MSRA-TD500

MSRA Text Detection 500 Database (MSRA-TD500) The MSRA Text Detection 500 Database (MSRA-TD500) is a publicly released benchmark designed to evaluate text detection algorithms. This dataset aims to track recent progresses in the field of text detection within natural images, particularly focusing on texts of arbitrary orientations. Dataset Overview MSRA-TD500 contains 500 natural images sourced from indoor (e.g., office and mall) and outdoor (e.g., street) scenes captured… See the full description on the dataset page: https://huggingface.co/datasets/yunusserhat/MSRA-TD500-Dataset.

Papers using MSRA-TD500 (6)

Inceptext: A New Inception-text Module With Deformable PSROI Pooling For Multi-oriented Scene Text Detection2018 · 120 citesOmnidirectional Scene Text Detection With Sequential-free Box Discretization2019 · 97 citesFused Text Segmentation Networks for Multi-oriented Scene Text Detection2017 · 25 citesSelf-training For Domain Adaptive Scene Text Detection2020 · 22 citesEfficient Scene Text Detection With Textual Attention Tower2020 · 7 citesScale-invariant Multi-oriented Text Detection In Wild Scene Images2020 · 6 cites