• Journal of Korea Society of Industrial Information Systems
• /
• 제12권4호
• /
• pp.164-168
• /
• 2007

In this paper, we propose the eye detection algorithms which can apply to the Real-Time Embedded systems. To detect the eye region, the feature vectors are obtained at the first step and then, PCA(Principal Component Analysis) and amplitude projection method is applied to composite the feature vectors. In the decision state, the estimated probability density functions (PDFs) are applied by the proposed Bayesian method to detect eye region in an image from the CCD camera. The simulation results show that our proposed method has a good detection rate on the frontal face and this can be applied to the embedded system because of its small amount of the mathematical complexity.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 한국통신학회 1996년도 추계종합학술발표회 논문집
• /
• pp.706-709
• /
• 1996

• Journal of Korea Society of Industrial Information Systems
• /
• 제5권2호
• /
• pp.16-21
• /
• 2000

Vector quantization(VQ) is widely used in many high-quality and high-rate data compression applications such as speech coding, audio coding, image coding and video coding. When the size of a VQ codebook is large, the computational complexity for the full codeword search method is a significant problem for many applications. A number of complexity reduction algorithms have been proposed and investigated using such properties of the codebook as the triangle inequality. This paper proposes a new fast VQ search algorithm that is based on a multi-stage structure for searching for the best codeword. Even using only two stages, a significant complexity reduction can be obtained without any loss of quality.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제40권4호
• /
• pp.286-291
• /
• 2003

In this Paper, we designed an LSP(Line Spectral Pairs) parameter quantizer with cascaded structure of vector quantizer and scalar quantizer for the wideband speech coder. We have chosen the 16th-order of the LP coefficients. These coefficients are then transformed into the LSP parameters which have the excellent properties for quantization and easy stability checking condition of synthesis filter. In the first stage of quantization, input LSP parameters are split-vector-quantized using two 8-th order codebooks. In the second stage, the components of residual vector are individually quantized by the scalar quantizer utilizing the ordering property of LSP parameters. The designed adaptive VQ-SQ quantizer using 35 bits/frame shows the wideband transparency that the average spectral distortion should be less than 1.6 ㏈ and less than 4% of the frames should have SD above 3 ㏈. The simulation results show that the designed quantizer provides a 2-3 bits/frame saving over the typical vector-scalar quantizer.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제40권4호
• /
• pp.237-247
• /
• 2003

The Motion Estimation (ME) process is an important part of a video encoding systems since they can significantly reduce bitrate with keeping the output quality of an encoded sequence. Unfortunately this process may dominate the encoding time using straightforward full search algorithm (FS). Up to now, many fast algorithms can reduce the computation complexity by limiting the number of searching locations. This is accomplished at the expense of less accuracy of motion estimation. In this paper, we introduce a new fast motion estimation method based on the spatio-temporal correlation of adjacent blocks. A reliable predicted motion vector (RPMV) is defined. The reliability of RPMV is shown on the basis of motion vectors achieved by FS. The scalar and the direction of RPMV are used in our proposed scheme. The experimental results show that the proposed method Is about l1~14% faster than the nearest neighbor method which is a wellknown conventional fast scheme.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• 제15권6호
• /
• pp.579-589
• /
• 2004

The radar signals are generally very sensitive to relative orientations between radar and target. Thus, the performance of a target recognition system significantly deteriorates as the region of aspect angles becomes broader. To address this difficulty, in this paper, we propose a method based on the multi-aspect information in order to improve the classification capability ever for a wide angular region. First, range profiles are used to extract feature vectors based on the central moments and principal component analysis(PCA). Then, a classifier with the use of multi-aspect information is applied to them, yielding an additional improvement of target recognition capability. There are two different strategies among the classifiers that can fuse the information from multi-aspect radar signals: independent methodology and dependent methodology. In this study, the performances of the two strategies are compared within the frame work of target recognition. The radar cross section(RCS) data of six aircraft models measured at compact range of Pohang University of Science and Technology are used to demonstrate and compare the performances of the two strategies.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 한국퍼지및지능시스템학회 2000년도 추계학술대회 학술발표 논문집
• /
• pp.133-136
• /
• 2000

우리는 인터넷을 통한 사용자의 선호도(preference)를 분석하고 협력적 여과 기술을 학습하여 유머문서를 추천하는 MrHumor 시스템을 구축하였다. MrHumor에서는 사용자집합이 유머문서 집합에 대하여 보여준 등급매김값을 토대로 사용집합의 백터공간(vector space)를 설정하고 노이즈에 강하면서 효율적인 학습을 위해 선형 PCA를 이용하여 축소된 2차원 공간상에서 유머문서의 통계적 특성을 반영하여 적응형 k-NN으로 지엽성을 적적히 조절하여 새로운 문서에 대한 선호도를 추정하게 된다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 한국방송∙미디어공학회 2019년도 하계학술대회
• /
• pp.158-159
• /
• 2019

본 논문에서는 심층 신경망을 기반으로 하는 감정 인식을 위해 스파이크 특성을 추출하는 기술을 제안한다. 기존의 심층 신경망을 이용한 감정 인식 기술은 대부분 MFCC를 특성 백터를 사용한다. 그러나 프레임 단위의 연산인 MFCC는 높은 시간 해상도를 확보하기 어려워 시간적 특성의 영향을 받는 감정 인식에 한계가 있다. 이를 해결하기 위해 본 논문에서는 인간의 청각 필터를 모델링한 ERB에 따라 샘플 단위로 주파수의 특성을 나타내는 스파이크그램을 이용한 감정 인식 기술을 제안한다. 제안하는 방법이 감정 인식의 대표적 특성인 MFCC보다 높은 인식률을 제공하는 것을 확인하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• 제40권4호
• /
• pp.256-265
• /
• 2003

To improve reliability and practicality, a fingerprint-based biometric system needs to be robust to rotations of an input fingerprint and the processing speed should be fast. Accordingly, this paper presents a new filterbank-based fingerprint feature extraction and matching method that is robust to diverse rotations and reasonably fast. The proposed method fast extracts fingerprint features using a directional filter bank, which effectively decomposes an image into several subband outputs Since matching is also performed rapidly based on the Euclidean distance between the corresponding feature vectors, the overall processing speed is so fast. To make the system robust to rotations, the proposed method generates a set of feature vectors considering various rotations of an input fingerprint and then matches these feature vectors with the enrolled single template feature vector. Experimental results demonstrated the high speed of the proposed method in feature extraction and matching, along with a comparable verification accuracy to that of other leading techniques.

• Proceedings of the Optical Society of Korea Conference
• /
• 한국광학회 1995년도 광학 및 양자전자학 워크샵 논문집
• /
• pp.195-200
• /
• 1995

화상표시자의 기본특성은 밝기와 명암대비이다. 액정표시자에서는 이러한 특정들을 결정하는 요소들이 많고, 이들 사이의 관계가 복잡하여 최적고건을 최적조건을 찾기 어렵다. 이 논문에서는 빛의 편광상태와 광학소자의 편광투과특성을 각각 뽀앙카레공에서의 백터와 기하학적변환으로 나타내어, 이를 바탕으로 화상의 특성을 나타내는 양을 정의하고, 이들을 최적화하는 설계방법을 설명하며, 이 방법을 실험적으로 확인한다.