Texture Segmentation Using a Kernel Modifying Neural Network
Summary :
A novel neural network architecture for image texture classification is introduced. The proposed model (Kernel Modifying Neural Network: KM Net) which incorporates the convolution filter kernel and the classifier in one, enables an automated texture feature extraction in multichannel texture classification through the modification of the kernel and the connection weights by the backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves a most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified using a basic problem on a synthetic texture image. In addition, the possibilities of applying the KM Net to natural texture classification and biological tissue classification using an ultrasonic echo image have been tried.
- Publication
- IEICE TRANSACTIONS on Information Vol.E80-D No.11 pp.1092-1101
- Publication Date
- 1997/11/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Category
- Image Processing,Computer Graphics and Pattern Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Keisuke KAMEYAMA, Kenzo MORI, Yukio KOSUGI, "Texture Segmentation Using a Kernel Modifying Neural Network" in IEICE TRANSACTIONS on Information,
vol. E80-D, no. 11, pp. 1092-1101, November 1997, doi: .
Abstract: A novel neural network architecture for image texture classification is introduced. The proposed model (Kernel Modifying Neural Network: KM Net) which incorporates the convolution filter kernel and the classifier in one, enables an automated texture feature extraction in multichannel texture classification through the modification of the kernel and the connection weights by the backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves a most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified using a basic problem on a synthetic texture image. In addition, the possibilities of applying the KM Net to natural texture classification and biological tissue classification using an ultrasonic echo image have been tried.
URL: https://global.ieice.org/en_transactions/information/10.1587/e80-d_11_1092/_p
Copy
@ARTICLE{e80-d_11_1092,
author={Keisuke KAMEYAMA, Kenzo MORI, Yukio KOSUGI, },
journal={IEICE TRANSACTIONS on Information},
title={Texture Segmentation Using a Kernel Modifying Neural Network},
year={1997},
volume={E80-D},
number={11},
pages={1092-1101},
abstract={A novel neural network architecture for image texture classification is introduced. The proposed model (Kernel Modifying Neural Network: KM Net) which incorporates the convolution filter kernel and the classifier in one, enables an automated texture feature extraction in multichannel texture classification through the modification of the kernel and the connection weights by the backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves a most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified using a basic problem on a synthetic texture image. In addition, the possibilities of applying the KM Net to natural texture classification and biological tissue classification using an ultrasonic echo image have been tried.},
keywords={},
doi={},
ISSN={},
month={November},}
Copy
TY - JOUR
TI - Texture Segmentation Using a Kernel Modifying Neural Network
T2 - IEICE TRANSACTIONS on Information
SP - 1092
EP - 1101
AU - Keisuke KAMEYAMA
AU - Kenzo MORI
AU - Yukio KOSUGI
PY - 1997
DO -
JO - IEICE TRANSACTIONS on Information
SN -
VL - E80-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 1997
AB - A novel neural network architecture for image texture classification is introduced. The proposed model (Kernel Modifying Neural Network: KM Net) which incorporates the convolution filter kernel and the classifier in one, enables an automated texture feature extraction in multichannel texture classification through the modification of the kernel and the connection weights by the backpropagation-based training rule. The first layer units working as the convolution kernels are constrained to be an array of Gabor filters, which achieves a most efficient texture feature localization. The following layers work as a classifier of the extracted texture feature vectors. The capability of the KM Net and its training rule is verified using a basic problem on a synthetic texture image. In addition, the possibilities of applying the KM Net to natural texture classification and biological tissue classification using an ultrasonic echo image have been tried.
ER -
English
