• Proceedings of the Korean Information Science Society Conference
• /
• 2007.10c
• /
• pp.415-418
• /
• 2007

본 논문은 머리카락을 포함한 얼굴 영역 추출에 관한 것으로서, 보다 구체적으로는 조명변화에도 강인 한 얼굴영역 추출방법과 다양한 머리카락의 모양과 색의 변화에도 신뢰성 있는 머리카락 추출 방법에 관한 것이다. 일반적으로 얼굴영상은 개인의 특징을 잘 표현할 수 있는 정보로써, 영상에서 얼굴 영역을 추출하여 이를 실제 얼굴영상정보를 이용한 얼굴인식, 관상정보 서비스를 위한 전처리, 기반기술을 제공하고, 실사 캐릭터 제작에도 바로 적용될 수 있다. 기존의 템플리트 매칭, 곡선추적 알고리즘 등과의 같은 추출방법에서는 얼굴크기 변화, 안경 및 장신구의 착용 여부 그리고 조명의 변화에 따라 얼굴영역 추출하는 처리속도가 많이 걸리고, 성능이 크게 저하되는 문제점이 있다. 상기한 바와 같이 종래의 문제점을 개선하기 위하여, 본 논문에서는 얼굴의 크기변화, 안경 및 장신구의 착용 여부 그리고 조명의 변화에서도 얼굴 영역을 잘 추출 할 있는 방법과 다양한 머리카락의 색, 형태 변화에도 신뢰성 있는 머리카락 추출방법을 제안하였다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.10
• /
• pp.129-136
• /
• 2015

We propose a hybrid face recognition to deal with illumination variation. For this, we extract discriminant features by using the different illumination invariant feature extraction methods. In order to utilize both advantages of each method, we evaluate the discriminant power of each feature by using the discriminant distance and then construct a composite feature with only the features that contain a large amount of discriminative information. The experimental results for the Multi-PIE, Yale B, AR and yale databases show that the proposed method outperforms an individual illumination invariant feature extraction method for all the databases.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.5
• /
• pp.25-30
• /
• 2011

This paper present a method for abnormal traffic behavior, or trajectory, detection in static traffic surveillance camera with user-defined trajectories. The method computes the abnormality of moving object with a trajectory of the object and user-defined trajectories. Because of using user-define based information, the presented method have more accurate and faster performance than models need a learning about normal behaviors. The method also have adaptation process of assigned rule, so it can handle scene variation for more robust performance. The experimental results show that our method can detect abnormal traffic behaviors in various situation.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.8
• /
• pp.140-147
• /
• 2015

In this paper, we propose a state feedback robust controller of 2-axis gimbal system which have bounded parametric uncertainty. The proposed controller is robust against dynamics variations of gimbal system and contains a dynamic compensator in order to improve a steady state error and a transient response. The stability of the closed-loop system is proved by Lyapunov approach. The performance of the proposed method is demonstrated by simulation on a 2-axis gimbal system.

• The KIPS Transactions:PartB
• /
• v.12B no.3 s.99
• /
• pp.283-290
• /
• 2005

The mismatched allocation of watermarking position due to parallel translation, rotation, and scaling distortion is a problem that requires an answer in watermarking. In this paper, we propose a watermarking method robust enough to hold against geometrical distorting using restoration pattern matching. The proposed method defines restoration pattern, then inserts the pattern to a watermark embedded image for distribution. Geometrical distortion is verified by comparing restoration pattern extracted from distributed image and the original restoration pattern inserted to the image. If geometrical distortion is found, inverse transformation is equally performed to synchronize the watermark insertion and extraction position. To evaluate the performance of the proposed method, experiments in translation, rotation, and scaling attack are performed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.3C
• /
• pp.408-418
• /
• 2004

In this paper, we propose a novel scalable video coding algorithm based on adaptively weighted multiple reference frame method. To improve the coding efficiency in the enhancement layer, the enhancement frame is predicted by the sum of adaptively weighted double motion compensated frames in the enhancement layer and the current frame in the base layer, according to the input video characteristics. By employing adaptive reference selection scheme at the decoder, the proposed method reduce the drift problem significantly. From the experimental results, the proposed algorithm shows more than 1.0 ㏈ PSNR improvement, compared with the conventional scalable H.263+ for various packet loss rate channel conditions.

• Journal of Internet Computing and Services
• /
• v.17 no.2
• /
• pp.11-17
• /
• 2016

In this paper, the optimum weight of the algorithm based on the cross information-potential with the delta functions (CIPD) is derived and its robustness against impulsive noise is studied. From the analysis of the behavior of optimum weight, it is revealed that the magnitude controlling operation for input plays the main role of keeping optimum weight of CIPD stable from the impulsive noise. The simulation results show that the steady state weight of CIPD is equivalent to that of MSE criterion. Also in the simulation environment of impulsive noise, unlike the LMS algorithm based on MSE, the steady state weight of CIPD is shown to be kept stable.

• Journal of IKEEE
• /
• v.9 no.1 s.16
• /
• pp.72-78
• /
• 2005

This paper describes the design of a robust output-feedback controller for a single-input single-output nonlinear dynamical system with a full relative degree. While all the previous research works on the output-feedback control are based on dynamic observers, a new state estimator which uses the past values of the measurable system output is proposed. We name it backward-difference state estimator since the derivatives of the output are estimated simply by backward difference of the present and past values of the output. The disturbance generated due to the error between the estimated and real state variables is compensated using an additional robustifying control law whose gain is tuned adaptively. Overall control system guarantees that the tracking error is asymptotically convergent and that all signals involved are uniformly bounded. Theoretical results are illustrated through a simulation example of inverted pendulum.

• The KIPS Transactions:PartB
• /
• v.10B no.5
• /
• pp.479-484
• /
• 2003

We propose a blind watermarking method that embeds a binary pseudo-random sequence (watermarks), (-1, 1), into wavelet dc components, while most watermarking techniques embed watermarks in the middle frequency range for robustness and fidelity. In our scheme, the watermarks are embedded into particular locations to be selected by a key, where some watermark embeddings are skipped to avoid severe degradation in quality. Our robustness is compared to some results registered to the ChechMark [1] that is one of the most popular benchmarking tools.

• Journal of IKEEE
• /
• v.7 no.2 s.13
• /
• pp.156-165
• /
• 2003

This paper describes the design of a robust adaptive fuzzy observer for uncertain nonlinear dynamical system. We propose a new method in which no strictly positive real (SPR) condition is needed. No a priori knowledge of an upper bound on the lumped uncertainty is required. The Lyapunov synthesis approach is used to guarantee a semi-global uniform ultimate boundedness property of the state observation error, as well as of all other signals in the closed-loop system. The theoretical results are illustrated through a simulation example of a mass-spring-damper system.