home
sign in
my orders
my e-books
my trolley
my account
contact
keyword
isbn13
author
title
| can't find it |
Tell us the title, author
and / or ISBN number
*
Any other details such as author,
ISBN, title or genre. Please be specific
What is your email address?
*
Not a valid email address
| browse books |
Textbooks
books
antiques & collectibles
architecture
art
biography & autobiography
body, mind & spirit
business & economics
comics & graphic novels
computers
cooking
crafts & hobbies
drama
education
family & relationships
fiction
foreign language study
games
gardening
health & fitness
history
house & home
humor
juvenile fiction
juvenile nonfiction
language arts & disciplines
law
literary collections
literary criticism
mathematics
medical
music
nature
non-classifiable
performing arts
pets
philosophy
photography
poetry
political science
psychology
reference
religion
science
self-help
social science
sports & recreation
study aids
technology
transportation
travel
true crime
books
| book details |
Multilingual Text Recognition: A Deep Learning Approach
By (author)
Liangrui Peng
, By (author)
Ruijie Yan
| on special |
normal price: R 2 267.95
Price: R 2 153.95
| add to trolley |
processing...
| book description |
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 a novel deep learning framework termed Primitive Representation Learning for sequence modeling. In contrast to conventional approaches that employ either (1) convolutional neural networks (CNNs) combined with recurrent neural networks (RNNs) and connectionist temporal classification (CTC) for decoding, or (2) attention-based encoder-decoder architectures, the proposed framework offers an alternative paradigm for sequence representation and processing. 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. Multielement 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.Â
| product details |
Normally shipped |
Forthcoming. We are not accepting backorders for this item yet
Publisher |
Springer Nature Switzerland AG
Published date |
7 Dec 2025
Language |
Format |
Paperback / softback
Pages |
0
Dimensions |
235 x 155 x 0mm (L x W x H)
Weight |
0g
ISBN |
978-9-8196-7897-6
Readership Age |
BISAC |
computers / data processing / optical data processing
| other options |
| back |
| your trolley |
To view the items in your trolley please sign in.
| sign in |
| specials |
Helgoland: The Strange and Beautiful Story of Quantum Physics
Carlo Rovelli
Paperback / softback
208 pages
was: R 295.95
now: R 265.95
Available from overseas. Usually dispatched in 3 to 6 weeks
| more |
| add to trolley |
processing...
The Order of Time
Carlo Rovelli
Paperback / softback
224 pages
was: R 295.95
now: R 265.95
Available from overseas. Usually dispatched in 3 to 6 weeks
Originally published in Italian: L'ordine del tempo (Milan: Adelphi Edizioni, 2017).
| more |
| add to trolley |
processing...
The Coming Wave: AI, Power and Our Future
Mustafa Suleyman
Paperback / softback
352 pages
was: R 295.95
now: R 265.95
Stock is usually dispatched in 6-12 days from date of order
| more |
| add to trolley |
processing...
Copyright 2025
|
terms and conditions