Hidden Markov Models : Applications in Computer Vision
H. Bunke
Bok Engelsk 2001 · Electronic books.
| Annen tittel | |
|---|---|
| Utgitt | Singapore : : World Scientific Publishing Company, , 2001.
|
| Omfang | 1 online resource (246 p.)
|
| Opplysninger | Description based upon print version of record.. - CONTENTS; PREFACE; INTRODUCTION; A SIMPLE COMPLEX IN ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING; AN INTRODUCTION TO HIDDEN MARKOV MODELS AND BAYESIAN NETWORKS; 1. Introduction; 2. What are Hidden Markov Models?; 3. A Bayesian Network Tutorial; 3.1. Dynamic Bayesian networks; 3.2. State-space models; 4. Learning and Inference; 4.1. ML estimation with complete data; 4.2. ML estimation with hidden variables: the EM algorithm; 4.3. Example 1: Learning hidden Markov models using EM; 4.4. The forward-backward algorithm; 4.5. Example 2: Learning state-space models using EM; 4.6. Kalman smoothing. - 2.2. Design of multiple models by clustering. - 3. Byblos OCR System3.1. Preprocessing; 3.2. Feature extraction; 3.3. Training; 3.4. Recognition; 4. Basic System Performance; 4.1. English OCR; 4.2. Arabic OCR; 4.3 . Chinese OCR; 4.3.1. Corpus; 4.3.2. Experimental results; 5. Degraded Data and Adaptation; 5.1. Corpus collection; 5.2. Basic results; 5.3. Adaptation; 5.4. Adaptation results; 6. Summary and Future Work; References; USING A STATISTICAL LANGUAGE MODEL TO IMPROVE THE PERFORMANCE OF AN HMM-BASED CURSIVE HANDWRITING RECOGNITION SYSTEM; 1. Introduction; 2. System Overview; 3. Preprocessing; 3.1. Line separation; 3.2. Skew correction. - 3.1. Definition of Image Models3.2. An efficient decoding using look-ahead technique; 3.3. Classification; 4. Estimation of Model Parameters; 4.1. Initialization; 4.2. Estimation algorithm; 5. Vector Quantization for Symbol Generation; 6. Experiments; 6.1. Encoding character images; 6.1.1. Gray-scale mosaic feature; 6.1.2. Gray-scale bitmap feature; 6.2. Experimental results; 7. Conclusions; References; DATA-DRIVEN DESIGN OF HMM TOPOLOGY FOR ONLINE HANDWRITING RECOGNITION; 1. Introduction; 2. Data-Driven Design of HMM Topology; 2.1. Mapping line segment to HMM state. - 3.3. Slant correction3.4. Positioning of the text line; 3.5. Horizontal scaling; 4. Feature Extraction; 5. Hidden Markov Models; 6. Statistical Language Models; 6.1. Corpus; 6.2. Simple sentence model; 6.3. Unigram sentence model; 6.4. Bigram sentence model; 6.5. Back-off sentence model; 6.6. Perplexity; 7. Experiments and Results; 7.1. Database; 7.2. Perplexity analysis; 7.3. Recognition experiments; 8. Conclusions; References; A 2-D HMM METHOD FOR OFFLINE HANDWRITTEN CHARACTER RECOGNITION*; 1. Introduction; 2. Related Works; 3. HMMRF Models for Character Recognition. - 5. Limitations of HMMs and Generalizations5.1. Extension 1: Factorial HMMs; 5.2. Extension 2: Tree structured HMMs; 5.3. Extension 3: Switching state-space models; 6. Approximate Inference and Intractability; 6.1. Approximation 1: Gibbs sampling; 6.2. Approximation 2: Variational methods; 6.3. Example 1: Mean field for factorial HMMs; 6.4. Example 2: Structured approximation for factorial HMMs; 7. Bayesian HMMs; 8. Conclusion; Acknowledgments; References; MULTILINGUAL MACHINE PRINTED OCR; 1. Introduction; 2. Theoretical Framework; 2.1. Problem formulation; 2.2. Hidden Markov models. - Hidden Markov models (HMMs) originally emerged in the domain of speech recognition. In recent years, they have attracted growing interest in the area of computer vision as well. This book is a collection of articles on new developments in the theory of HMMs and their application in computer vision. It addresses topics such as handwriting recognition, shape recognition, face and gesture recognition, tracking, and image database retrieval.This book is also published as a special issue of the International Journal of Pattern Recognition and Artificial Intelligence (February 2001).
|
| Emner | |
| Sjanger | |
| Dewey | |
| ISBN | 9810245645
|
