• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.555-562
• /
• 2012

This paper presents a hybrid method for improving the recognition performance, which is based on the nonlinear histogram equalization, features extraction, and statistical correlation of images. The nonlinear histogram equalization based on a logistic function is applied to adaptively improve the quality by adjusting the brightness of the image according to its intensity level frequency. The statistical correlation that is measured by the normalized cross-correlation(NCC) coefficient, is applied to rapidly and accurately express the similarity between the images. The local features based on independent component analysis(ICA) that is used to calculate the NCC, is also applied to statistically measure the correct similarity in each images. The proposed method has been applied to the problem for recognizing the 30-face images of 40*50 pixels. The experimental results show that the proposed method has a superior recognition performances to the method without performing the preprocessing, or the methods of conventional and adaptively modified histogram equalization, respectively.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.10C
• /
• pp.942-948
• /
• 2003

In this paper, we analyze the performance of multiple trellis coded modulation applied to continuous phase frequency shift keying (MTCM/CPFSK) for the noncoherent receiver without channel state information (CSI) on the interleaved Rician fading channel. In this system, the squared cross-correlation between the received signal and a candidate signal is used as the branch metric of the Viterbi decoder. To obtain the bit error performance of this system, we analyze the approximated pairwise error probability (PEP) and the exact PEP. We also derive the equivalent normalized squared distance (ENSD) and compare it with the ENSD of the noncoherent receiver with perfect CSI. Simulation results are also provided to verify the theoretical performance analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.7
• /
• pp.1-7
• /
• 2021

In this paper, we propose a feature selection technique for multi-label classification. Many existing feature selection techniques have selected features by calculating the relation between features and labels such as a mutual information scale. However, since the mutual information measure requires a joint probability, it is difficult to calculate the joint probability from an actual premise feature set. Therefore, it has the disadvantage that only a few features can be calculated and only local optimization is possible. Away from this regional optimization problem, we propose a feature selection technique that constructs a low-rank space in the entire given feature space and selects features with sparsity. To this end, we designed a regression-based objective function using Nuclear norm, and proposed an algorithm of gradient descent method to solve the optimization problem of this objective function. Based on the results of multi-label classification experiments on four data and three multi-label classification performance, the proposed methodology showed better performance than the existing feature selection technique. In addition, it was showed by experimental results that the performance change is insensitive even to the parameter value change of the proposed objective function.

• Korean Journal of Remote Sensing
• /
• v.37 no.2
• /
• pp.257-274
• /
• 2021

Although image segmentation is a critical part of object-based analysis of high resolution imagery, there has been lack of studies to evaluate the quality of image segmentation. In this study, we aimed to find practical and effective methods to obtain optimal parameters for image segmentation. Evaluations of image segmentation are divided into unsupervised, supervised, and qualitative visual interpretation methods. Using the multispectral UAV images, sampled from urban and forest over the Incheon Metropolitan City Park, three evaluation methods were compared. In overall, three methods showed very similar results regardless of the computational costs and applicability, although the optimal parameters determined by the evaluations were different between the urban and forest images. There is no single measure that outperforms in the unsupervised evaluation. Any combinations of intra-segment measures (V, COV, WV) and inter-segment measures (MI, BSH, DTNP) provided almost the same results. Although supervised method may be biased by subjective selection of reference data, it can be easily applied to detect object of interest. The qualitative visual interpretation on the segmentation results corresponded with the unsupervised and supervised evaluations.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.22 no.5
• /
• pp.465-473
• /
• 2002

Images are easily corrupted by noise during the data transmission, data capture and data processing. A technical method of noise analyzing and adaptive filtering for reducing of quantum noise in radiography is presented. By adjusting the characteristics of the filter according to local statistics around each pixel of the image as moving windowing, it is possible to suppress noise sufficiently while preserve edge and other significant information required in reading. We have proposed adaptive weighted median(AWM) filters based on local statistics. We show two ways of realizing the AWM filters. One is a simple type of AWM filter, whose weights are given by a simple non-linear function of three local characteristics. The other is the AWM filter which is constructed by homogeneous factor(HF). Homogeneous factor(HF) from the quantum noise models that enables the filter to recognize the local structures of the image is introduced, and an algorithm for determining the HF fitted to the detection systems with various inner statistical properties is proposed. We show by the experimented that the performances of proposed method is superior to these of other filters and models in preserving small details and suppressing the noise at homogeneous region. The proposed algorithms were implemented by visual C++ language on a IBM-PC Pentium 550 for testing purposes, the effects and results of the noise filtering were proposed by comparing with images of the other existing filtering methods.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.405-408
• /
• 2006

본 논문에서는 영상의 1차 모멘트와 주요성분분석을 이용한 효율적인 얼굴표정 인식방법을 제안하였다. 여기서 1차 모멘트는 영상의 중심이동을 위한 전처리 과정으로 인식에 불필요한 배경의 배제와 계산시간의 감소로 인식성능을 개선하기 위함이다. 또한 주요성분분석은 얼굴표정의 특징인 고유영상을 추출하는 것으로, 이는 2차의 통계성을 고려한 중복신호의 제거로 인식성능을 개선하기 위함이다. 제안된 방법을 각각 320*243 픽셀의 48개(4명*6장*2그룹) 얼굴표정을 대상으로 Euclidean 분류척도를 이용하여 실험한 결과 전처리를 수행하지 않는 기존 방법보다 우수한 인식성능이 있음을 확인하였다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.2A
• /
• pp.187-194
• /
• 2004

We propose priority-based reservation code multiple access (P-RCMA) which can enhance voice traffic quality of the previous RCMA. The proposed protocol maintains two power levels and consider traffic characteristics in contending shared available codes to transmit packets. P-RCMA gives priority to the voice request packets rather than data packets by capture effect at the receiver part of base station. We show numerical results from EPA (equilibrium point analysis) analysis and simulation study in terms of voice packet dropping probability and average data packet transmission delay.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 1997.11a
• /
• pp.49-53
• /
• 1997

본 논문에서는 평활한 완전 8방향 윤곽선을 부호화하는 법의 성능을 기존의 방법과 비교 평가한다. 평활한 완전 8방향 윤곽선은 majority filter를 이용하여 윤곽선에서 화질에 큰 영향을 미치지 않는 작은 돌출부분들을 제거함으로써 얻을 수 있고, 이의 효율적인 부호화 방법으로 2단계 움직임 보상 후 NDSC를 적용하는 기법이 소개되어 있다. 본 논문에서는 이러한 윤곽선 부호화 방법의 성능을 현지 MPEG4에서 검토중인 CAE와 비교하였다. 그 결과, 2단계 움직임 보상 후 NDSC를 적용하는 기법은 CAE에 비해 비트율을 7∼37% 감소시킬 수 있고, Dp, Dn 척도에서 본 distortion-bitrate 특성도 우수한 것으로 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.493-496
• /
• 2004

본 연구에서는 신경망 학습의 중요한 평가 척도로써 고려될 수 있는 일반화 성능과 학습속도를 개선시키기 위한 방안으로써 초기 가중값과 학습률과 같은 주요 인자들을 이용한 신경망 학습 영향을 살펴본다. 특히 초기 가중값과 학습률을 고정시킨 후 새롭게 조정된 계수들을 점차적으로 변화시키는 새로운 인자 결합방법을 이용하여 신경망 학습량과 학습속도를 비교해 보고 계수조정을 통한 개선된 학습 영향을 살펴본다. 그리고 단순한 예제를 이용한 실증분석을 통하여 신경망 모형의 일반화 성능과 학습 속도 개선을 위한 각 인자들의 개별 효과와 결합 효과를 살펴보고 그 개선 방안을 제시한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.11a
• /
• pp.583-586
• /
• 2004

본 논문에서는 자율학습의 속성을 가지는 주요성분분석을 이용한 얼굴인식 기법을 제안하였다. 이는 대용량의 입력 데이터를 통계적으로 독립인 특징들의 집합으로 변환시켜 중복신호를 제거하는 특성을 가지는 주요성분분석의 우수한 속성을 이용한 것이다. 제안된 기법을 Yale 얼굴영상 데이터베이스로부터 선택된 20개의 $320{\ast}243$ 픽셀의 영상을 대상으로 시뮬레이션한 결과, 주요성분의 개수에 따른 압축성능과 city-block, Euclidian, 그리고 negative angle(cosine)의 거리척도에 따른 인식에서의 분류성능에서 우수한 성능이 있음을 확인할 수 있었다.