• The Magazine of the IEIE
• /
• v.39 no.2
• /
• pp.36-44
• /
• 2012

본 논문에서는 최근 얼굴 인식 평가에 많이 사용된 FRGC Ver 2.0 DB와 그 프로토콜을 간략히 소개하고 이를 이용한 다양한 얼굴 인식 방법 및 그 개발 동향에 대해서 살펴보고자 한다. FRGC는 객관적인 2D/3D 얼굴 인식 알고리즘 성능 평가를 위해서 공개되었는데, 본 논문에서는 2D 정면 얼굴 인식에 대한 내용을 위주로 기술하고자 한다. FRGC의 2D 얼굴 인식 DB는 주로 조명의 Control 유무에 따른 성능 비교를 위한 평가 프로토콜을 제안하고 있다. 이에 2004년부터 최근까지 10개 이상의 알고리즘이 발표되었고, 본 논문에서는 중요한 11개의 알고리즘을 살펴보고자 한다. 또한 이들 알고리즘에서 핵심적으로 사용되는 특징 추출 알고리즘을 살펴보고 마지막으로 각 알고리즘의 FRGC DB에서의 성능을 비교 평가하고자 한다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• spring
• /
• pp.37-40
• /
• 2002

최근 음성 인식 시스템의 성능 향상을 위해 화자 적응(speaker adaptation)에 대한 연구가 활발히 진행되고 있다. HMM 기반 인식 시스템의 모델 파라미터를 수정하는 화자 적응의 경우, MAP 방법과 MLLR 방법에 대한 연구가 주류를 이루고 있다. 두 방법은 adaptation data의 양에 따라서 서로 다른 성능을 보인다. 본 논문에서는 adaptation data의 quality를 정의하고, 이를 기존 두 방법의 가중치로 이용하여 화자 적응을 수행하는 방법을 제안한다. 제안한 방법을 KAIST 통신연구실에서 구축한 한국어 도시이름 500단어 인식 시스템에 적용하여 성능을 개선하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2004.05a
• /
• pp.773-776
• /
• 2004

본 논문에서는 에지 검출기에 의해 다양한 명암이 존재하는 차량 번호판 영역의 사각형 에지를 검출시 사용되는 소벨 및 Prewitt, Roberts, 가우시안의 라플라시안, 그리고 Canny 검출기를 사용하여 처리 속도와 에지 검출의 정확성을 실험하여 각 연산자의 성능을 평가하였다. 기존의 Sobel 에지 검출기는 적응적 임계값을 구하지 않으면 다양한 조명의 영향에 강인하지 못하다. 또한 Canny 에지 검출기는 조명의 영향에 강인하기는 하나, 계산량이 Sobel 보다는 많아 처리 속도가 느리다. 색상에 의해 번호판 후보 영역을 추출한 후 에지 검출기 번호판 내의 명암이 둘 이상으로 차량 번호판 영역에 대해서, 다양한 에지 검출기를 적용하여 속도와 에지 검출 성능을 비교 평가하고자 한다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.8A
• /
• pp.664-670
• /
• 2005

OFDM is a very attractive technique for achieving high-bit-rate data transmission and high spectrum efficiency in fading environment. However, the reliable detection of an OFDM signal in time-varying multipath fading channels is a challenging problem. Accordingly, various channel estimation methods have been proposed for performance improvement. But, conventional pilot patterns for channel estimation in OFDM systems have not robust characteristics relating to various mobile speed. To solve this drawback in conventional patterns, we propose the pilot patterns modified from conventional patterns to have a good error performance in time-varying fading channel. Simulation results show that the performance of the proposed pilot patterns is better than conventional patterns in fast time-varying channel.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1075-1082
• /
• 2007

In this paper, we propose the method of multiple human action recognition on video clip. For being invariant to the change of speed or size of actions, Spatial-Temporal Pyramid method is applied. Proposed method can minimize the complexity of the procedures owing to select Motion Gradient Histogram (MGH) based on statistical approach for action representation feature. For multiple action detection, Motion Energy Image (MEI) of binary frame difference accumulations is adapted and then we detect each action of which area is represented by MGH. The action MGH should be compared with pre-learning MGH having pyramid method. As a result, recognition can be done by the analyze between action MGH and pre-learning MGH. Ten video clips are used for evaluating the proposed method. We have various experiments such as mono action, multiple action, speed and site scale-changes, comparison with previous method. As a result, we can see that proposed method is simple and efficient to recognize multiple human action with stale variations.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.4A
• /
• pp.269-277
• /
• 2012

When there are mismatches between the beamforming steering vector and the array response vector for the desired signal, the performance can be severely degraded as the adaptive array attempts to suppress the desired signal as well as interferences. In this paper, an robust method is proposed for the adaptive array in the presence of both direction errors and random errors in the steering vector. The proposed method first finds a signal-plus-interference subspace (SIS) from the correlation matrix, which in turn is exploited to extract an interference subspace based on the structure of a uniform linear array (ULA), the effect of the desired signal direction vector being reduced as much as possible. Then, the weight vector is attained to be orthogonal to the interference subspace. Simulation shows that the proposed method, in terms of signal-to-interference plus noise ratio (SINR), outperforms existing ones such as the doubly constrained robust Capon beamformer (DCRCB).

• Journal of KIISE
• /
• v.42 no.2
• /
• pp.190-202
• /
• 2015

Much research has been conducted on location-based intelligent personal assistants that can understand a user's intention by learning the user's route model and then inferring the user's destinations and routes using data of GPS and other sensors in a smartphone. The intelligence of the location-based personal assistant is contingent on the accuracy and efficiency of the real-time predictions of the user's intended destinations and routes by processing movement information based on uncertain sensor data. We propose a robust particle filter based on Dynamic Bayesian Network model to infer the user's routes. The proposed robust particle filter includes a particle generator to supplement the incorrect and incomplete sensor information, an efficient switching function and an weight function to reduce the computation complexity as well as a resampler to enhance the accuracy of the particles. The proposed method improves the accuracy and efficiency of determining a user's routes and destinations.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.19 no.7
• /
• pp.1694-1704
• /
• 2015

In this paper, a robust trajectory tracking control method of a wheeled mobile robot is newly proposed combining the PDC and the ISMC. The PDC is a relatively simple and easy control method for nonlinear system compared to the other non-linear control methods. And the ISMC can have robust and stable control characteristics against model uncertainties and disturbances from the initial time by placing the states on the sliding plane with desired nominal dynamics. Therefore, the proposed PDC+ISMC trajectory tracking control method shows robust trajectory tracking performance in spite of external disturbance. The tracking performance of the proposed method is verified through simulations. Even though the disturbance increases, the proposed method keeps the performance of the PDC method when there is no disturbance. However, the PDC trajectory tracking control method has increasing tracking error unlike the proposed method when the disturbance increases.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.48 no.5
• /
• pp.373-381
• /
• 2020

Quadrotor is simple to model because of the symmetric structure but it has the disadvantage of being relatively sensitive to the external disturbance and system uncertainty. The PID technique applied for the attitude control of quadrotor has been applied comprehensively, but it has a disadvantage that is hard to precise control in the nonlinear system. In this work, a quadrotor attitude control law using the super twisting algorithm is studied, which has robust characteristics against disturbance and system uncertainty. To evaluate the attitude performance by the proposed technique, simulation studies and actual flight tests are carried out, and compared with the conventional PID controller.

• Journal of KIISE:Software and Applications
• /
• v.33 no.5
• /
• pp.481-488
• /
• 2006

The performance of face recognition methods using subspace projection is directly related to the characteristics of their basis images, especially in the cases of local distortion or partial occlusion. In order for a subspace projection method to be robust to local distortion and partial occlusion, the basis images generated by the method should exhibit a part-based local representation. We propose an effective part-based local representation method named locally salient ICA (LS-ICA) method for face recognition that is robust to local distortion and partial occlusion. The LS-ICA method only employs locally salient information from important facial parts in order to maximize the benefit of applying the idea of 'recognition by parts.' It creates part-based local basis images by imposing additional localization constraint in the process of computing ICA architecture I basis images. We have contrasted the LS-ICA method with other part-based representations such as LNMF (Localized Non-negative Matrix Factorization) and LFA (Local Feature Analysis). Experimental results show that the LS-ICA method performs better than PCA, ICA architecture I, ICA architectureII, LFA, and LNMF methods, especially in the cases of partial occlusions and local distortions.