國立高雄大學圖資館 |

Language: English

Back

Multilingual text recognitiona deep learning approach /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Multilingual text recognitionby Liangrui Peng, Ruijie Yan.
Reminder of title:	a deep learning approach /
Author:	Peng, Liangrui.
other author:	Yan, Ruijie.
Published:	Singapore :Springer Nature Singapore :2025.
Description:	xiii, 115 p. :ill., digital ;24 cm.
Contained By:	Springer Nature eBook
Subject:	Optical pattern recognition.
Online resource:	https://doi.org/10.1007/978-981-96-7898-3
ISBN:	9789819678983$q(electronic bk.)

Multilingual text recognitiona deep learning approach /
Peng, Liangrui.

Multilingual text recognitiona deep learning approach /[electronic resource] :by Liangrui Peng, Ruijie Yan. - Singapore :Springer Nature Singapore :2025. - xiii, 115 p. :ill., digital ;24 cm. - SpringerBriefs in computer science,2191-5776. - SpringerBriefs in computer science..

Chapter 1 Introduction -- Chapter 2 Primitive Representation Learning -- Chapter 3 Multielement Attention Mechanism -- Chapter 4 Dynamic Temporal Residual Learning and Attention Rectification -- Chapter 5 TH-DL Multilingual Text Recognition System Framework.

Multilingual text recognition is crucial for cross language information acquisition and related applications in the mobile computing era. The core problem is to find efficient representation and decoding methods for multilingual text recognition, including scene text recognition or handwriting recognition tasks. This book introduces primitive representation learning, which is a new deep learning framework for sequence modeling in contrast to CNN RNN CTC (convolutional neural network recurrent neural network connectionist temporal classification) or attention based encoder decoder approaches. Primitive representations are learned via global feature aggregation and then transformed into high level visual text representations via a graph convolutional network, which enables parallel decoding for text transcription. Multi element attention mechanism and temporal residual mechanism are further introduced to enhance the utilization of spatial and temporal feature information. The methods presented in this book have been evaluated on public datasets and applied to scene text recognition and handwriting recognition systems. Readers will gain a better understanding of state of the art methods and research findings in multilingual scene text recognition, handwriting recognition, and related fields. The prerequisites needed to understand this book include basic knowledge for machine learning and deep learning.

ISBN: 9789819678983$q(electronic bk.)

Standard No.: 10.1007/978-981-96-7898-3doiSubjects--Topical Terms:

188326
Optical pattern recognition.

LC Class. No.: Q337.5

Dewey Class. No.: 006.31

Multilingual text recognitiona deep learning approach /
LDR:02744nmm a2200337 a 4500 001 692019
003 DE-He213
005 20260102123006.0
006 m d
007 cr nn 008maaau
008 260527s2025 si s 0 eng d
020 $a 9789819678983$q(electronic bk.)
020 $a 9789819678976$q(paper)
024 7 $a 10.1007/978-981-96-7898-3 $2 doi
035 $a 978-981-96-7898-3
040 $a GP $c GP
041 0 $a eng
050 4 $a Q337.5
072 7 $a UYQP $2 bicssc
072 7 $a COM016000 $2 bisacsh
072 7 $a UYQP $2 thema
082 0 4 $a 006.31 $2 23
090 $a Q337.5 $b .P398 2025
100 1 $a Peng, Liangrui. $3 980600
245 1 0 $a Multilingual text recognition $h [electronic resource] : $b a deep learning approach / $c by Liangrui Peng, Ruijie Yan.
260 $a Singapore : $b Springer Nature Singapore : $b Imprint: Springer, $c 2025.
300 $a xiii, 115 p. : $b ill., digital ; $c 24 cm.
490 1 $a SpringerBriefs in computer science, $x 2191-5776
505 0 $a Chapter 1 Introduction -- Chapter 2 Primitive Representation Learning -- Chapter 3 Multielement Attention Mechanism -- Chapter 4 Dynamic Temporal Residual Learning and Attention Rectification -- Chapter 5 TH-DL Multilingual Text Recognition System Framework.
520 $a Multilingual text recognition is crucial for cross language information acquisition and related applications in the mobile computing era. The core problem is to find efficient representation and decoding methods for multilingual text recognition, including scene text recognition or handwriting recognition tasks. This book introduces primitive representation learning, which is a new deep learning framework for sequence modeling in contrast to CNN RNN CTC (convolutional neural network recurrent neural network connectionist temporal classification) or attention based encoder decoder approaches. Primitive representations are learned via global feature aggregation and then transformed into high level visual text representations via a graph convolutional network, which enables parallel decoding for text transcription. Multi element attention mechanism and temporal residual mechanism are further introduced to enhance the utilization of spatial and temporal feature information. The methods presented in this book have been evaluated on public datasets and applied to scene text recognition and handwriting recognition systems. Readers will gain a better understanding of state of the art methods and research findings in multilingual scene text recognition, handwriting recognition, and related fields. The prerequisites needed to understand this book include basic knowledge for machine learning and deep learning.
650 0 $a Optical pattern recognition. $3 188326
650 0 $a Deep learning (Machine learning) $3 913129
650 1 4 $a Automated Pattern Recognition. $3 913155
650 2 4 $a Computer Vision. $3 913138
650 2 4 $a Image Processing. $3 273705
650 2 4 $a Machine Learning. $3 833608
650 2 4 $a Natural Language Processing (NLP). $3 988974
650 2 4 $a Artificial Intelligence. $3 212515
700 1 $a Yan, Ruijie. $3 1008634
710 2 $a SpringerLink (Online service) $3 273601
773 0 $t Springer Nature eBook
830 0 $a SpringerBriefs in computer science. $3 559641
856 4 0 $u https://doi.org/10.1007/978-981-96-7898-3
950 $a Professional and Applied Computing (SpringerNature-12059)