SCUT-DLVCLab

Document-AI-Recommendations

Algorithms, papers, datasets, performance comparisons for Document AI. Continuously updating.

GPT-4V_OCR

Evaluation of the Optical Character Recognition (OCR) capabilities of GPT-4V(ision)

RFUND

Official release of RFUND introduced in the paper "PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction" (arXiv:2401.03472).

SCUT-EnsExam

SCUT-EnsExam is a real-world handwritten text erasure dataset for examination paper scenarios, which consists of 545 examination paper images. The dataset is randomly divided into training set and test set of 430 and 115 images, respectively.

Mnist-99.7-Accuracy-with-Pytorch

A CNN model builds with Pytorch and reaches 99.7% accuracy

MegaHan97K

MegaHan97K: A Large-Scale Dataset for Mega-Category Chinese Character Recognition with over 97K Categories

WenMind

WenMind benchmark.

.github

C3bench

C3 benchmark