PaddleOCR

PaddleOCR Layout Analysis¶

Here we use PaddleOCR to detect analyze, its a example, and how it will ideally run.

In [ ]:

from omnidocs.tasks.layout_analysis.extractors.paddle import PaddleLayoutDetector

from omnidocs.tasks.layout_analysis.extractors.paddle import PaddleLayoutDetector

Once we import, we call the PaddleLayout detector and pass

In [ ]:

detector = PaddleLayoutDetector(device='cpu',show_log=True)
image_path = "assets/news_paper.png"
annotated_image, layout_output = detector.detect(image_path)
print(f"Detected {len(layout_output.bboxes)} elements")

print("Saving visualization...")
output_path = "tests/layout_detectors/output/paddle_result.png"
detector.visualize((annotated_image, layout_output), output_path)
print(f"✓ Saved visualization to {output_path}")

detector = PaddleLayoutDetector(device='cpu',show_log=True) image_path = "assets/news_paper.png" annotated_image, layout_output = detector.detect(image_path) print(f"Detected {len(layout_output.bboxes)} elements") print("Saving visualization...") output_path = "tests/layout_detectors/output/paddle_result.png" detector.visualize((annotated_image, layout_output), output_path) print(f"✓ Saved visualization to {output_path}")

In [ ]:

from IPython.display import Image, display
# Display in notebook
display(Image(output_path))

from IPython.display import Image, display # Display in notebook display(Image(output_path))