Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform

Abdulsamet HAŞİLOĞLU

Makale detayları

Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform

Yazarlar:

Abdulsamet HAŞİLOĞLU

Yayıncı:

TUBITAK

Dergi:

Turkish Journal of Engineering and Environmental Sciences 2001 Vol.25 Issue 5, pp.405-413

Belge Tipi:

Makale

Yayın Tarihi:

4/2001

Belge Dili:

Türkçe

Document ID (Org No.):

2000745223

Sıklık:

Üç Yıllık

eISSN:

1303-6157

pISSN:

1300-0160

Özet:

 

A large number of approaches for texture analysis have been suggested for the purpose of texture classification. Recently, wavelet frames were  proposed for texture features extraction. In this study, non-subsampled  wavelet frame transform was used for feature extraction of 16 textures  from a set of Brodatz' album by means of various wavelet families. Texture  classification was accomplished by artificial neural network with a fast  adaptive backpropagation algorithm. A new pyramidal-windowing algorithm is  proposed, which forms randomly rotated texture windows of variable sizes texture windows  for training a neural networks classifier, and perfect classification results  were obtained.

 

A large number of approaches for texture analysis have been suggested for the purpose of texture classification. Recently, wavelet frames were  proposed for texture features extraction. In this study, non-subsampled  wavelet frame transform was used for feature extraction of 16 textures  from a set of Brodatz' album by means of various wavelet families. Texture  classification was accomplished by artificial neural network with a fast  adaptive backpropagation algorithm. A new pyramidal-windowing algorithm is  proposed, which forms randomly rotated texture windows of variable sizes texture windows  for training a neural networks classifier, and perfect classification results  were obtained.

Makale detayları

Rotation-Invariant Texture Analysis and Classification by Artificial Neural Networks and Wavelet Transform

Yazarlar: Abdulsamet HAŞİLOĞLU

Yayıncı: TUBITAK

Dergi: Turkish Journal of Engineering and Environmental Sciences 2001 Vol.25 Issue 5, pp.405-413

Belge Tipi: Makale

Yayın Tarihi: 4/2001

Belge Dili: Türkçe

Document ID (Org No.): 2000745223

Sıklık: Üç Yıllık

eISSN: 1303-6157

pISSN: 1300-0160

Sayı

Yazarlar:

Abdulsamet HAŞİLOĞLU

Yayıncı:

TUBITAK

Dergi:

Turkish Journal of Engineering and Environmental Sciences 2001 Vol.25 Issue 5, pp.405-413

Belge Tipi:

Makale

Yayın Tarihi:

4/2001

Belge Dili:

Türkçe

Document ID (Org No.):

2000745223

Sıklık:

Üç Yıllık

eISSN:

1303-6157

pISSN:

1300-0160