Neural network classification of defects in veneer boards

2000 ◽  
Vol 214 (3) ◽  
pp. 255-258 ◽  
Author(s):  
D T Pham ◽  
S Sagiroglu
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Vector Quantization ◽  
Learning Vector Quantization ◽  
Defect Classification ◽  
Neural Network Classification ◽  
Different Types ◽  
High Degree

Learning vector quantization (LVQ) networks are known good neural classifiers which provide fast and accurate results for many applications. The aim of this work was to test if this network paradigm could be employed for the classification of wood sheet defects. Experiments conducted with LVQ networks have shown that they provide a high degree of discrimination between the different types of defects and potentially can perform defect classification in real time.

A Study on the Application of Learning Vector Quantization Neural Network in Pattern Classification

2014 ◽  
Vol 525 ◽  
pp. 657-660 ◽  
Author(s):  
Shuo Ding ◽  
Xiao Heng Chang ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Pattern Classification ◽  
Vector Quantization ◽  
Bp Neural Network ◽  
Back Propagation ◽  
Learning Vector Quantization ◽  
Classification Method ◽  
Two Dimensional ◽  
The One

Standard back propagation (BP) neural network has disadvantages such as slow convergence speed, local minimum and difficulty in definition of network structure. In this paper, an learning vector quantization (LVQ) neural network classifier is established, then it is applied in pattern classification of two-dimensional vectors on a plane. To test its classification ability, the classification results of LVQ neural network and BP neural network are compared with each other. The simulation result shows that compared with classification method based on BP neural network, the one based on LVQ neural network has a shorter learning time. Besides, its requirements for learning samples and the number of competing layers are also lower. Therefore it is an effective classification method which is powerful in classification of two-dimensional vectors on a plane.

NEURAL NETWORK CLASSIFICATION OF SYMMETRICAL AND NONSYMMETRICAL IMAGES USING NEW MOMENTS WITH HIGH NOISE TOLERANCE

1999 ◽  
Vol 13 (08) ◽  
pp. 1233-1250
Author(s):  
R. PALANIAPPAN ◽  
P. RAVEENDRAN ◽  
SIGERU OMATU
Keyword(s):  
Neural Network ◽  
Random Noise ◽  
Noise Tolerance ◽  
Neural Network Classification ◽  
Reference Centre ◽  
Different Types ◽  
Moment Functions ◽  
Classification Of Images ◽  
Invariant Properties

The classification of images using regular or geometric moment functions suffers from two major problems. First, odd orders of central moments give zero value for images with symmetry in the x and/or y directions and symmetry at centroid. Secondly, these moments are very sensitive to noise especially for higher order moments. In this paper, a single solution is proposed to solve both these problems. The solution involves the computation of the moments from a reference point other than the image centroid. The new reference centre is selected such that the invariant properties like translation, scaling and rotation are still maintained. In this paper, it is shown that the new proposed moments can solve the symmetrical problem. Next, we show that the new proposed moments are less sensitive to Gaussian and random noise as compared to two different types of regular moments derived by Hu.6 Extensive experimental study using a neural network classification scheme with these moments as inputs are conducted to verify the proposed method.

Classification of Underwater Echo Based on Fractal Theory and Learning Vector Quantization Neural Network

2011 ◽  
Vol 148-149 ◽  
pp. 1365-1369
Author(s):  
Pu Hua Tang ◽  
Mu Rong Zhou ◽  
Ying Yong Bu
Keyword(s):  
Neural Network ◽  
Fractal Dimension ◽  
Wavelet Transform ◽  
Vector Quantization ◽  
Continuous Wavelet Transform ◽  
Fractal Theory ◽  
Learning Vector Quantization ◽  
Experimental Results ◽  
Continuous Wavelet

A classification method for underwater echo is introduced, which based on fractal theory and learning vector quantization (LVQ) neural network. The fractal dimension was extracted from the underwater echo by continuous wavelet transform. Combining with accumulative energy as input of a LVQ neural network, neural network was used to classify four kinds of underwater echo. The experimental results showed this method is effective and reliable.

Neuro-Classification of Currency Fatigue Levels Based on Acoustic Cepstrum Patterns

2000 ◽  
Vol 4 (1) ◽  
pp. 18-23 ◽  
Author(s):  
Masaru Teranishi ◽  
◽  
sigeru Omatu ◽  
Toshihisa Kosaka ◽  
◽  
...  
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Acoustic Signal ◽  
Learning Vector Quantization ◽  
Experimental Results ◽  
New Method ◽  
Competitive Neural Network ◽  
Good Classification

This paper proposes a new method to classify currencies into different fatigue levels. Acoustic cepstrum patterns obtained from an acoustic signal generated by a currency passing through a banking machine are used for classification. The acoustic cepstrum patterns are fed to a competitive neural network with the Learning Vector Quantization (LVQ) algorithm, and classified the currency into three fatigue levels. The experimental results show that the proposed method is useful for classification of fatigue levels of currencies, and the LVQ algorithm performs a good classification.

Sign in / Sign up

Export Citation Format

Share Document