• International Journal of Contents
• /
• 제3권2호
• /
• pp.35-39
• /
• 2007

The cognitive radio communication is taking the attentions because the development of the technique came to be possible to analyze wireless signals. In the IEEE 802.22 WRAN Systems[1], how to detect a spectrum and signals is continuously studied. In this paper, we propose the efficient signal detection method using SCF (Spectral Correlation Function). It is easy to detect the signal feature when we are using the SCF. Because most modulated signals have the cyclo-stationarity which is unique for each signal. But the fading channel effected serious influence even though it detects the feature of the signal. We applied LMS(Least Mean Square) filter for the compensation of the signal which is effected the serious influence in the fading channel. And we analyze some signal patterns through the SCF. And we show the unique signal feature of each signal through the SCF method. It is robust for low SNR(Signal to Noise Ratio) environment and we can distinguish it in the fading channel using LMS Filter.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제4권3호
• /
• pp.322-326
• /
• 2004

This paper describes a new iris recognition method based on a shift-invariant wavelet sub-images. For the feature representation, we first preprocess an iris image for the compensation of the variation of the iris and for the easy implementation of the wavelet transform. Then, we decompose the preprocessed iris image into multiple subband images using a shift-invariant wavelet transform. For feature representation, we select a set of subband images, which have rich information for the classification of various iris patterns and robust to noises. In order to reduce the size of the feature vector, we quantize. each pixel of subband images using the Lloyd-Max quantization method Each feature element is represented by one of quantization levels, and a set of these feature element is the feature vector. When the quantization is very coarse, the quantized level does not have much information about the image pixel value. Therefore, we define a new similarity measure based on mutual information between two features. With this similarity measure, the size of the feature vector can be reduced without much degradation of performance. Experimentally, we show that the proposed method produced superb performance in iris recognition.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 춘계 학술대회 발표논문집
• /
• pp.49-52
• /
• 2005

Cepstral Mean Subtraction (CMS) makes effectively compensation for a channel distortion, but there are some shortcomings such as distortions of feature parameters, waiting for the whole speech sentence. By assuming that the silence parts have the channel characteristics, we consider the channel normalization using subtraction of cepstral means which are only obtained in the silence areas. If the considered techniques are successfully used for the channel compensation, the proposed method can be used for real time processing environments or time important areas. In the experiment result, however, the performance of our method is not good as CMS technique. From the analysis of the results, we found potentiality of the proposed method and will try to find the technique reducing the gap between CMS and ours method.

• 한국음향학회지
• /
• 제23권3호
• /
• pp.228-234
• /
• 2004

본 논문에서는 공통 코드북의 평균값과 개인 코드북의 평균값 간의 바이어스 제거에 의한 채널 불일치 보상 알고리즘을 제안하였다. 제안한 방식은 학습시 공통 코드북의 센터값과 학습 데이터의 센터값과의 차수별 차를 미리 보상하여 학습하고, 확인시에도 공통 코드북의 센터값과 학습 데이터의 센터값과의 차수별 차를 보상하여 확인함으로써 채널의 불일치에 의한 급격한 본인 인식율 하락을 해결한다. 그러나 무조건적인 평균값 보상은 사칭자의 인증오류를 가져오게 되므로 채널의 변이에 비례하는 적절한 가중치를 통한 평균값 보상이 필요하다. 따라서, 제안하는 방식은 음성구간을 제외한 묵음구간의 분포를 고려하여 학습시 채널과의 변이차이를 비선형함수에 의한 가중치로 보상해준다. 모의 실험 결과 기존의 켑스트럼 평균 차감법을 사용할 때보다 제안한 알고리즘을 적용했을 때의 본인 거부 오류율이 평균 14.95% 감소함을 알 수 있었다.

• 한국정밀공학회지
• /
• 제32권1호
• /
• pp.9-16
• /
• 2015

The machining-chatter stands for a sudden relative vibration appeared between a material and a tool while processing with a machine. This chatter is key factor that seriously affects the quality of processed materials as well as being a factor which causes serious damages to the tool and the machine. This study is related to the monitoring and smart control of chatter problem that can compensate machining-chatter faster and produce processed goods with more precision by autonomous compensation. The above-mentioned machining-chatter compensator includes the chatter vibration sensor and the chatter compensator that estimates the compensation value according to the sensor detecting the chatter vibration of machine-tool and the chatter vibration detected from the sensor while having a feature of being organized by interlocking with the machine-tool controller.

• 디지털산업정보학회논문지
• /
• 제5권2호
• /
• pp.167-176
• /
• 2009

In this paper, a system that detects driver's drowsiness has been implemented based on the automatic extraction and the tracking of pupils. The research also focuses on the compensation of illumination and reduction of background noises that naturally exist in the driving condition. The system, that is based on the principle of Haar-like feature, automatically collects data from areas of driver's face and eyes among the complex background. Then, it makes decision of driver's drowsiness by using recognition of characteristics of pupils area, detection of pupils, and their movements. The implemented system has been evaluated and verified the practical uses for the prevention of driver's drowsiness.

• 제어로봇시스템학회논문지
• /
• 제22권6호
• /
• pp.403-410
• /
• 2016

This paper proposes a robust image-based visual servoing scheme using a nonlinear observer for a monocular eye-in-hand manipulator. The proposed control method is divided into a range estimation phase and a target-tracking phase. In the range estimation phase, the range from the camera to the target is estimated under the non-moving target condition to solve the uncertainty of an interaction matrix. Then, in the target-tracking phase, the feature point uncertainty caused by the unknown motion of the target is estimated and feature point errors converge sufficiently near to zero through compensation for the feature point uncertainty.

• 한국멀티미디어학회논문지
• /
• 제15권1호
• /
• pp.18-31
• /
• 2012

본 논문은 다성음원에서 추출된 특성정보 기반 QbSH (Query-by-Singing/ Humming) 시스템의 매칭엔진에 대해 제안하였다. 다성음원 기반 QbSH 시스템은 사람의 노래나 허밍에서 추출된 특성정보와 MP3 파일과 같은 다성음원에서 추출된 특성정보를 비교하여, 가장 유사한 음원을 검색하는 시스템이다. 제안된 매칭엔진에는 다성음원에서 특성 추출시 발생하는 오류를 줄이고, 매칭성능을 향상시키기 위해 크로마-스케일 표현기법 (Chroma-Scale Representation), 보상기법 (Compensation) 및 비대칭적 DTW (Asymmetric Dynamic Time Warping) 알고리즘을 적용하였다. 또한 다양한 거리 함수 (Distance Metric)를 적용하여 매칭엔진의 성능향상을 확인하였다. 1,000개의 허밍 질의와 450곡의 다성음원 데이터베이스를 기반으로 제안한 QbSH 시스템의 성능 실험을 수행하다. 성능 평가를 통해 제안한 QbSH 시스템이 MRR (Mean Reciprocal Rank) 0.718의 정확도를 가지는 것으로 확인되었다.

• 융합신호처리학회논문지
• /
• 제14권3호
• /
• pp.162-168
• /
• 2013

본 논문에서는 디지털 카메라를 이용하여 사진을 촬영할 때 눈의 감긴 상태를 확인하여 이를 자동으로 보정하여 출력해주는 모듈의 구현에 관하여 연구하였다. 먼저 촬영된 영상에 대하여 얼굴 및 눈의 영역을 검출하고 눈의 상태를 인식한다. 만약 눈이 감긴 영상이 촬영되었을 때 버퍼에 임시로 저장된 이전 프레임 영상들에 대하여 눈의 상태를 인식한 후, 가장 눈의 상태가 만족스러운 영상을 이용하여 눈을 보정한 후에 사진을 출력한다. 얼굴 및 눈을 정확하게 인식하기 위해서 SURF 알고리즘과 호모그래피 방법을 적용하여 영상을 보정하는 전처리 과정을 수행한다. 얼굴 영역과 눈 영역을 검출하는 것은 Haar-like feature 알고리즘을 이용하였다. 눈을 뜨고 있는 상태인지 감은 상태인지를 눈의 영역에 대한 템플릿매칭을 이용한 유사도를 판단하여 확인한다. 본 연구에서 개발된 기능을 다양한 형태의 얼굴 환경에서 테스트한 결과 얼굴이 포함된 영상에 대하여 효과적으로 보정이 수행됨을 확인하였다.

• 한국정밀공학회지
• /
• 제28권3호
• /
• pp.330-338
• /
• 2011

Odometry is the critical factor to estimate the location of the robot. In the mobile robot with wheels, odometry can be performed using the information from the encoder. However, the information of location in the encoder is inaccurate because of the errors caused by the wheel's alignment or slip. In general, visual odometer has been used to compensate for the kinetic errors of robot. In case of using the visual odometry under some robot system, the kinetic analysis is required for compensation of errors, which means that the conventional visual odometry cannot be easily applied to the implementation of the other type of the robot system. In this paper, the novel visual odometry, which employs only the single camera toward the ground, is proposed. The camera is mounted at the center of the bottom of the mobile robot. Feature points of the ground image are extracted by using median filter and color contrast filter. In addition, the linear and angular vectors of the mobile robot are calculated with feature points matching, and the visual odometry is performed by using these linear and angular vectors. The proposed odometry is verified through the experimental results of driving tests using the encoder and the new visual odometry.