I want to create a table OCR with table transformer

Beginners
1

Hi everyone !

I want to create a table OCR for read invoices but my code returns random cuts.

from PIL import Image
from transformers import DetrImageProcessor,TableTransformerForObjectDetection,DetrFeatureExtractor,AutoImageProcessor,AutoFeatureExtractor,AutoModelForObjectDetection
import torch

def table_detector(image):
processor = AutoImageProcessor.from_pretrained(“microsoft/table-transformer-detection”)
model = TableTransformerForObjectDetection.from_pretrained(“microsoft/table-transformer-detection”)
with torch.no_grad():
inputs = processor(images=image, return_tensors=“pt”)
outputs = model(**inputs)
target_sizes = torch.tensor([image.size[::-1]])
results = processor.post_process_object_detection(outputs, threshold=0.9, target_sizes=target_sizes)[0]

for score, label, box in zip(results[“scores”], results[“labels”], results[“boxes”]):
box = [round(i, 2) for i in box.tolist()]
x, y, w, h = tuple(box)
return image.crop((x, y, x + w, y + h))

def table_struct_recog(image):
feature_extractor = AutoFeatureExtractor.from_pretrained(“microsoft/table-transformer-structure-recognition”)
model = AutoModelForObjectDetection.from_pretrained(“microsoft/table-transformer-structure-recognition”)
inputs = feature_extractor(images=image, return_tensors=“pt”)
outputs = model(**inputs)
target_sizes = torch.tensor([image.size[::-1]])
results = feature_extractor.post_process_object_detection(outputs, threshold=0.9, >target_sizes=target_sizes)[0]
i=0
for score, label, box in zip(results[“scores”], results[“labels”], results[“boxes”]):
box = [round(i, 2) for i in box.tolist()]
x, y, w, h = tuple(box)
image.crop((x, y, x + w, y + h)).save(str(i)+“.jpg”)
i = i+1

if name == “main”:
image = Image.open(“facture.jpg”).convert(“RGB”)
image = table_detector(image)
table_struct_recog(image)

Thanks for your help :slight_smile: