in tqdm(file_paths): #[:10000]): | |
filename = os.path.basename(file_path) | |
filename = filename.replace(".csv","") | |
words = [] | |
for row in csv.DictReader(open(file_path)): | |
if int(row['x'])<200 and int(row['w'])<300: | |
continue | |
if int(row['x'])>650: | |
continue | |
if int(row['h'])<=10: # datum, aantal etc | |
continue | |
if re.findall("aantal|betrek|betrok|datum",row['text'], re.IGNORECASE): | |
continue | |
words.append(row['text']) | |
row['filename'] = filename | |
boxes.writerow(row) | |
########## | |
text = " ".join(words).strip() | |
text = re.sub("\.$","",text) | |
scans.writerow({ | |
"filename": filename, | |
"text": text | |
}) | |
if text: | |
counter[text] += 1 | |
counter = dict(sorted(counter.items(), key=lambda x:x[1], reverse=True)) | |
json.dump(counter, open("count.json","w"), indent=2, ensure_ascii=False) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment