An HMM-MLP Hybrid Model for Cursive Script Recognition

Kim, Jin Ho; Kim, Kye Kyung; Suen, Ching Y.

doi:10.1007/s100440070003

Cited by 24 publications

(15 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The HMM classifier is often accompanied with another pattern recognition method that is used for discretization of continues signal. Those can be for example NN [20,25] or Support Vectors Machine [36].…”

Section: State Of the Art On Application Of Hmm To Gestures And Actiomentioning

confidence: 99%

Human actions recognition on multimedia hardware using angle-based and coordinate-based features and multivariate continuous hidden Markov model classifier

Hachaj

Ogiela

2015

Multimed Tools Appl

View full text Add to dashboard Cite

In this paper we have proposed human actions recognition schema that uses angle-based and state-of-the-art coordinates-based features and multivariate continuous hidden Markov model (HMM) classifier with Gaussian distribution. The main novelty of this paper besides presenting this approach is its evaluation on large (containing 770 actions) motion-capture dataset of various gym exercises. We have evaluated HMM with various number of hidden states and Gaussian mixture model classifier. We have performed PCA analysis of both features sets to justify our choices. We have also test 24 subsets of proposed angle-based features dataset in order to estimate which body joints are vital for correct actions recognition. The highest recognition rate in k-fold cross validation was 97±14 % and was obtained for 4-states HMM with 10 angle-based features. The common problem with markerless motion capture vision -based systems is that if some parts of body surface are covered by another part it is impossible to perform accurate features measurements. Knowing this we have evaluated 24 subsets of proposed features dataset in order to estimate which body joints are vital for correct actions recognition.

show abstract

Section: State Of the Art On Application Of Hmm To Gestures And Actiomentioning

confidence: 99%

Human actions recognition on multimedia hardware using angle-based and coordinate-based features and multivariate continuous hidden Markov model classifier

Hachaj

Ogiela

2015

Multimed Tools Appl

View full text Add to dashboard Cite

show abstract

“…Pattern analysis is an area of research that often deals with the recognition of a known object in the image. The research fields, such as content-based retrieval that locates relevant images in a large collection of images [35], [36], analysis of the symbols in a printed document [37], recognition of the script words [38], recognition of the handwritten letters [39], [40], [41], the face recognition [42] or the object recognition [43], are limited to perform recognition based on application of classical pattern recognition tools. This approach can give good results in the case when a number of objects that need to be recognized is rather small.…”

Section: Learningmentioning

confidence: 99%

Shape Understanding System – Knowledge Implementation and Learning

Leś

Les

2013

Studies in Computational Intelligence

View full text Add to dashboard Cite

“…Hybrid approaches, based on combination of various neural networks and HMMs have also been proposed in application to handwriting, cursive script and speech recognition. In most of the hybrid approaches [9], [10], [11], [12] a neural network is used to augment the HMM either as an approximation of the probability density function or as a neural vector quantizer. Other hybrid approaches [13], [14], [15] use the neural networks as part of feature extraction process or to obtain the observation probabilities for HMMs.…”

Section: Related Workmentioning

confidence: 99%

Scanning Neural Network for Text Line Recognition

Rashid

Breuel

2012

2012 10th IAPR International Workshop on Document Analysis Systems

View full text Add to dashboard Cite

Abstract-Optical character recognition (OCR) of machine printed Latin script documents is ubiquitously claimed as a solved problem. However, error free OCR of degraded or noisy text is still challenging for modern OCR systems. Most recent approaches perform segmentation based character recognition. This is tricky because segmentation of degraded text is itself problematic. This paper describes a segmentation free text line recognition approach using multi layer perceptron (MLP) and hidden markov models (HMMs). A line scanning neural network -trained with character level contextual information and a special garbage class-is used to extract class probabilities at every pixel succession. The output of this scanning neural network is decoded by HMMs to provide character level recognition. In evaluations on a subset of UNLV-ISRI document collection, we achieve 98.4% character recognition accuracy that is statistically significantly better in comparison with character recognition accuracies obtained from state-of-the-art open source OCR systems.

show abstract

An HMM-MLP Hybrid Model for Cursive Script Recognition

Cited by 24 publications

References 17 publications

Human actions recognition on multimedia hardware using angle-based and coordinate-based features and multivariate continuous hidden Markov model classifier

Human actions recognition on multimedia hardware using angle-based and coordinate-based features and multivariate continuous hidden Markov model classifier

Shape Understanding System – Knowledge Implementation and Learning

Scanning Neural Network for Text Line Recognition

Contact Info

Product

Resources

About