A Novel Word Spotting Algorithm Using Bidirectional Long Short-Term Memory Neural Networks

被引：0

作者：

Frinken, Volkmar ^{[1
]}

Fischer, Andreas ^{[1
]}

Bunke, Horst ^{[1
]}

机构：

[1] Univ Bern, Inst Comp Sci & Appl Math, CH-3012 Bern, Switzerland

来源：

ARTIFICIAL NEURAL NETWORKS IN PATTERN RECOGNITION, PROCEEDINGS | 2010年 / 5998卷

关键词：

HANDWRITING RECOGNITION;

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Keyword spotting refers to the process of retrieving all instances of a given key word in a document. in the present paper, a novel keyword spotting system for handwritten documents is described. It is derived from a neural network based system for unconstrained handwriting recognition. As such it performs template-free spotting, i.e. it is not necessary for a keyword to appear in the training set. The keyword spotting is done using a modification of the CTC Token Passing algorithm. We demonstrate that such a system has the potential for high performance. For example, a precision of 95% at 50% recall is reached for the 41,000 most frequent words on the IAM offline handwriting database.

引用

下载

页码：185 / 196

页数：12

共 50 条

[1] Twitter Bot Detection Using Bidirectional Long Short-term Memory Neural Networks and Word Embeddings
Wei, Feng
Uyen Trang Nguyen
2019 FIRST IEEE INTERNATIONAL CONFERENCE ON TRUST, PRIVACY AND SECURITY IN INTELLIGENT SYSTEMS AND APPLICATIONS (TPS-ISA 2019), 2019, : 101 - 109
[2] Arabic Word Segmentation With Long Short-Term Memory Neural Networks and Word Embedding
Almuhareb, Abdulrahman
Alsanie, Waleed
Al-Thubaity, Abdulmohsen
IEEE ACCESS, 2019, 7 : 12879 - 12887
[3] Biomedical word sense disambiguation with bidirectional long short-term memory and attention-based neural networks
Zhang, Canlin
Bis, Daniel
Liu, Xiuwen
He, Zhe
BMC BIOINFORMATICS, 2019, 20 (Suppl 16)
[4] Biomedical word sense disambiguation with bidirectional long short-term memory and attention-based neural networks
Canlin Zhang
Daniel Biś
Xiuwen Liu
Zhe He
BMC Bioinformatics, 20
[5] Sleep Stage Classification using Convolutional Neural Networks and Bidirectional Long Short-Term Memory
Yulita, Intan Nurma
Fanany, Mohamad Ivan
Arymurthy, Aniati Murni
2017 INTERNATIONAL CONFERENCE ON ADVANCED COMPUTER SCIENCE AND INFORMATION SYSTEMS (ICACSIS), 2017, : 303 - 307
[6] Short-Term Traffic Prediction Using Long Short-Term Memory Neural Networks
Abbas, Zainab
Al-Shishtawy, Ahmad
Girdzijauskas, Sarunas
Vlassov, Vladimir
2018 IEEE INTERNATIONAL CONGRESS ON BIG DATA (IEEE BIGDATA CONGRESS), 2018, : 57 - 65
[7] Articulatory Movement Prediction Using Deep Bidirectional Long Short-Term Memory Based Recurrent Neural Networks and Word/Phone Embeddings
Zhu, Pengcheng
Xie, Lei
Chen, Yunlin
16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 2192 - 2196
[8] QUERY-BY-EXAMPLE KEYWORD SPOTTING USING LONG SHORT-TERM MEMORY NETWORKS
Chen, Guoguo
Parada, Carolina
Sainath, Tara N.
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 5236 - 5240
[9] VOICE CONVERSION USING DEEP BIDIRECTIONAL LONG SHORT-TERM MEMORY BASED RECURRENT NEURAL NETWORKS
Sun, Lifa
Kang, Shiyin
Li, Kun
Meng, Helen
2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), 2015, : 4869 - 4873
[10] Arabic Diacritization Using Bidirectional Long Short-Term Memory Neural Networks With Conditional Random Fields
Al-Thubaity, Abdulmohsen
Alkhalifa, Atheer
Almuhareb, Abdulrahman
Alsanie, Waleed
IEEE ACCESS, 2020, 8 : 154984 - 154996

← 1 2 3 4 5 →