Feature extraction using wavelet transform for neural network based image classification

Sarlashkar, A.N.; Bodruzzaman, M.; Malkani, Mohan

doi:10.1109/ssst.1998.660107

Cited by 24 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…12,13,40 Wavelet based image decomposition can be viewed as a form of sub-band decomposition. 41 Each QMF pair consists of a low pass filter (H) and a high pass filter (G), which splits the signal's bandwidth into half.…”

Section: Discrete Wavelet Transformmentioning

confidence: 99%

“…13 This is because the low frequency components spread in the time domain can be treated as global property while the high frequency concentrated in time domain, can be discarded. The multiresolution capability of wavelets also provides the capability to examine the signal at various scales and provides for reduced data.…”

Section: Feature Selectionmentioning

confidence: 99%

“…This MHI representation of hand actions is based on moment based features of wavelet sub-images resulting from the decomposition of MHI using stationary wavelet transform (SWT), and classification using neural networks. [13][14][15] This technique combines the use of geometrical moments and wavelet transforms and is computationally inexpensive and is not sensitive to inter and intra subject variation of speed of movement. The results of classification accuracy of SWT with moment-based features are compared for the classification accuracy between the earlier works of authors for hand gestures classification of similar hand movements using Hu-moments [24][25][26] and stationary wavelet transform with approximate wavelet sub-images.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Visual Hand Gestures Classification Using Wavelet Transform and Moment Based Features

Kumar

2005

Int. J. Wavelets Multiresolut Inf. Process.

View full text Add to dashboard Cite

This paper presents a novel technique for classifying human hand gestures based on stationary wavelet transform (SWT) and classification based on geometrical based moments and compares the results with the classification based on Hu-moments and wavelet approximate images. The technique uses view-based approach for representation of hand actions, and uses a cumulative image-difference technique where the time between the sequences of images is implicitly captured in the representation of action resulting in Motion History Images (MHI). These MHIs are decomposed into wavelet sub-images using SWT. Translation and scaling invariant moments are then computed from the resulting high scale low pass residue of the wavelet sub-images. These geometrical moments are used as the global image descriptors and are fed to Artificial Neural Network (ANN) for classification. The recognition criterion is established using backpropagation based multilayer perceptron (MLP). The experiments show that such a system can classify human hand gestures with a classification accuracy of 97%.

show abstract

Section: Discrete Wavelet Transformmentioning

confidence: 99%

Section: Feature Selectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Visual Hand Gestures Classification Using Wavelet Transform and Moment Based Features

Kumar

2005

Int. J. Wavelets Multiresolut Inf. Process.

View full text Add to dashboard Cite

show abstract

“…In conventional pattern recognition, the task is divided into two parts. The first part is obtaining a feature space of reduced dimensions and complexity, and the second part is the classification of that space [14]. Neural networks (NNs) have been employed and compared to conventional classifiers for a number of classification problems.…”

Section: Introductionmentioning

confidence: 99%

A Multicriteria Multitransform Neural Network Classifier

Mikhael

Abdelwahab

2002

Circuits Syst Signal Process

View full text Add to dashboard Cite

In this paper, we propose a novel one-and multi-dimensional signal classification neural network system that employs a set of criteria extracted from the signal representation in different transform domains, denoted the multicriteria multitransform neural network classifier. The signal projection, in each appropriately selected transform domain, reveals unique signal characteristics. The criteria in the different domains are properly formulated and their parameters adapted to obtain classification with desirable implementation properties such as speed and accuracy. Results for image classification confirm the improved classification performance relative to existing techniques. In addition to the improved computational efficiency and accuracy, preliminary results indicate that the proposed technique lends itself to higher classification accuracy in the presence of additive noise.

show abstract

“…The approximate coefficients of the Wavelet transforms of the images can provide denoising and scale and rotation invariance [13]. This is because the low frequency components spread in the time domain can be treated as global property while the high frequency concentrated in time domain, can be discarded.…”

Section: Feature Extraction and A Pattern Recognition Framework Usingmentioning

confidence: 99%

Classification of visual hand movements using multiresolution wavelet images

Kumar

Sharma

et al.

International Conference on Intelligent Sensing and Information Processing, 2004. Proceedings Of

View full text Add to dashboard Cite

This paper presents a novel technique for classifying human hand gestures based on stationary wavelet transform (SW). It uses view-based approach for representation of hand actions, and artijkial neural networks (ANN) for classijkation. This approach uses a cumulative image-diflerence technique where the time between the sequences of images is implicitly captured in the representation of action. This results in the construction of Motion Histoly Images (MHI). These MHl's are decomposed into 4 sub images using S V , approximate and detailed images. The approximate image is fed as the global image descriptors to the ANN for classification. The recognition criterion is established using backpropagation based multilayer perceptron (MLP). The preliminary experiments show that such a system can classifi human hand gestures with a classification accuracy of 97%. Index Terms-Hand gestures classijication, motion based representation, wavelet transform, computer vision, and artijicial neural networks.

show abstract

Feature extraction using wavelet transform for neural network based image classification

Cited by 24 publications

References 7 publications

Visual Hand Gestures Classification Using Wavelet Transform and Moment Based Features

Visual Hand Gestures Classification Using Wavelet Transform and Moment Based Features

A Multicriteria Multitransform Neural Network Classifier

Classification of visual hand movements using multiresolution wavelet images

Contact Info

Product

Resources

About