• Journal of KIISE:Software and Applications
• /
• 제28권2호
• /
• pp.132-140
• /
• 2001

야외에서 인지되는 자연 경치는 다양한 개체, 빛의 산란, 또는 변화를 주는 많은 요소들 때문에 컴퓨터 영상처리에서 인식하기가 쉽지 않다. 본 논문에서는 다층 인지 신경망을 이용하여 도로가 포함된 야외영상에 나타나는 개체들을 인식하는 방법을 연구하였다. 자연 영상을 영역화한 후, 각각의 영역들에 대하여 색상과 기하학적인 특성에 근거하여 특성벡터를 추출하고 이를 신경망에 입력하여 각 영역을 구분하는 2단계의 알고리듬을 제안한다. 먼저 야외 영상들을 개선된 영역 확장법과 병합과정에 의하여 개체별로 영역화하였다. 영역화된 연상은 자연 영상과 함께 영상 데이타베이스에 저장되고, 이 자료들을 이용하여 각 영역의 특성벡터를 계산하였다. 이 특성 벡터를 구성된 신경망의 입력층에 전달하면, 각 영역은 27개의 개체 중의 하나로 출력층에서 인식된다. 제안된 방법은 학습에 사용된 데이타, 학스베 사용되지 않은 새로운 데이타, 그리고 모두 합하여 놓은 데이타의 세가지 데이타 군에서 무작위로 선별하여 인식률을 측정하였다. 학습된 데이타에서는 99.4%까지의 인식률을 보여주었고, 학습되지 않은 데이타에 대해서도 최고 89.1%까지의 인식률을 나타내었다. 제안된 방법은 평균적으로 88.1%~97.9%의 인식률을 보여주어 자연 경치의 인식에 신뢰성이 있는 방법으로 사용될 수 있음을 증명하였다.

• The Proceedings of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• 제9권6호
• /
• pp.41-48
• /
• 1995

In field oriented control of Induction motors, speed sensor is required, which reduces the sturdiness of drive system and together with the expenditure of hardware for faultless transmission and processing of sensor signals it causes considerable expenses. These expensive sensors can be replaced by speed sensorless concept. And for good control, the knowledge of the rotor flux component or the rotor resistance are needs. Thus, this paper is based on a Extended Kalman Filter (EKF) that estimates the state variables that are required for the control by only measuring the line voltages and currents of the machine. the rotor time constant and speed estimated by the EKF show satisfactory agreement with the real values, with the simulation approaches.

• The Journal of the Korea Contents Association
• /
• 제16권10호
• /
• pp.687-692
• /
• 2016

Conventional way to search documents is keyword-based queries using vector space model, like tf-idf. Searching process of documents which is based on keywords can make some problems. it cannot recogize the difference of lexically different but semantically same words. This paper studies a scheme of document search based on document queries. In particular, it uses centrality vectors, instead of tf-idf vectors, to represent query documents, combined with the Word2vec method to capture the semantic similarity in contained words. This scheme improves the performance of document search and provides a way to find documents not only lexically, but semantically close to a query document.

• The Journal of the Korea Contents Association
• /
• 제7권12호
• /
• pp.322-332
• /
• 2007

We consider a deformation method suitable for fractal. In IFS fractal, the position of a point is characterized by its code as well as by its coordinates. Code has a meaning of address for fractal. If we move a point by changing its code, the resulting movement shows fractal behavior. We propose three deformation methods based on code information. For the deformation vector of a point in fractal, 1) we use the vector of a given vector field at the point obtained by code transformation, 2) we use the vector constructed by adding predefined displacement vectors according to the code information of the point. Both methods show a fractal-like character as well as an ordinary continuous deformation character. Also, 3) we can deform fern-fractal more naturally by restricting its deforming region using code form.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제29권9C호
• /
• pp.1330-1336
• /
• 2004

This paper addresses an adaptive motion vector prediction algorithm to improve the performance of video encoder. The block-based motion vector is characterized by non-stationary local statistics so that the coefficients of LS (Least Squares) based linear motion can be optimized. However, it requires very expensive computational cost. The proposed algorithm using LS approach with spatially varying motion-directed property adaptively controls the coefficients of the motion predictor and reduces the computational cost as well as the motion prediction error. Experimental results show the capability of the proposed algorithm.

• Journal of the Institute of Convergence Signal Processing
• /
• 제3권1호
• /
• pp.41-47
• /
• 2002

Fractal image compression can reduce the size of image data by the contractive mapping that is affine transformation to find the block(called as range block) which is the most similar to the original image. Even though fractal image compression is regarded as an efficient way to reduce the data size, it has high distortion rate and requires long encoding time. In this paper, we presented a hybrid fractal image compression system with the modified SOFM Vector Quantizer which uses improved competitive learning method. The simulation results showed that the VQ hybrid fractal using improved competitive loaming SOFM has better distortion rate than the VQ hybrid fractal using normal SOFM.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제18권3호
• /
• pp.51-59
• /
• 2008

The biometrics has been researched as a means for authenticating user's identity. Among the biometrics schemes for face recognition, the eigenvector-based schemes, which use eigenvector made from training data for transforming test data to abstracted data, are widely adopted. From those schemes, however, it is hard to expect cancelable feature, which is a general concept for security in the biometrics. In this paper, we point out the security problem that is the recovery of valuable face information from the abstracted face data and consider a possible attack scenario by showing our experiment results.

• Journal of KIISE:Computing Practices and Letters
• /
• 제10권3호
• /
• pp.273-281
• /
• 2004

There is the temporal correlation of the video sequence between the motion vector of current block and the motion vector of previous block. In this paper, we propose the prediction search algorithm for block matching using the temporal correlation of the video sequence and the center-biased property of motion vectors. The proposed algorithm determines the location of a better starting point for the search of an exact motion vector using the point of the smallest SAD(sum of absolute difference) value by the predicted motion vector from the same block of the previous frame and the predictor candidate point on each search region. Simulation results show that PSNR(Peak-to-Signal Noise Ratio) values are improved up to the 1.06㏈ as depend on the video sequences and improved about 0.19∼0.46㏈ on an average except the full search(FS) algorithm.

• Journal of the Korea Computer Industry Society
• /
• 제9권4호
• /
• pp.149-156
• /
• 2008

There is the temporal correlation of a animation sequence between the motion vector of current block and the motion vector of previous block. In this paper, we propose the scene change detection algorithm for block matching using the temporal correlation of the animation sequence and the center-biased property of motion vectors. The proposed algorithm determines the location of a better starting point for the search of an exact motion vector using the point of the smallest SAD(sum of absolute difference) value by the predicted motion vector from the same block of the previous frame and the predictor candidate point on each search region. Simulation results show that the proposed algorithm has better detection performance, such as recall rate, then the existing method. The algorithm has the advantage of speed, simplicity and accuracy. In addition, it requires less amount of storage.

• Annual Conference of KIPS
• /
• 한국정보처리학회 2010년도 추계학술발표대회
• /
• pp.613-616
• /
• 2010

본 논문에서는 새로운 움직임 추정(motion estimation, ME) 방식을 사용한 프레임 비율 변환(frame rate conversion, FRC) 기법에 대해 제안한다. 기존의 프레임 비율 변환을 위한 움직임 추정 방식은 영상 압축에서 사용되고 있는 SAD를 사용하여 블록(block) 단위로 움직임 벡터를 추정하는 방식에 기초를 두고 있다. 그러나 잔여 신호(residual signal)를 저장하는 영상 압축과 달리, 잘못된 움직임 추정은 합성된 출력 영상에서 심각한 품질 저하를 가져올 수 있다. 이를 보완하기 위해 움직임 개선(motion refinement, MR)이 사용되고 있지만, 근본적인 해결을 위해서는 정확한 움직임 추정 알고리즘 사용이 필요하다. 특히 SAD를 통한 움직임 추정은 고르지 못한 움직임 벡터장(motion vector field, MVF)을 형성할 수 있으며, 종래의 연구에서 이를 해결하기 위해 SAD(sum of absolute difference)에 벡터의 공간제약(spatial constraint) 항목을 추가하여 비교적 고른 움직임 벡터장을 형성하는 방식이 제시되었다. SAD와 공간 제약 항목의 반영 비율에 따라 움직임 벡터의 중요성과 움직임 벡터장의 일관성이 서로 상충하는데, 기존의 방식은 이 비율을 일정한 상수(constant)값을 사용하고 있으며, 이러한 방식은 이미지의 특성에 따라 결과가 달라진다. 본 논문에서는 SAD와 공간 제약 항목 사이의 반영 비율을 이미지의 특성에 적응하는 방식을 사용하는 움직임 예측을 제시하고, 수행한 결과를 기존의 방식에 의한 결과와 비교하였다.