4.6 Article

Enhanced Feature Model Based Hybrid Neural Network for Text Detection on Signboard, Billboard and News Tickers

Related references

Note: Only part of the references are listed.
Article Computer Science, Artificial Intelligence

Real-Time Scene Text Detection With Differentiable Binarization and Adaptive Scale Fusion

Minghui Liao et al.

Summary: Recently, segmentation-based scene text detection methods have gained attention due to their ability to detect text instances of arbitrary shapes and extreme aspect ratios. However, existing methods are limited by complex post-processing algorithms and scale robustness of segmentation models. In this paper, a Differentiable Binarization (DB) module is proposed to integrate the binarization process into a segmentation network, improving the accuracy of text detection. Additionally, an Adaptive Scale Fusion (ASF) module is proposed to enhance scale robustness. By incorporating these modules, the proposed scene text detector achieves state-of-the-art results on five standard benchmarks in terms of detection accuracy and speed.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2023)

Article Computer Science, Artificial Intelligence

Scene text recognition via context modeling for low-quality image in logistics industry

Herui Heng et al.

Summary: Text recognition has been widely applied in various fields, but there is limited research on the recognition of curved, distorted, and low-resolution text in the logistics field. This study proposes a new method that addresses this research gap by considering irregular and low-resolution English letters. The method includes different modules such as rectification, CNN extractor, semantic context, global context, and lightweight transformer decoder. Experimental results demonstrate that the method improves robustness for low-resolution and irregular text images.

COMPLEX & INTELLIGENT SYSTEMS (2023)

Article Engineering, Electrical & Electronic

Robust Scene Text Detection for Partially Annotated Training Data

Prateek Keserwani et al.

Summary: This article analyzes the impact of training data with partial annotations on scene text detection and proposes a text region refinement approach to address it. The proposed method refines text regions by generating pseudo-labels, resulting in significant improvement over existing approaches for partially annotated training data.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Article Engineering, Electrical & Electronic

Industrial Scene Text Detection With Refined Feature-Attentive Network

Tongkun Guan et al.

Summary: In this paper, a refined feature-attentive network (RFN) is proposed to tackle the challenging task of detecting marking characters on industrial metal parts. By utilizing a parallel feature integration mechanism and an attentive proposal refinement module, the RFN method achieves accurate localization of low-contrast and corroded text areas.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY (2022)

Article Computer Science, Information Systems

GMIF: A Gated Multiscale Input Feature Fusion Scheme for Scene Text Detection

Tofik Ali et al.

Summary: The GMIF approach proposed in this study achieves precise localization of text instances of different sizes through feature fusion and gated recurrent unit mechanism. Experimental results demonstrate the consistent and superior performance of the GMIF method on various datasets.

IEEE ACCESS (2022)

Article Computer Science, Information Systems

Accurate Scene Text Detection Via Scale-Aware Data Augmentation and Shape Similarity Constraint

Pengwen Dai et al.

Summary: This paper presents an arbitrary-shape scene text detection method that achieves better generalization ability and more accurate localization through Scale-Aware Data Augmentation (SADA) and Shape Similarity Constraint (SSC) techniques. Extensive experiments demonstrate the effectiveness of the proposed techniques over public benchmarks.

IEEE TRANSACTIONS ON MULTIMEDIA (2022)

Article Computer Science, Information Systems

Anomaly Detection in Natural Scene Images Based on Enhanced Fine-Grained Saliency and Fuzzy Logic

Hamam Mokayed et al.

Summary: This paper presents a method for anomaly detection in natural scene images, which has made significant progress in improving natural scene text detection and recognition. The method classifies text and non-text components by exploring saliency maps and rough set theory, showing efficacy in text detection and recognition based on experimental results.

IEEE ACCESS (2021)

Article Engineering, Electrical & Electronic

Based on Improved Edge Detection Algorithm for English Text Extraction and Restoration From Color Images

Jianbo Xu et al.

IEEE SENSORS JOURNAL (2020)

Article Computer Science, Information Systems

FDTA: Fully Convolutional Scene Text Detection With Text Attention

Yongcun Cao et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

Cursive Character Recognition in Natural Scene Images Using a Multilevel Convolutional Neural Network Fusion

Asghar Ali Chandio et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

RNTR-Net: A Robust Natural Text Recognition Network

Qiaokang Liang et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

Two-Step CNN Framework for Text Line Recognition in Camera-Captured Images

Yulia S. Chernyshova et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

Text Detection and Recognition for Images of Medical Laboratory Reports With a Deep Learning Approach

Wenyuan Xue et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

Urdu-Text Detection and Recognition in Natural Scene Images Using Deep Learning

Syed Yasser Arafat et al.

IEEE ACCESS (2020)

Article Computer Science, Artificial Intelligence

ASTER: An Attentional Scene Text Recognizer with Flexible Rectification

Baoguang Shi et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2019)

Article Computer Science, Artificial Intelligence

Reading scene text with fully convolutional sequence modeling

Yunze Gao et al.

NEUROCOMPUTING (2019)

Proceedings Paper Computer Science, Information Systems

Signboard Detection and Text Recognition Using Artificial Neural Networks

Muhammad A. Panhwar et al.

PROCEEDINGS OF 2019 IEEE 9TH INTERNATIONAL CONFERENCE ON ELECTRONICS INFORMATION AND EMERGENCY COMMUNICATION (ICEIEC 2019) (2019)

Article Computer Science, Artificial Intelligence

TextBoxes plus plus : A Single-Shot Oriented Scene Text Detector

Minghui Liao et al.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2018)

Proceedings Paper Computer Science, Artificial Intelligence

Multi-Oriented Scene Text Detection via Corner Localization and Region Segmentation

Pengyuan Lyu et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Proceedings Paper Computer Science, Artificial Intelligence

AON: Towards Arbitrarily-Oriented Text Recognition

Zhanzhan Cheng et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Article Computer Science, Artificial Intelligence

An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition

Baoguang Shi et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

Article Computer Science, Artificial Intelligence

TextProposals: A text-specific selective search algorithm for word spotting in the wild

Lluis Gomez et al.

PATTERN RECOGNITION (2017)

Article Computer Science, Information Systems

A Novel Text Structure Feature Extractor for Chinese Scene Text Detection and Recognition

Xiaohang Ren et al.

IEEE ACCESS (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Max-Pooling based Scene Text Proposal for Scene Text Detection

Dinh Nguyen Van et al.

2017 14TH IAPR INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR), VOL 1 (2017)

Article Computer Science, Artificial Intelligence

Reading Text in the Wild with Convolutional Neural Networks

Max Jaderberg et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2016)

Proceedings Paper Computer Science, Artificial Intelligence

FASText: Efficient Unconstrained Scene Text Detector

Michal Busta et al.

2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2015)