• The Transactions of the Korea Information Processing Society
• /
• v.6 no.5
• /
• pp.1393-1402
• /
• 1999

This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.466-471
• /
• 2006

IAn important problem of pattern recognition is to extract or select feature set, which is included in the pre-processing stage. In order to extract feature set, Principal component analysis has been usually used and SFS(Sequential Forward Selection) and SBS(Sequential Backward Selection) have been used as a feature selection method. This paper applies genetic algorithm which is a popular method for nonlinear optimization problem to the feature selection problem. So, we call it Genetic Algorithm Feature Selection(GAFS) and this algorithm is compared to other methods in the performance aspect.

• ETRI Journal
• /
• v.29 no.3
• /
• pp.292-299
• /
• 2007

In this paper, we present a speech recognition system using a throat microphone. The use of this kind of microphone minimizes the impact of environmental noise. Due to the absence of high frequencies and the partial loss of formant frequencies, previous systems using throat microphones have shown a lower recognition rate than systems which use standard microphones. To develop a high performance automatic speech recognition (ASR) system using only a throat microphone, we propose two methods. First, based on Korean phonological feature theory and a detailed throat signal analysis, we show that it is possible to develop an ASR system using only a throat microphone, and propose conditions of the feature extraction algorithm. Second, we optimize the zero-crossing with peak amplitude (ZCPA) algorithm to guarantee the high performance of the ASR system using only a throat microphone. For ZCPA optimization, we propose an intensification of the formant frequencies and a selection of cochlear filters. Experimental results show that this system yields a performance improvement of about 4% and a reduction in time complexity of 25% when compared to the performance of a standard ZCPA algorithm on throat microphone signals.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2013.10a
• /
• pp.77-80
• /
• 2013

SURF algorithm is an algorithm to extract feature points and to generate descriptors from input images. It is robust to change of environment such as scale, rotation, illumination and view points. Because of these features, it is used for many image processing applications such as object recognition, constructing panorama pictures and 3D image restoration. But there is disadvantage for real time operation because many recognition algorithms such as SURF algorithm requires a lot of calculations. In this paper, we propose a design of feature extractor and descriptor generator based on SURF for high memory efficiency. The proposed design reduced a memory access and memory usage to operate in real time.

• Journal of the Korean Society for Precision Engineering
• /
• v.31 no.11
• /
• pp.1031-1040
• /
• 2014

In this paper, a new condition diagnosis algorithm for the lens injection molding process using various features extracted from cavity pressure, nozzle pressure and screw position signals is developed with the aid of probability neural network (PNN) method. A new feature extraction method is developed for identifying five (5), seven (7) and two (2) critical features from cavity pressure, nozzle pressure and screw position signals, respectively. The node energies extracted from cavity and nozzle pressure signals are also considered based on wavelet packet decomposition (WPD). The PNN method is introduced to build the condition diagnosis model by considering the extracted features and node energies. A series of the lens injection molding experiments are conducted to validate the model, and it is demonstrated that the proposed condition diagnosis model is useful with high diagnosis accuracy.

• Journal of Korea Multimedia Society
• /
• v.15 no.2
• /
• pp.195-203
• /
• 2012

This paper proposes ground target classification algorithm based on decision fusion and feature extraction method using multi-sensor images. The decisions obtained from the individual classifiers are fused by applying a weighted voting method to improve target recognition rate. For classifying the targets belong to the individual sensors images, features robust to scale and rotation are extracted using the difference of brightness of CM images obtained from CCD image and the boundary similarity and the width ratio between the vehicle body and turret of target in FLIR image. Finally, we verity the performance of proposed ground target classification algorithm and feature extraction method by the experimentation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.7
• /
• pp.3594-3607
• /
• 2017

The traditional feature extraction methods such as principal component analysis (PCA) cannot obtain the local structure of the samples, and locally linear embedding (LLE) cannot obtain the global structure of the samples. However, a common drawback of existing PCA and LLE algorithm is that they cannot deal well with the sparse problem of the samples. Therefore, by integrating the globality of PCA and the locality of LLE with a sparse constraint, we developed an improved and unsupervised difference algorithm called Sparse Difference Embedding (SDE), for dimensionality reduction of high-dimensional data in small sample size problems. Significantly differing from the existing PCA and LLE algorithms, SDE seeks to find a set of perfect projections that can not only impact the locality of intraclass and maximize the globality of interclass, but can also simultaneously use the Lasso regression to obtain a sparse transformation matrix. This characteristic makes SDE more intuitive and more powerful than PCA and LLE. At last, the proposed algorithm was estimated through experiments using the Yale and AR face image databases and the USPS handwriting digital databases. The experimental results show that SDE outperforms PCA LLE and UDP attributed to its sparse discriminating characteristics, which also indicates that the SDE is an effective method for face recognition.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.175-180
• /
• 2018

In this paper, a feature extraction and object recognition algorithm using only morphological operations is proposed. The morphological operations used in feature extraction are erosion and dilation, opening and closing combining erosion and dilation, and morphological edge and skeleton detection operation. In the process of recognizing an object based on features, a pooling operation is applied to reduce the dimension. Among various structuring elements, $3{\times}3$ rhombus, $3{\times}3$ square, and $5{\times}5$ circle are arbitrarily selected in morphological operation process. It has confirmed that the proposed algorithm can be applied in object recognition fields through experiments using Internet images.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.18 no.10
• /
• pp.965-975
• /
• 2005

In the case of the fault in stator windings of a high voltage motor. it facilitates certain destructive characteristics in insulations. This will result in a decreased reliability in power supplies and will prevent the generation of electricity, which will result in huge economic losses. This study simulates motor windings using normal windings and four faulty windings for an actual fault in stator winding of a high voltage motor. The partial discharge signals produced in each faulty winding were measured using an 80 PF epoxy/mica coupler sensor. In order to quantified signal waves its a way of feature extraction for each faulty signal, the signal wave of winding was quantified to measure the degree of skewness shape and kurtosis, which are both types of statistical parameters, using a discrete wavelet transformation method for each faulty type. Wave types present different types lot each faulty type, and the skewness and kurtosis also present different quantified values. The result of feature extraction was used as a preprocessing stage to identify a certain fault in stater windings. It is evident that the type of faulty signals can be classified from the test results using faulty signals that were randomly selected from the signal, which was not applied in the training after the training and learning period, by applying it to a back-propagation algorithm due to the supervising and learning method in a neural network in order to classify the faulty type. This becomes an important basis for studying diagnosis methods using the classification of faulty signals with a feature extraction algorithm, which can diagnose the fault of stator windings in the future.

• Journal of IKEEE
• /
• v.25 no.2
• /
• pp.273-279
• /
• 2021

In this paper, we propose an algorithm that shortens the learning time by performing individual learning using partitioning the deep learning structure. The proposed algorithm consists of four processes: network classification origin setting process, feature vector extraction process, feature noise removal process, and class classification process. First, in the process of setting the network classification starting point, the division starting point of the network structure for effective feature vector extraction is set. Second, in the feature vector extraction process, feature vectors are extracted without additional learning using the weights previously learned. Third, in the feature noise removal process, the extracted feature vector is received and the output value of each class is learned to remove noise from the data. Fourth, in the class classification process, the noise-removed feature vector is input to the multi-layer perceptron structure, and the result is output and learned. To evaluate the performance of the proposed algorithm, we experimented with the Extended Yale B face database. As a result of the experiment, in the case of the time required for one-time learning, the proposed algorithm reduced 40.7% based on the existing algorithm. In addition, the number of learning up to the target recognition rate was shortened compared with the existing algorithm. Through the experimental results, it was confirmed that the one-time learning time and the total learning time were reduced and improved over the existing algorithm.