Text Detector
Text detection, the automated identification of text within images or documents, aims to improve efficiency and accuracy in various applications. Current research focuses on enhancing the robustness and speed of text detectors, exploring architectures like transformers and incorporating techniques such as contextual reasoning and adaptive shrink-masks to handle diverse text shapes, sizes, and challenging conditions like low light. These advancements are crucial for applications ranging from automated document processing and educational assessment to content moderation and accessibility tools, impacting fields like computer vision, natural language processing, and digital humanities.
Papers
September 7, 2022
July 26, 2022
July 4, 2022
January 20, 2022
December 14, 2021
November 18, 2021