A Multi-Level Feature Fusion Network For Scene Text Detection with Text Attention Mechanism

In the last years, methods for detecting text in real scenes have made significant progress with an increase in neural networks. However, due to the limitation of the receptive field of the central nervous system and the simple representation of text by using rectangular bounding boxes, the previous methods may be insufficient for working with more challenging instances of text. To solve this problem, this paper proposes a scene text detection network based on cross-scale feature fusion (CSFF-Net). The framework is based on the lightweight backbone network Resnet, and the feature learning is enhanced by embedding the depth weighted convolution module (DWCM) while retaining the original feature information extracted by CNN. At the same time, the 3D-Attention module is also introduced to merge the context information of adjacent areas, so as to refine the features in each spatial size. In addition, because the Feature Pyramid Network (FPN) cannot completely solve the interdependence problem by simple element-wise addition to process cross-layer information flow, this paper introduces a Cross-Level Feature Fusion Module (CLFFM) based on FPN, which is called Cross-Level Feature Pyramid Network (Cross-Level FPN). The proposed CLFFM can better handle cross-layer information flow and output detailed feature information, thus improving the accuracy of text region detection. Compared to the original network framework, the framework provides a more advanced performance in detecting text images of complex scenes, and extensive experiments on three challenging datasets validate the realizability of our approach.

Download Full-text

Arbitrary Shape Natural Scene Text Detection Method Based on Soft Attention Mechanism and Dilated Convolution

IEEE Access ◽

10.1109/access.2020.3007351 ◽

2020 ◽

Vol 8 ◽

pp. 122685-122694

Author(s):

Xiao Qin ◽

Jianhui Jiang ◽

Chang-An Yuan ◽

Shaojie Qiao ◽

Wei Fan

Keyword(s):

Arbitrary Shape ◽

Detection Method ◽

Text Detection ◽

Attention Mechanism ◽

Natural Scene ◽

Dilated Convolution ◽

Scene Text Detection ◽

Scene Text

Download Full-text

MFECN: Multi-level Feature Enhanced Cumulative Network for Scene Text Detection

ACM Transactions on Multimedia Computing Communications and Applications ◽

10.1145/3440087 ◽

2021 ◽

Vol 17 (3) ◽

pp. 1-22

Author(s):

Zhandong Liu ◽

Wengang Zhou ◽

Houqiang Li

Keyword(s):

Text Detection ◽

Detection Algorithms ◽

Features Fusion ◽

Irregular Shapes ◽

Scene Text Detection ◽

Scene Text ◽

Text Information ◽

Multi Level ◽

Public Datasets ◽

High Level

Recently, many scene text detection algorithms have achieved impressive performance by using convolutional neural networks. However, most of them do not make full use of the context among the hierarchical multi-level features to improve the performance of scene text detection. In this article, we present an efficient multi-level features enhanced cumulative framework based on instance segmentation for scene text detection. At first, we adopt a Multi-Level Features Enhanced Cumulative ( MFEC ) module to capture features of cumulative enhancement of representational ability. Then, a Multi-Level Features Fusion ( MFF ) module is designed to fully integrate both high-level and low-level MFEC features, which can adaptively encode scene text information. To verify the effectiveness of the proposed method, we perform experiments on six public datasets (namely, CTW1500, Total-text, MSRA-TD500, ICDAR2013, ICDAR2015, and MLT2017), and make comparisons with other state-of-the-art methods. Experimental results demonstrate that the proposed Multi-Level Features Enhanced Cumulative Network (MFECN) detector can well handle scene text instances with irregular shapes (i.e., curved, oriented, and horizontal) and achieves better or comparable results.

Download Full-text

Feature Fusion for Scene Text Detection

2018 13th IAPR International Workshop on Document Analysis Systems (DAS) ◽

10.1109/das.2018.60 ◽

2018 ◽

Cited By ~ 1

Author(s):

Zhen Zhu ◽

Minghui Liao ◽

Baoguang Shi ◽

Xiang Bai

Keyword(s):

Feature Fusion ◽

Text Detection ◽

Scene Text Detection ◽

Scene Text

Download Full-text

Feature Fusion Network for Scene Text Detection

2018 25th IEEE International Conference on Image Processing (ICIP) ◽

10.1109/icip.2018.8451402 ◽

2018 ◽

Cited By ~ 1

Author(s):

Chenqin Cai ◽

Pin Lv ◽

Bing Su

Keyword(s):

Feature Fusion ◽

Text Detection ◽

Scene Text Detection ◽

Scene Text

Download Full-text

TextFuseNet: Scene Text Detection with Richer Fused Features

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/72 ◽

2020 ◽

Author(s):

Jian Ye ◽

Zhe Chen ◽

Juhua Liu ◽

Bo Du

Keyword(s):

Text Detection ◽

Feature Representation ◽

Natural Scenes ◽

Weak Supervision ◽

Feature Representations ◽

General Semantics ◽

Scene Text Detection ◽

Scene Text ◽

Multi Level ◽

Different Levels

Arbitrary shape text detection in natural scenes is an extremely challenging task. Unlike existing text detection approaches that only perceive texts based on limited feature representations, we propose a novel framework, namely TextFuseNet, to exploit the use of richer features fused for text detection. More specifically, we propose to perceive texts from three levels of feature representations, i.e., character-, word- and global-level, and then introduce a novel text representation fusion technique to help achieve robust arbitrary text detection. The multi-level feature representation can adequately describe texts by dissecting them into individual characters while still maintaining their general semantics. TextFuseNet then collects and merges the texts’ features from different levels using a multi-path fusion architecture which can effectively align and fuse different representations. In practice, our proposed TextFuseNet can learn a more adequate description of arbitrary shapes texts, suppressing false positives and producing more accurate detection results. Our proposed framework can also be trained with weak supervision for those datasets that lack character-level annotations. Experiments on several datasets show that the proposed TextFuseNet achieves state-of-the-art performance. Specifically, we achieve an F-measure of 94.3% on ICDAR2013, 92.1% on ICDAR2015, 87.1% on Total-Text and 86.6% on CTW-1500, respectively.

Download Full-text