• 전자공학회논문지S
• /
• 제35S권12호
• /
• pp.55-62
• /
• 1998

두개의 영상을 정합 하는 것은 많은 컴퓨터 시각장치의 응용과정 중 기본적인 과정이다. 본 논문에서는 선형특징을 사용한 정합기법으로서 회전각도와 크기비율에 불변한 영상정합 기법을 제안한다. 영상은 edge 검출, 세선화, 선형화 과정에 의해 선형 세그먼트의 집합으로 묘사된다. 세그먼트 사이의 각도차이와 새로운 거리척도에 의한 크기비율을 사용해 Hough 공간에서 최대로 일치하는 변환 파라메터를 추정한다. 추정된 파라메터는 1단계 relaxation과 Hough 기법으로 이루어진 고속 선형특징 정합과정에 의해 검증된다. 제안한 기법은 변환 파라메터에 대한 사전정보를 필요로 하지 않으며 추출된 선형 세그먼트 크기의 변화에 민감하지 않은 특성과 기존의 relaxation 기법에 비해 빠른 처리속도를 가진다.

• 디지털콘텐츠학회 논문지
• /
• 제15권6호
• /
• pp.675-682
• /
• 2014

전립선은 남자에게만 있는 장기이다. 전립선의 질병을 진단하기 위하여 일반적으로 TRUS 영상이 사용되는데, 희미한 전립선 경계나 잡음, 좁은 그레이 레벨 분포 때문에, 전립선의 경계를 검출하는 것은 상당히 어려운 작업 중의 하나이다. 본 논문에서는 SVM을 사용하여 TRUS 영상에서 자동적으로 전립선 분할을 하는 방법을 제안한다. 이 방법은 전처리, 가버 특징 추출, 훈련, 전립선 분할 과정으로 진행된다. 전처리 과정에서 잡음 제거는 스틱 필터와 top-hat 변환이 적용된다. 회전 불변 텍스처 추출을 위하여 가버 필터 뱅크가 사용된다. 훈련과정에서 SVM은 전립선과 비전립선의 각 특징을 얻기 위해 사용되며, 마지막으로 전립선 경계가 추출된다. 여러 실험 결과로 제안 방법은 충분히 유효하고, 의사의 수동 추출 방법과 비교했을 때 10%미만의 경계 차이를 보였다.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 Proceedings of the Korea Automatic Control Conference, 11th (KACC); Pohang, Korea; 24-26 Oct. 1996
• /
• pp.16-19
• /
• 1996

In this paper, a sliding mode control scheme that guarantees the smoothness of the control signal and the exponential error convergence is proposed for robot manipulators. The proposed method inserts a low pass filter (LPF) in front of the plant, and the virtual controller is designed for the virtual plant - the combination of the LPF and the robot manipulator. The virtual control signal contains high frequency components because of a switching function. The real control signal, however, always shows a smooth curve since it is an output of the LPF. In addition to the smoothness of the control signal is always assured, the overall system is in the sliding mode at all times, that is, its performance is always invariant under the existence of parameter uncertainties and external disturbances. The closed-loop system is shown to be globally exponentially stable.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1990년도 추계학술대회 논문집 학회본부
• /
• pp.421-424
• /
• 1990

An iterative learning control scheme for exact-tracking control and parameter estimation of uncertain robotic systems is presented. In the learning control structure, tracking and feedforward input converge globally and asymptotically as iteration increases. Since convergence of parameter errors depends only on the persistent exciting condition of system trajectories along the iteration independently of length of trajectories, it may be achieved with only system trajectories of small duration. In addition, these learning control schemes are expected to be effectively applicable to time-varying parametric systems as well as time-invariant systems, for the parameter estimation is performed at each fixed time along the iteration. Finally, no usage of acceleration signal and no in version of estimated inertia matrix in the parameter estimator makes these learning control schemes more feasible.

• 대한수학회보
• /
• 제54권6호
• /
• pp.2043-2051
• /
• 2017

Consider a sequence of compactly supported Hamiltonian diffeomorphisms ${\phi}_k$ of an exact symplectic manifold, all of which are "graphical" in the sense that their graphs are identified by a Darboux-Weinstein chart with the image of a one-form. We show by an elementary argument that if the ${\phi}_k$ $C^0$-converge to the identity, then their Calabi invariants converge to zero. This generalizes a result of Oh, in which the ambient manifold was the two-disk and an additional assumption was made on the Hamiltonians generating the ${\phi}_k$. We discuss connections to the open problem of whether the Calabi homomorphism extends to the Hamiltonian homeomorphism group. The proof is based on a relationship between the Calabi invariant of a $C^0$-small Hamiltonian diffeomorphism and the generalized phase function of its graph.

• Journal of information and communication convergence engineering
• /
• 제9권2호
• /
• pp.207-211
• /
• 2011

This paper presents a method for facial feature representation and recognition from the Covariance Matrices of the Gabor-filtered images. Gabor filters are a very powerful tool for processing images that respond to different local orientations and wave numbers around points of interest, especially on the local features on the face. This is a very unique attribute needed to extract special features around the facial components like eyebrows, eyes, mouth and nose. The Covariance matrices computed on Gabor filtered faces are adopted as the feature representation for face recognition. Geodesic distance measure is used as a matching measure and is preferred for its global consistency over other methods. Geodesic measure takes into consideration the position of the data points in addition to the geometric structure of given face images. The proposed method is invariant and robust under rotation, pose, or boundary distortion. Tests run on random images and also on publicly available JAFFE and FRAV3D face recognition databases provide impressively high percentage of recognition.

• 통합자연과학논문집
• /
• 제12권4호
• /
• pp.122-126
• /
• 2019

In this paper, we propose a simple and efficient retrieval technique using the feature value of the corner region, which is one of the shape information attributes of images. The proposed algorithm extracts the edges and corner points of the image and rearranges the feature values of the corner regions doubly, and then measures the similarity with the image in the database using the correlation of these feature values as the feature vector. The proposed algorithm is confirmed to be more robust to rotation and size change than the conventional image retrieval method using the corner point.

• International journal of advanced smart convergence
• /
• 제9권3호
• /
• pp.85-96
• /
• 2020

It is important to extract salient object image and to solve the invariance problem for image recognition. In this paper we propose a new hybrid algorithm for invariance and improved classification performance in image recognition, whose algorithm is combined by FT(Frequency-tuned Salient Region Detection) algorithm, Guided filter, Zernike moments, and a simple artificial neural network (Multi-layer Perceptron). The conventional FT algorithm is used to extract initial salient object image, the guided filtering to preserve edge details, Zernike moments to solve invariance problem, and a classification to recognize the extracted image. For guided filtering, guided filter is used, and Multi-layer Perceptron which is a simple artificial neural networks is introduced for classification. Experimental results show that this algorithm can achieve a superior performance in the process of extracting salient object image and invariant moment feature. And the results show that the algorithm can also classifies the extracted object image with improved recognition rate.

• 한국해양공학회지
• /
• 제3권2호
• /
• pp.559-559
• /
• 1989

This paper deals with the robust controller design of robot manipulator to track a desired trajectory in spite of the presence of unmodelled dynamics in cause of nonlinearity and parameter uncertainty. The approach follwed in this paper is based on model reference adaptive control technique and convergence on hyperstability theory but it does away with the assumption that process is characterized by a linear model remaining time invariant during adaptation process. The performance of controller is demonstrated by computed simulation about position and speed control of six link manipulator in case of disturbance and payload variation.

• 한국해양공학회지
• /
• 제3권2호
• /
• pp.59-69
• /
• 1989

This paper deals with the robust controller design of robot manipulator to track a desired trajectory in spite of the presence of unmodelled dynamics in cause of nonlinearity and parameter uncertainty. The approach follwed in this paper is based on model reference adaptive control technique and convergence on hyperstability theory but it does away with the assumption that process is characterized by a linear model remaining time invariant during adaptation process. The performance of controller is demonstrated by computed simulation about position and speed control of six link manipulator in case of disturbance and payload variation.