AT-Text: Assembling Text Components for Efficient Dense Scene Text Detection

AT-Text: Assembling Text Components for Efficient Dense Scene Text Detection

Text detection is a prerequisite for text recognition in scene images. Previous segmentation-based methods for detecting scene text have already achieved a promising performance. However, these kinds of approaches may produce spurious text instances, as they usually confuse the boundary of dense tex...

Full description

Bibliographic Details
Main Authors: Haiyan Li, Hongtao Lu
Format: Article
Language:English
Published: MDPI AG 2020-11-01
Series:Future Internet
Subjects:
scene text detection
segmentation model
Convolutional Neural Network (CNN)
bottom-up mechanism
Online Access:https://www.mdpi.com/1999-5903/12/11/200

Internet

https://www.mdpi.com/1999-5903/12/11/200

Similar Items