• Journal of Broadcast Engineering
• /
• v.19 no.6
• /
• pp.967-970
• /
• 2014

An efficient peak detection algorithm in magnitude spectrum is proposed to distinguish the M-frequency shift keying(FSK) signals from other digitally modulated signal. In addition, recognition of the modulation order estimation of FSK signals is also studied based on the fact that the magnitude spectrum of FSK signals reveals the number of peaks equal to the modulation order. When no a priori information about the signals, we utilize the histogram of the magnitude spectrum to determine the threshold which is important factor in peak detection algorithm. The simulation results show high probability of classification under 500 symbols and signal-to-noise ratio(SNR) higher than 4dB.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.21 no.5
• /
• pp.1256-1265
• /
• 1996

Soft-decision detectors are used in many FEC and ARQ schemes to enhance the bit-error-probability and system throughput. Also, the hybrid-ARQ protocol is a very efficient schemeto achieve overall performance improvement. In this paper, we propose a new hybrid-ARQ protocol based on the first-order Reed-Muller codes employing soft-decision detectors. The Reed-Muller codes have the virtue of being able to use the fast Green machine decoder that is simple to implement. As the performance measures, the bit-error-probability and system throughput are evaluted for the proposed hybrid-ARQ procol, and compared with those of other hybrid-ARQ schemes. It is shown that the use of the proposed hybrid-ARQ protocol results in significant performance improvement without causing much loss in view of system complexity.

• Journal of Biomedical Engineering Research
• /
• v.15 no.4
• /
• pp.447-454
• /
• 1994

A method has been proposed for the fully automatic detection of left ventricular endocardial boundary in 2D short axis echocardlogram using geometric model. The procedure has the following three distinct stages. First, the initial center is estimated by the initial center estimation algorithm which is applied to decimated image. Second, the center estimation algorithm is applied to original image and then best-fit elliptic model estimation is processed. Third, best-fit boundary is detected by the cost function which is based on the best-fit elliptic model. The proposed method shows effective result without manual intervention by a human operator.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2011.07a
• /
• pp.494-495
• /
• 2011

본 논문에서는 스마트 TV 시청시에 녹화하는 골프 동영상에서 오디오기반의 경계영역 검출를 이용하여 썸네일을 고속으로 생성하는 방법을 제안한다. 제안된 방법은 녹화되는 골프동영상의 인코딩된 오디오 정보로 부터 추출된 MDCT계수를 이용하여 온셋 구간 검출 및 오디오 세그먼테이션을 수행함으로써 골프 동영상을 6개의 오디오 클래스로 자동 분할한다. 분할된 오디오 세그먼트와 상응하는 비디오 프레임을 맵핑하여 골프 동영상의 썸네일을 생성한다. 제안된 오디오기반 경계영역 검출방법의 성능 측정 결과, 97.4%의 Recall과 96.85%의 Precision의 우수한 분류 성능을 나타내었다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.11b
• /
• pp.889-891
• /
• 2005

본 논문에서는 실시간 영상을 대상으로 조명변화에 강인한 얼굴 영역 자동 검출 방법을 제안한다. 실시간 영상에서 가장 효율적이고 컴퓨터의 계산량을 줄일 수 있는 색상 정보를 이용하여 얼굴 영역을 추출함에 있어 색상 정보사용 시 단점인 외부 조명의 영향을 줄여주는 효과적인 조명 보정 방법을 제시하고 조명 보정에 의해 평활화된 영상에서 YCbCr 색상모델을 적용하여 얼굴 후보 영역을 검출하는 방법을 제시한다. 실험 결과 조명의 영향을 많이 받는 실시간 영상에서 적응적 조명 보정 방법으로 영상을 향상시킨 뒤 Cb, Cr 그리고 Y를 이용함으로서 기존의 방법보다. 얼굴 영역을 보다 정확하게 검출할 수 있음을 볼 수 있었다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.04a
• /
• pp.870-872
• /
• 2015

본 연구에서는 웨이퍼의 자동광학검사를 위한 결점 검출 비전 시스템을 개발하였다. 성공적 결점 검출을 위해 몇 가지 이진화 방법을 비교하였고, bimodal과 unimodal 분포에 모두 좋은 결과를 나타낸 개선된 Otsu 방법을 선택하였다. 빠르고 정확한 임계값 계산을 위해 ROI 추출기능을 개발하였으며 최종적으로 웨이퍼의 검출 패턴은 정의된 기준에 따라 영상 분류되었고 성능평가를 위해 14개 이상의 웨이퍼 영상으로 테스트하였다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.221-222
• /
• 2022

본 논문에서는 모발 정밀검사(Phototrichogram)를 통해 일정 간격을 두고 촬영된 환자의 모발 두피 사진을 이용하여 머리카락 검출 및 머리카락의 개수 변화 추이에 따른 환자의 탈모 진단에 도움을 줄 방법을 제안하였다. 모발 정밀검사를 진행하여 촬영된 환자의 모발 사진으로부터 딥러닝 기반의 영상 분할 기법(Image Segmentation)의 하나인 DetectoRS 모델을 활용하여 머리카락을 자동 검출한다. 실험 결과 DetectoRS 모델의 분할 성능은 74.74%로 효과적으로 머리카락을 검출하였음을 확인할 수 있었다.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.155-160
• /
• 2021

This paper proposes an automatic method for detecting snore sound, one of the important symptoms of sleep apnea patients. In the proposed method, sound signals generated during sleep are input to detect a sound generation section, and a spectrogram transformed from the detected sound section is applied to a classifier based on a Convolutional Bidirectional Gated Recurrent Unit (CBGRU) with attention mechanism. The applied attention mechanism improved the snoring sound detection performance by extending the CBGRU model to learn discriminative feature representation for the snoring detection. The experimental results show that the proposed snoring detection method improves the accuracy by approximately 3.1 % ~ 5.5 % than existing method.

• Nuclear Engineering and Technology
• /
• v.20 no.3
• /
• pp.170-178
• /
• 1988

An automated ultrasonic flaw detection system was developed for thin-walled and short tubes such as Zircaloy-4 tubes used for cladding heavy-water reactor fuel. The system was based on the two channels immersion pulse-echo technique using 14 MHz shear wave and the specially developed helical scanning technique, in which the tube to be tested is only rotated and the small water tank with spherical focus ultrasonic transducers is translated along the tube length. The optimum angle of incidence of ultrasonic beam was 26 degrees, at which the inside and outside surface defects with the same size and direction could be detected with the same sensitivity. The maximum permissible defects in the Zircaloy-4 tubes, i.e., the longitudinal and circumferential v notches with the length of 0.76mm and 0.38mm, respectively and the depth of 0.04 mm on the inside and outside surface, could be easily detected by the system with the inspection speed of about 1 m/min and the very excellent reproducibility. The ratio of signal to noise was greater than 20 dB for the longitudinal defects and 12 dB for the circumferential defects.

• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1161-1170
• /
• 2004

This paper proposes to segment skin color areas using a clustering algorithm. Most of previously proposed clustering algorithms have some difficulties, since they generally detect hyperspherical clusters, run in a batch mode, and predefine a number of clusters. In this paper, we use a well-known elliptical clustering algorithm, an EM algorithm, and modify it to learn on-line and find automatically the number of clusters, called to an EAM algorithm. The effectiveness of the EAM algorithm is demonstrated on a task of skin color region segmentation. Experimental results present the EAM algorithm automatically finds a right number of clusters in a given image without any information on the number. Comparing with the EM algorithm, we achieved better segmentation results with the EAM algorithm. Successful results were achieved to detect and segment skin color regions using a conditional probability on a region. Also, we applied to classify images with persons and got good classification results.