Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction

Hand gestures in Bharatanatyam dance carry valuable information. Learning the meaning of hand gesture, mimic and practice them with the best way and high matching for the people who want to be expert in this field is necessary. Therefore,hand gesture recognition system can be implemented to help peo...

Full description

Saved in:
Bibliographic Details
Main Author: Jaganathan, Kavitha
Format: Thesis
Language:English
Published: 2015
Subjects:
Online Access:http://psasir.upm.edu.my/id/eprint/65377/1/FSKTM%202015%2024IR.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-upm-ir.65377
record_format uketd_dc
spelling my-upm-ir.653772018-09-07T03:14:13Z Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction 2015-09 Jaganathan, Kavitha Hand gestures in Bharatanatyam dance carry valuable information. Learning the meaning of hand gesture, mimic and practice them with the best way and high matching for the people who want to be expert in this field is necessary. Therefore,hand gesture recognition system can be implemented to help people to learn it effectively and efficiently. In this thesis, a combined feature extraction method based on the Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) is proposed. DWT with two level decompositions is applied to the image by size of 128 × 128. Two-dimensional DCT is then applied and convert the coefficients of DCT to vector. Finally, neuro fuzzy classifier is used to classify the given images in somegiven classes. The results are shown in a graphical format to prepare a good understanding in final stage for the user. A suitable number of images with good illumination for different applications have been created. Many types of image processing techniques like scaling and translation can also be applied to the original database and make ready more options for any future study. The experimental results show that the proposed method has good performance in most of single hand gestures. The dataset of single hand gesture in Bharatanatyam dance has been successfully created and it could serve as a benchmark data set as well. Our proposed system is able to recognize single hand gesture with the accuracy of 93%. At the testing stage, 130 out of 140 images of single hand gestures are correctly classified by the proposed graphic user interface GUI. This is because the parameters identified were the right signal, which gave the best 70 features to be classified and recognized. Human-computer interaction User interfaces (Computer systems) Gesture in dance 2015-09 Thesis http://psasir.upm.edu.my/id/eprint/65377/ http://psasir.upm.edu.my/id/eprint/65377/1/FSKTM%202015%2024IR.pdf text en public masters Universiti Putra Malaysia Human-computer interaction User interfaces (Computer systems) Gesture in dance
institution Universiti Putra Malaysia
collection PSAS Institutional Repository
language English
topic Human-computer interaction
User interfaces (Computer systems)
Gesture in dance
spellingShingle Human-computer interaction
User interfaces (Computer systems)
Gesture in dance
Jaganathan, Kavitha
Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
description Hand gestures in Bharatanatyam dance carry valuable information. Learning the meaning of hand gesture, mimic and practice them with the best way and high matching for the people who want to be expert in this field is necessary. Therefore,hand gesture recognition system can be implemented to help people to learn it effectively and efficiently. In this thesis, a combined feature extraction method based on the Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) is proposed. DWT with two level decompositions is applied to the image by size of 128 × 128. Two-dimensional DCT is then applied and convert the coefficients of DCT to vector. Finally, neuro fuzzy classifier is used to classify the given images in somegiven classes. The results are shown in a graphical format to prepare a good understanding in final stage for the user. A suitable number of images with good illumination for different applications have been created. Many types of image processing techniques like scaling and translation can also be applied to the original database and make ready more options for any future study. The experimental results show that the proposed method has good performance in most of single hand gestures. The dataset of single hand gesture in Bharatanatyam dance has been successfully created and it could serve as a benchmark data set as well. Our proposed system is able to recognize single hand gesture with the accuracy of 93%. At the testing stage, 130 out of 140 images of single hand gestures are correctly classified by the proposed graphic user interface GUI. This is because the parameters identified were the right signal, which gave the best 70 features to be classified and recognized.
format Thesis
qualification_level Master's degree
author Jaganathan, Kavitha
author_facet Jaganathan, Kavitha
author_sort Jaganathan, Kavitha
title Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
title_short Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
title_full Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
title_fullStr Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
title_full_unstemmed Single hand Indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
title_sort single hand indian classical gesture recognition based on discrete wavelet transform and discrete cosine transform feature extraction
granting_institution Universiti Putra Malaysia
publishDate 2015
url http://psasir.upm.edu.my/id/eprint/65377/1/FSKTM%202015%2024IR.pdf
_version_ 1747812333360513024