Recognition of whiteboard notes: online, offline and combination
Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Liwicki, Marcus (VerfasserIn)
Format: Elektronisch E-Book
Sprache:English
Veröffentlicht: Singapore World Scientific c2008
Schriftenreihe:Series in machine perception and artificial intelligence v. 71
Schlagworte:
Online-Zugang:FAW01
FAW02
Volltext
Beschreibung:Includes bibliographical references (p. 191-204) and index
"This book addresses the task of processing online handwritten notes acquired from an electronic whiteboard, which is a new modality in handwriting recognition research. The main motivation of this book is smart meeting rooms, aim to automate standard tasks usually performed by humans in a meeting." "The book can be summarized as follows. A new online handwritten database is compiled, and four handwriting recognition systems are developed. Moreover, novel preprocessing and normalization strategies are designed especially for whiteboard notes and a new neural network based recognizer is applied. Commercial recognition systems are included in a multiple classifier system."--BOOK JACKET.
1. Introduction. 1.1. Motivation. 1.2. Handwriting recognition. 1.3. Comparability of recognition results. 1.4. Related topics. 1.5. Contribution. 1.6. Ouline -- 2. Classification methods. 2.1. Hidden Markov models. 2.2. Neural networks. 2.3. Gaussian mixture models. 2.4. Language models -- 3. Linguistic resources and handwriting databases. 3.1. Linguistic resources. 3.2. IAM offline database. 3.3. IAM online database -- 4. Offline approach. 4.1. System description. 4.2. Enhancing the training set. 4.3. Experiments. 4.4. Word extraction. 4.5. Conclusions -- 5. Online approach. 5.1. Line segmentation. 5.2. Preprocessing. 5.3. Features. 5.4. HMM-based experiments. 5.5. Experiments with neural networks. 5.6. Conclusions and discussion -- 6. Multiple classifier combination. 6.1. Methodology. 6.2. Recognition systems. 6.3. Initial experiments. 6.4. Experiments with all recognition systems. 6.5. Advanced confidence measures. 6.6. Conclusions -- 7. Writer-dependent recognition. 7.1. Writer identification. 7.2. Writer-dependent experiments. 7.3. Automatic handwriting classification. 7.4. Conclusions -- 8. Conclusions. 8.1. Overview of recognition systems. 8.2. Overview of experimental results. 8.3. Concluding remarks. 8.4. Outlook
Beschreibung:1 Online-Ressource (xx, 206 p.)
ISBN:9789812814531
9789812814548
9812814531
981281454X

Es ist kein Print-Exemplar vorhanden.

Fernleihe Bestellen Achtung: Nicht im THWS-Bestand! Volltext öffnen