• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.14 no.6
• /
• pp.663-674
• /
• 1989

In order to design the automatic processing system of image document, the pattern segmentation of image document and classification methods are presented. The contour extraction using first order differential operator of Gauassian distribution fucntions, the image segmentation using the chain code, and the pattern classication using the second order moments and two=dimensional Rf distance(in transform domain) are implemented. The resuts applied in specially documantated image shows to classify the characters, fingerprints, seals etc well. And the utility of the used algorithms is verified.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.354-354
• /
• 2000

In this paper, we would study the applicability of neural networks to the recognition process of Korean stenographic character image, applying the classification function, which is the greatest merit of those of neural networks applied to the various pans so far, to the stenographic character recognition, relatively simple classification work. Korean stenographic recognition algorithms, which recognize the characters by using some methods, have a quantitative problem that despite the simplicity of the structure, a lot of basic characters are impossible to classify into a type. They also have qualitative one that it is not easy to classify characters for the delicacy of the character forms. Even though this is the result of experiment under the limited environment of the basic characters, this shows the possibility that the stenographic characters can be recognized effectively by neural network system. In this system, we got 90.86% recognition rate as an average.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.99-102
• /
• 1997

A neural spike sorting technique has been developed that also has the capability of template learning. A system of software has been written that first obtains the templates by learning, and then performs the sorting of the spikes into single units. The spike sorting can be done in real time. The template learning consists of spike detection based on the discrete Haar transform (DHT), feature extraction by clustering of spike amplitude and duration, classification based on rms error, and fabrication of templates. The developed algorithms can be implemented into real time systems using digital signal processors.

• Korean Journal of Remote Sensing
• /
• v.34 no.4
• /
• pp.591-600
• /
• 2018

Recent SAR systems provide fully polarimetric SAR data, which is known to be useful in a variety of applications such as disaster monitoring, target recognition, and land cover classification. The objective of this study is to evaluate the performance of polarization SAR data for landslide detection. The detectability of different SAR parameters was investigated based on the supervised classification approach. The classifier used in this study is the Adaptive Boosting algorithms. A fully polarimetric L-band PALSAR-2 data was used to examine landslides caused by the 2016 Kumamoto earthquake in Kyushu, Japan. Experimental results show that fully polarimetric features from the target decomposition technique can provide improved detectability of landslide site with significant reduction of false alarms as compared with the single polarimetric observables.

• Journal of Biosystems Engineering
• /
• v.24 no.1
• /
• pp.67-74
• /
• 1999

A prototype cut-flower sorter was developed and tested for its performance with five varieties of roses. Support plates driven by a chain mechanism transported the roses into an image inspection chamber. Color image processing algorithms were developed to evaluate the length, thickness, and straightness of stem and color, height, and maturity of bud. The average absolute errors of the system for the measurements of stem length, stem thickness, and height of bud were 19.7 mm, 0.5 mm, and 3.8 mm, respectively. The results of classification by the sorter were compared with those of a human inspector for straightness of stem and maturity of bud. The classification error for the straightness of stem was 8.6%, when both direct image and reflected image by a mirror were analyzed. The accuracy in classifying the maturity of bud varied among the varieties, the smallest for‘Nobless’(1.5%) and the largest for‘Rote Rose’(13.5%). The time required to process a rose averaged 2.06 seconds, equivalent to the capacity of 1,600 roses per hour.

• Journal of the Korean Data and Information Science Society
• /
• v.12 no.2
• /
• pp.113-124
• /
• 2001

CHAID, logistic regression, bagging trees, and bagging trees are compared on SAS artificial data set as HMEQ in terms of classification accuracy and training time. In error rates, bagging trees is at the top, although its run time is slower than those of others. The run time of logistic regression is best among given models, but there is no uniformly efficient model satisfied in both criteria.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.49 no.5
• /
• pp.269-277
• /
• 2000

We propose two new types multi-stage blind clustering equalizers for QAM demoulation, which are called a complex classification algorithm(CCA) and a radial basis function algorithm(RBFA). The CCA uses a clustering technique based on the joint gaussian probability function and computes separately the real part and imaginary part for simple implementation as well as less computation. In order to improve the performance of CCA, the Dual-Mode CCA(DMCCA) incorporates the CCA tap-updating mode with the decision-directed(DD) mode. The RBFA reduces the number of cluster centers through three steps using the classification technique of RBF and then updates the equalizer taps for QAM demodulation. Test results on 16-QAM confirm that the proposed algorithms perform better the conventional multi-state equalizers in the senses of SER and MSE under multi-path fading channel.

• KIEE International Transaction on Systems and Control
• /
• v.12D no.1
• /
• pp.27-32
• /
• 2002

In this paper, we would study the applicability of neural networks to the recognition process of Korean stenographic character image, applying the classification function, which is the greatest merit of those of neural networks applied to the various parts so far, to the stenographic character recognition, relatively simple classification work. Korean stenographic recognition algorithms, which recognize the characters by using some methods, have a quantitative problem that despite the simplicity of the structure, a lot of basic characters are impossible to classify into a type. They also have qualitative one that It Is not easy to classify characters fur the delicacy of the character farms. Even though this is the result of experiment under the limited environment of the basic characters, this shows the possibility that the stenographic characters can be recolonized effectively by neural network system. In this system, we got 90.86% recognition rate as an average.

• Journal of Intelligence and Information Systems
• /
• v.3 no.2
• /
• pp.83-91
• /
• 1997

DELVAUX is an inductive learning environment that learns Bayesian classification rules from a set o examples. In DELVAUX, a genetic a, pp.oach is employed to learn the best rule-set, in which a population consists of rule-sets and rule-sets generate offspring by exchanging some of their rules. We have explored a meta-learning a, pp.oach in the DELVAUX learning environment to improve the classification performance of the DELVAUX system. The meta-learning a, pp.oach learns the bias of a classifier so that it can evaluate the prediction made by the classifier for a given example and thereby improve the overall performance of a classifier system. The paper discusses the meta-learning a, pp.oach in details and presents some empirical results that show the improvement we can achieve with the meta-learning a, pp.oach.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.19 no.2
• /
• pp.236-243
• /
• 2016

This paper presents a threat list acquisition method in an engagement area using the support vector machines (SVM). The proposed method consists of track creation, track estimation, track feature extraction, and threat list classification. To classify the threat track robustly, dynamic track estimation and pattern recognition algorithms are used. Dynamic tracks are estimated accurately by approximating a track movement using position, velocity and time. After track estimation, track features are extracted from the track information, and used to classify threat list. Experimental results showed that the threat list acquisition method in the engagement area achieved about 95 % accuracy rate for whole test tracks when using the SVM classifier. In case of improving the real-time process through further studies, it can be expected to apply the fire control systems.