Open-source table detection model for table-transformer-detection-ifrs - Optimize IFRS documents and excel at recognizing borderless tables

Table Transformer Detection Ifrs

Developed by apkonsta

A table detection model optimized for International Financial Reporting Standards (IFRS) PDF documents, excelling in processing borderless tables

Object Detection

Transformers

#IFRS table detection #Borderless table recognition #Financial document parsing

Downloads 3,025

Release Time : 11/24/2024

Model Overview

A table detection model based on the Table Transformer architecture, optimized for table elements in IFRS financial documents, particularly adept at detecting borderless tables in scanned documents

Model Features

Borderless table detection

Specially optimized for detecting borderless tables, suitable for complex table structures in scanned documents

Rotated table recognition

Capable of detecting and classifying both regular tables and rotated tables

IFRS document optimization

Trained and optimized for the special formats of International Financial Reporting Standards documents

Model Capabilities

PDF document table detection

Image table recognition

Borderless table localization

Table type classification

Use Cases

Financial document processing

IFRS report table extraction

Automatically extract table data from International Financial Reporting Standards documents

Accurately identifies table regions in documents, including borderless tables

Financial document digitization

Convert tables in scanned financial documents into structured data

Improves document processing efficiency and reduces manual annotation workload

Document analysis

Table data extraction

Extract table content from various document formats

Provides structured input for downstream data analysis tasks

🚀 Table Transformer for IFRS Table Detection

This project offers a fine - tuned Table Transformer model for detecting tables in IFRS PDFs, leveraging the power of the Transformer architecture to handle unstructured document data.

🚀 Quick Start

This repository contains a fine - tuned version of the Table Transformer model, specifically adapted for detecting tables in IFRS (International Financial Reporting Standards) PDFs. The model is based on the Table Transformer architecture, which is designed to extract tables from unstructured documents such as PDFs and images.

📚 Documentation

Model Details

Property	Details
Base Model	microsoft/table - transformer - detection
Library	transformers
Training Data	The model was trained on a dataset consisting of 2359 IFRS scans, with a focus on detecting tables without borders.
Classes	The model is trained to detect two classes: 0 - table (regular tables) and 1 - table_rotated (rotated tables).

Example Image

model image

💻 Usage Examples

Basic Usage

from transformers import DetrForObjectDetection, DetrImageProcessor
from PIL import Image
import torch

# Load the image processor and model
# DetrImageProcessor is used to preprocess the images before feeding them to the model
image_processor = DetrImageProcessor()

# Load the pre-trained TableTransformer model for object detection
# This model is specifically trained for detecting tables in IFRS documents
model = TableTransformerForObjectDetection.from_pretrained(
    "apkonsta/table-transformer-detection-ifrs",
)

# Prepare the image
# Open the image file and convert it to RGB format
image = Image.open("path/to/your/ifrs_pdf_page.png").convert("RGB")

# Table detection threshold
# Set a threshold for detecting tables; only detections with a confidence score above this threshold will be considered
TD_th = 0.5

# Preprocess the image using the image processor
# The image is encoded into a format that the model can understand
encoding = image_processor(image, return_tensors="pt")

# Perform inference without computing gradients (saves memory and computations)
with torch.no_grad():
    outputs = model(**encoding)

# Get the probabilities for each detected object
# The softmax function is applied to the logits to get probabilities
probas = outputs.logits.softmax(-1)[0, :, :-1]

# Keep only the detections with a confidence score above the threshold
keep = probas.max(-1).values > TD_th

# Get the target sizes for post-processing
# The target sizes are the dimensions of the original image
target_sizes = torch.tensor(image.size[::-1]).unsqueeze(0)

# Post-process the model outputs to get the final bounding boxes
# The bounding boxes are scaled back to the original image size
postprocessed_outputs = image_processor.post_process(outputs, target_sizes)
bboxes_scaled = postprocessed_outputs[0]["boxes"][keep]

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご