AIbase
EN
Home
Table Transformer Structure Recognition V1.1 Fin
T

Table Transformer Structure Recognition V1.1 Fin

Developed by microsoft
A table structure recognition model based on the DETR architecture, specifically designed for detecting and analyzing table structures in documents.
Text Recognition
Transformers
Open Source License:MIT#Table Structure Recognition#Document Processing#Transformer Architecture
Downloads 575
Release Time : 11/18/2023

Model Overview

This model is trained on the FinTabNet.c dataset and is primarily used for recognizing table structures in documents, supporting table detection and structural analysis.

Model Features

Transformer-based Detection
Utilizes the DETR architecture with Transformers for table detection and structure recognition.
Pre-Layer Normalization
Applies layer normalization before self-attention and cross-attention to enhance model performance.
Pre-trained Model
Pre-trained on the FinTabNet.c dataset, ready for direct use in table recognition tasks.

Model Capabilities

Table Detection
Table Structure Recognition
Document Analysis

Use Cases

Document Processing
PDF Table Extraction
Automatically identifies and extracts table data from PDF documents.
Accurately recognizes table positions and structures, facilitating subsequent data extraction.
Financial Report Analysis
Automatically identifies tables in financial reports for data analysis and processing.
Improves efficiency in financial data processing and reduces manual intervention.
Data Mining
Structured Data Extraction
Extracts table data from unstructured documents and converts it into a structured format.
Supports output in formats like CSV and Excel for further analysis.
Featured Recommended AI Models
AIbase
Empowering the Future, Your AI Solution Knowledge Base
English简体中文繁體中文にほんご
© 2025AIbase