Oct 21, 2021 · We propose an innovative Scale-Guided Regression Module (SRM), specially for multi-orientation scene text detection.
A deep direct regression based method for multi-oriented scene text detection that achieves the F-measure of 81%, which is a new state-of-the-art and ...
In this paper, we first provide a new perspective to di- vide existing high performance object detection methods into direct and indirect regressions.
Missing: guided | Show results with:guided
Jul 16, 2024 · To address the problem of low detection rate caused by the close alignment and multi-directional position of text words in practical ...
Dec 21, 2020 · We propose a new network with Attention Module and Image Pyramid Module, based on EAST but largely ameliorated, to overcome the obstacles.
May 30, 2024 · In this paper, we introduce “Detect Any Text” (DAT), an advanced paradigm that seamlessly unifies scene text detection, layout analysis, and document page ...
This paper proposes a scene text detection framework based on fully convolutional network with a bi-task prediction module, in which one is a pixel-wise ...
Text detection in natural scene images is an important prerequisite for many content-based image analysis tasks, while most current research efforts only ...
Scene text detection methods can be devided into four parts: (a) Traditional methods; (b) Segmentation-based methods; (c) Regression-based methods; (d) Hybrid ...
Compared to horizontal bounding box representation, additional variables such as the angle or ver- tex coordinates are required for representing multi-oriented.