File size: 1,912 Bytes
2a07d13 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 |
from transformers import TrOCRProcessor, VisionEncoderDecoderModel
from PIL import Image
import os
import re
# Load Hugging Face OCR model
processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-stage1")
model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-stage1")
# Directory where patient records are stored
PATIENT_RECORDS_DIR = "records/"
# Function to extract patient name from filename
def extract_patient_name(file_name):
match = re.match(r"([A-Za-z]+[A-Za-z]*)_.*\.(jpg|png|jpeg|pdf)$", file_name)
if match:
return match.group(1)
return None
# OCR function
def extract_text_from_image(image_path):
image = Image.open(image_path).convert("RGB")
pixel_values = processor(images=image, return_tensors="pt").pixel_values
generated_ids = model.generate(pixel_values)
generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
return generated_text.strip()
# Save text to patient record
def save_to_patient_record(patient_name, text):
os.makedirs(PATIENT_RECORDS_DIR, exist_ok=True)
filepath = os.path.join(PATIENT_RECORDS_DIR, f"{patient_name}_records.txt")
with open(filepath, "a") as file:
file.write("\n\n===== New Upload =====\n")
file.write(text)
# Main process
def process_uploaded_lab_result(file_path):
print(f"Processing: {file_path}")
patient_name = extract_patient_name(os.path.basename(file_path))
if not patient_name:
return "❌ Could not determine patient name from filename."
ocr_text = extract_text_from_image(file_path)
save_to_patient_record(patient_name, ocr_text)
return f"✅ OCR completed and saved under {patient_name}'s record."
# Example usage
if __name__ == "__main__":
file_to_upload = "JuanDelaCruz_2025-06-13.jpg" # Example uploaded file
result = process_uploaded_lab_result(file_to_upload)
print(result) |