---

ProtonX OCR tool: Table Detector

Only 11MB size

[![GitHub](https://img.shields.io/badge/ProtonX-GitHub-black?logo=github)](https://github.com/protonx-engineering/protonx-text-correction) [![HuggingFace](https://img.shields.io/badge/HuggingFace-Model-black?logo=huggingface)](https://huggingface.co/protonx-models/protonx-tc) [![Website](https://img.shields.io/badge/protonx.co-Website-blue)](https://protonx.co) [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1V9B38kbQP17RR0-WqVcPt0R7C5RiZ1_x?usp=sharing)

## **Introduction** This model helps ProtonX support customers in reducing OCR processing costs. For documents that do not contain tables, ProtonX routes them to open-source OCR models such as Dots OCR or DeepSeek OCR. For documents with complex tables, ProtonX routes them to more powerful OCR models such as Gemini OCR, ensuring high accuracy where it matters most. This model is a **binary image classification model** designed to determine **whether an input document image contains at least one table**. ![](https://storage.googleapis.com/mle-courses-prod/users/61b6fa1ba83a7e37c8309756/private-files/db73d3b0-e180-11f0-b179-8566ca0312de-table_detection_examples.png) Built on MobileNetV2 architecture, the model is optimized for **document images and scanned PDFs**, especially **Vietnamese documents**, and is intended to be used as a **fast pre-filtering step** in OCR and document understanding pipelines. --- ## **Task Definition** **Task**: Binary image classification **Objective**: Detect **table presence** in an image ### **Labels** | ID | Label | Meaning | |--|--|--| | 0 | `no_table` | Image contains **no tables** | | 1 | `table` | Image contains **one or more tables** | > ⚠️ The model detects **presence**, not the number or location of tables. --- ## **Training Data** The model is trained using a combination of: ### **DocLayNet Dataset** - Public document layout dataset - High-quality annotations - Diverse document layouts ### **In-house Labeled Vietnamese Document Dataset** - Scanned PDFs from Vietnamese legal documents - Mixed-quality OCR inputs - Real-world layouts: - Contracts - Administrative forms - Reports - Tables embedded in text-heavy pages This combination improves **generalization** across both clean and noisy document images. ## **Quick Usage** ### Using torchvision ```python import torch import torch.nn as nn import torchvision from torchvision import transforms from torchvision import models as pretrained_models from PIL import Image from huggingface_hub import hf_hub_download class TableDetector: def __init__(self, model_name: str, device: str = 'cpu'): self.device = torch.device(device) self.model_path = hf_hub_download(repo_id=model_name, filename="model/table_detector.pth") self.model = self.load_model(self.model_path) self.model.to(self.device) self.model.eval() def load_model(self, model_path: str): model = pretrained_models.mobilenet_v2(weights=None) model.classifier[1] = nn.Linear(in_features=model.classifier[1].in_features, out_features=2) model.load_state_dict(torch.load(model_path, map_location=self.device)) return model def preprocess_image(self, image_path: str): transform = transforms.Compose([ transforms.Resize((224, 224)), transforms.ToTensor(), ]) image = Image.open(image_path).convert('RGB') image = transform(image).unsqueeze(0) # Add batch dimension return image.to(self.device) def predict(self, image_path: str): image = self.preprocess_image(image_path) with torch.no_grad(): outputs = self.model(image) _, preds = torch.max(outputs, 1) return 'have_table' if preds.item() == 1 else 'no_table' if __name__ == "__main__": model = TableDetector(model_name='protonx-models/table-detector', device='cpu') prediction = model.predict("images/document_page_01.png") print(prediction) ``` ### Using ProtonX library ```python from protonx import ProtonX client = ProtonX( mode="offline" ) prediction = client.ocr.detect_table(image_path="images/document_page_01.png") print(prediction) ``` ## **Acknowledgments** Thanks to: * [DocLayNet](https://huggingface.co/datasets/docling-project/DocLayNet)