Cursive script text recognition in natural scence images : Arabic text complexities

著者

書誌事項

Cursive script text recognition in natural scence images : Arabic text complexities

Saad Bin Ahmed, Muhammad Imran Razzak, Rubiyah Yusof

Springer, c2020

  • : hardback

大学図書館所蔵 件 / 全1件

この図書・雑誌をさがす

注記

Includes bibliographical references (p. 101-107) and index

内容説明・目次

内容説明

This book offers a broad and structured overview of the state-of-the-art methods that could be applied for context-dependent languages like Arabic. It also provides guidelines on how to deal with Arabic scene data that appeared in an uncontrolled environment impacted by different font size, font styles, image resolution, and opacity of text. Being an intrinsic script, Arabic and Arabic-like languages attract attention from research community. There are a number of challenges associated with the detection and recognition of Arabic text from natural images. This book discusses these challenges and open problems and also provides insights into the complexities and issues that researchers encounter in the context of Arabic or Arabic-like text recognition in natural and document images. It sheds light on fundamental questions, such as a) How the complexity of Arabic as a cursive scripts can be demonstrated b) What the structure of Arabic text is and how to consider the features from a given text and c) What guidelines should be followed to address the context learning ability of classifiers existing in machine learning.

目次

Section#1 Introduction and Challenges Chapter# 1 Foundations of Cursive Scene Text 1.1 Introduction 1.2 What is Cursive script 1.3 Role of Context in Cursive script 1.5 Applications 1.6 Contribution Chapter# 2 Text in Wild and its Challenges 2.1 In-built Complexities Relevant to Cursive Scene Text 2.2 Scene Text Localization issues 2.3 Cursive Scene Text Recognition Limitations Chapter#3 Arabic Scene Text Acquisition and Statistics 3.1 Importance of Dataset Analysis 3.2 Dataset Collection 3.2.1 Multilingual Dataset Generation 3.2.2 English-Arabic Scene text 42k Dataset 3.5 Pre-processing of Acquired Samples 3.6 Generation and Verification of Ground Truth Methods and Algorithms Chapter#4 Traditional Approaches 4.1. Methods Designed for Feature Analysis 4.2 Research Methodologies Designed for Cursive Scene Text 4.2.1 Importance of Implicit Segmentation 4.3 Role of Explicit Segmentation 4.1 Invariance Feature Extraction in Co-occurrence Extremal Regions 4.2 Window based features 4.4 Linear spatial pyramid 4.4.1 Formulation and Preprocessing Chapter 5# Deep Learning 5.1 Hybrid Deep Learning Model 5.2 Deep Convolutional Neural Network 5.3 RNN 5.3.1 Why LSTM networks suitable for Cursive Scene Text? 5.3.2 Importance of Connectionist Temporal Classification (CTC) in LSTM 5.4 Hierarchical Subsampling based Cursive scene Text Recognition 5.5 Transfer Learning 4.11 Summary Chapter 6# Progress in Cursive Wild Text Recognition 5.1 Overview of latest trends 5.2 Current Status (Competition) Chapter# 7 Open Research issues and Future Direction 6.1 Research problems with perspective of state-of-the-art techniques 6.2 Future Directions

「Nielsen BookData」 より

詳細情報

ページトップへ