Hidden Markov Models: Applications In Computer VisionHorst Bunke, Terry Michael Caelli 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). |
Contents
| 1 | |
| 5 | |
| 9 | |
MULTILINGUAL MACHINE PRINTED OCR | 43 |
6 Summary and Future Work | 58 |
USING A STATISTICAL LANGUAGE MODEL TO IMPROVE THE PERFORMANCE OF AN HMMBASED CURSIVE HANDWRITING RECOG... | 65 |
A 2D HMM METHOD FOR OFFLINE HANDWRITTEN CHARACTER RECOGNITION | 91 |
DATADRIVEN DESIGN OF HMM TOPOLOGY FOR ONLINE HANDWRITING RECOGNITION | 107 |
HIDDEN MARKOV MODELS FOR MODELING AND RECOGNIZING GESTURE UNDER VARIATION | 123 |
SENTENCE LIPREADING USING HIDDEN MARKOV MODEL WITH INTEGRATED GRAMMAR | 161 |
TRACKING AND SURVEILLANCE IN WIDEAREA SPATIAL ENVIRONMENTS USING THE ABSTRACT HIDDEN MARKOV MODEL | 177 |
SHAPE TRACKING AND PRODUCTION USING HIDDEN MARKOV MODELS | 197 |
AN INTEGRATED APPROACH TO SHAPE AND COLORBASED IMAGE RETRIEVAL OF ROTATED OBJECTS USING HIDDEN MARKOV M... | 223 |
Other editions - View all
Hidden Markov Models: Applications in Computer Vision Horst Bunke,Terry Caelli No preview available - 2001 |
Common terms and phrases
AHMM application approach approximation Artificial Intelligence Baum-Welch algorithm Bayesian network bigram character recognition cluster Computer Science Computer Vision Conf corresponding current subgoal database defined Document Analysis dynamic EM algorithm encoded error estimate example feature extraction feature vector forward-backward algorithm Gaussian gesture recognition given goal handwriting recognition handwritten Hangul hidden Markov models inference input integration language model learning likelihood linear matrix maximization method Neural node observation sequence obtained OCR system offline output probability distributions parameterized parameters Patt Pattern Recognition PHMM pixels posterior probabilistic probability distribution problem Proc query Recogn recognition rate recognition system represented retrieval rotation samples segmentation sentence shape boundary shown in Fig spatial speech recognition state-space models statistical structure subgoal at level techniques test set text line tracking training data training set transition probabilities unigram update variables variation Viterbi Viterbi algorithm Viterbi search vocabulary