RNTR-Net: A Robust Natural Text Recognition Network
In this work, a novel robust natural text recognition network (RNTR-Net) is proposed based on a combination of convolutional neural network (CNN) (for feature extraction) and a recurrent neural network (RNN) (for sequence recognition). The pipeline design comprises an improved block of residual lear...
Main Authors: | Qiaokang Liang, Shao Xiang, Yaonan Wang, Wei Sun, Dan Zhang |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8950043/ |
Similar Items
-
BS-LSTM: An Ensemble Recurrent Approach to Forecasting Soil Movements in the Real World
by: Praveen Kumar, et al.
Published: (2021-08-01) -
Bidirectional Attention for Text-Dependent Speaker Verification
by: Xin Fang, et al.
Published: (2020-11-01) -
Robust Multi-Feature Learning for Skeleton-Based Action Recognition
by: Yingfu Wang, et al.
Published: (2019-01-01) -
Gesture Recognition Based on CNN and DCGAN for Calculation and Text Output
by: Wei Fang, et al.
Published: (2019-01-01) -
Natural Scene Text Recognition Based on Encoder-Decoder Framework
by: Ling-Qun Zuo, et al.
Published: (2019-01-01)