|
|
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
|
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
|
09 May 2023, Volume 38 Issue 3
|
|
|
Abstract
Natural scene text identification is critical for extracting textual information from natural settings. Natural scene text detection systems are emerging and yielding improved detection results as deep learning technology advances. The analysis and description of the current stage of deep learning-based text methods for natural scenes in this work may be separated into two types: proposal region and semantic segmentation, and the content of these two series of associated techniques is described. Second, we give a publicly available dataset and detection metrics for scene text detection. Finally, the study in scene text identification is summarized and predicted in the expectation of providing novel areas of study for future algorithms.
Keyword
Scene text, deep learning, text detection, LSTM, EAST Algorithm
PDF Download (click here)
|
|
|
|
|