• Journal of the Korean Institute of Telematics and Electronics
• /
• v.27 no.8
• /
• pp.1294-1302
• /
• 1990

In this paper, optical implementation of single layer perceptron to discriminate the even and odd numbers using commericla LCTV spatial light modulator is described. In order to overcome the low dynamic range of gray levels of LCTV, nonlinear quantized perceptron model is introduced, which is analyzed to have faster convergent time with small gray levels through the computer simulation. And the analog weights containing positive and negative values of single layer perceptron is represented by using the polarization-based encoding method. Finally, optical implementation of the nonlinear quantized perceptron learning model based on polarization property of the commercial LCTV is proposed and some experimental results are given.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.4
• /
• pp.1033-1043
• /
• 2007

The multi layer perceptron for segmenting objects in images only uses the input windows that are made from a image in a fixed size. These windows are recognized so each independent learning data that they make the performance of the multi layer perceptron poor. The poor performance is caused by not considering the position information and effect of input windows in input images. So we propose a new approach to add the position information and effect of input windows to the multi layer perceptron#s input layer. Our new approach improves the performance as well as the learning time in the multi layer perceptron. In our experiment, we can find our new algorithm good.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.1
• /
• pp.14-18
• /
• 2002

The perceptron algorithm, which is one of a class of gradient descent techniques, has been widely used in pattern recognition to determine linear decision boundaries. However, it may not give desirable results when pattern sets are nonlinerly separable. A fuzzy version was developed to male up for the weaknesses in the crisp perceptron algorithm. This was achieved by assigning memberships to the pattern sets. However, still another drawback exists in that the pattern memberships do not consider class typicality of the patterns. Therefore, we propose a possibilistic approach to the crisp perceptron algorithm. This algorithm combines the linearly separable property of the crisp version and the convergence property of the fuzzy version. Several examples are given to show the validity of the method.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2001.12a
• /
• pp.303-306
• /
• 2001

패턴 인식에서 선형 분류 가능한 경계면을 찾아 패턴을 분류하는 방법 중 가장 기본적인 방법은 퍼셉트론이라고 볼 수 있다. 하지만 선형 분류 불가능한 패턴에 대해서는 유용한 결과를 보여주지 못하였다. 먼저 제안된 퍼지 퍼셉트론은 베타영역 설정에 의해 수렴하지 못하는 특성을 보완하였다. 그러나 패턴의 순수한 전형성을 고려해 주지 못하는 단점이 있다. 이에 Crisp의 선형분류 특성과 퍼지의. 수렴특성을 합성하고자 Possibilistic 퍼셉트론을 제시한다.

• Journal of information and communication convergence engineering
• /
• v.6 no.2
• /
• pp.204-206
• /
• 2008

In this paper, we proposed the recognition method that automatically extracts cracks from a surface image acquired by a digital camera and recognizes the directions (horizontal, vertical, -45 degree, and 45 degree) of cracks using the fuzzy single layer perceptron. We compensate an effect of light on a concrete surface image by applying the closing operation, which is one of the morphological techniques, extract the edges of cracks by Sobel masking, and binarize the image by applying the iterated binarization technique. Two times of noise reduction are applied to the binary image for effective noise elimination. After the specific regions of cracks are automatically extracted from the preprocessed image by applying Glassfire labeling algorithm to the extracted crack image, the cracks of the specific region are enlarged or reduced to $30{\times}30$ pixels and then used as input patterns to the fuzzy single layer perceptron. The experiments using concrete crack images showed that the cracks in the concrete crack images were effectively extracted and the fuzzy single layer perceptron was effective in the recognition of the extracted cracks directions.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.1
• /
• pp.94-101
• /
• 1992

The multilayer perceptron, trained by the error back-propagation learning rule, has been known as a mapping network which can represent arbitrary functions. However depending on the complexity of a function and the initial weights of the multilayer perceptron, the error back-propagation learning may fall into a local minimum or a flat area which may require a long learning time or lead to unsuccessful learning. To solve such difficulties in training the multilayer perceptron by standard error back-propagation learning rule, the paper proposes a learning method which progressively enlarges the learning domain from a small area to the entire region. The proposed method is devised from the investigation on the roles of hidden nodes and connection weights in the multilayer perceptron which approximates a function of one variable. The validity of the proposed method was illustrated through simulations for a function of one variable and a function of two variable with many extremal points.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.2
• /
• pp.390-398
• /
• 1996

In this paper, a new image compression algorithm using the generality of the multilaryer perceptron is proposed. Proposed algorithm classifies image into some classes, and trains them through the multilayer perceptron. Multilayer perceptron which trained by the above method can do compression and reconstruction of the nontrained image by the generality. Also, it reduces memory size of the side of receiver and quantization error. For the experiment, we divide Lena image into 16 classes and train them through one multilayer perceptron. The experimental results show that we can get excellent reconstruction images by doing compression and reconstruction for Lena image, Dollar image and Statue image.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.5 s.37
• /
• pp.11-16
• /
• 2005

Recently, there are a lot of endeavor to implement a fuzzy theory to artificial neural network. Goh proposed the fuzzy single layer perceptron algorithm and advanced fuzzy perceptron based on the generalized delta rule to solve the XOR Problem and the classical Problem. However, it causes an increased amount of computation and some difficulties in application of the complicated image recognition. In this paper, we propose an enhanced fuzzy single layer Perceptron using the dynamic adjustment of threshold. This method is applied to the XOR problem, which used as the benchmark in the field of pattern recognition. The method is also applied to the recognition of digital image for image application. In a result of experiment, it does not always guarantee the convergence. However, the network show improved the learning time and has the high convergence rate.

• Proceedings of the KSPS conference
• /
• 2002.11a
• /
• pp.115-118
• /
• 2002

Neural networks have been known to have great discriminative power in pattern classification problems. In this paper, the multilayer perceptron neural networks are employed to automatically detect laryngeal pathology in speech. Also new feature parameters are introduced which can reflect the periodicity of speech and its perturbation. These parameters and cepstral coefficients are used as input of the multilayer perceptron neural networks. According to the experiment using Korean disordered speech database, incorporation of new parameters with cepstral coefficients outperforms the case with only cepstral coefficients.

• Proceedings of the Optical Society of Korea Conference
• /
• 1990.02a
• /
• pp.126-130
• /
• 1990

A single-layer Perceptron with 4x4 input neurons and one output neuron is optically implemented. Holo-graphic lenslet arrays are usee for the programmable optical interconnection topology. The hologram is bleached in order to increase the diffraction efficiency. It is shown that the performance of Perceptron depends on the learning rate, the inertia rate, and the correlation of input patterns.