• 지능정보연구
• /
• 제12권1호
• /
• pp.17-31
• /
• 2006

본 논문에서는 출입국자 관리의 효율성과 체계적인 출입국 관리를 위하여 여권 코드를 자동으로 인식하고 위조 여권을 판별할 수 있는 여권 인식 및 얼굴 인증 방법을 제안한다. 여권 이미지가 기울어진 상태로 스캔되어 획득되어질 경우에는 개별 코드 인식과 얼굴 인증에 많은 영향을 미칠 수도 있으므로 기울기 보정은 문자 분할 및 인식, 얼굴 인증에 있어 매우 중요하다. 따라서 본 논문에서는 여권 영상을 스미어링한 후, 추출된 문자열 중에서 가장 긴 문자열을 선택하고 이 문자열의 좌측과 우측 부분의 두께 중심을 연결하는 직선과 수평선과의 기울기를 이용하여 여권 영상에 대한 각도 보정을 수행한다. 여권 코드 추출은 소벨 연산자와 수평 스미어링, 8 방향 윤곽선 추적 알고리즘을 적용하여 여권 코드의 문자열 영역을 추출하고, 추출된 여권 코드 문자열 영역에 대해 반복 이진화 알고리즘을 적용하여 코드의 문자열 영역을 이진화한다. 이진화된 문자열 영역에 대해 CDM 마스크를 적용하여 문자열의 코드들을 복원하고 8 방향 윤곽선 추적 알고리즘을 적용하여 개별 코드를 추출한다. 추출된 개별 코드 인식은 개선된 RBF 네트워크를 제안하여 적용한다. 개선된 퍼지 ART 기반 RBF 네트워크는 퍼지 논리 접속 연산자를 이용하여 경계 변수를 동적으로 조정하는 퍼지 ART 알고리즘을 제안하여 RBF 네트워크의 중간층으로 적용한다. 얼굴 인증을 위해서는 얼굴 인증에 가장 보편적으로 사용되는 PCA 알고리즘을 적용한다. PCA 알고리즘은 고차원의 벡터를 저 차원의 벡터로 감량하여 전체 입력 영상들의 직교적인 공분산 행렬을 계산한 후, 그것의 고유 값에 따라 각 영상의 고유 벡터를 구한다. 따라서 본 논문에서는 PCA 알고리즘을 적용하여 얼굴의 고유 벡터를 구한 후, 특징 벡터를 추출한다. 그리고 여권 영상에서 획득되어진 얼굴 영상의 특징 벡터와 데이터베이스에 있는 얼굴 영상의 특징 벡터와의 거리 값을 계산하여 사진 위조 여부를 판별한다. 제안된 여권 인식 및 얼굴 인증 방법의 성능을 평가를 위하여 원본 여권에서 얼굴 부분을 위조한 여권과 기울어진 여권 영상을 대상으로 실험한 결과, 제안된 방법이 여권의 코드 인식 및 얼굴 인증에 있어서 우수한 성능이 있음을 확인하였다.

• 한국경영과학회지
• /
• 제6권1호
• /
• pp.65-70
• /
• 1981

L.G. Khachiyan's algorithm for solving a system of strict (or open) linear inequalities with integral coefficients is described. This algorithm is based on the construction of a sequence of ellipsoids in R$^n$ of decreasing n-dimensional volume and contain-ing feasible region. The running time of the algorithm is polynomial in the number of bits of computer core memory required to store the coefficients. It can be applied to solve linear programming problems in polynomially bounded time by the duality theorem of the linear programming problem. But it is difficult to use in solving practical problems. Because it requires the computation of a square roots, besides other arithmatic operations, it is impossible to do these computations exactly with absolute precision.

• 전자공학회논문지S
• /
• 제35S권1호
• /
• pp.68-79
• /
• 1998

In this paper, we propose a model-based FDI(fault detetion and isolation) algorithm to detect and isolate fault in a linear system. The proposed algorithm is gased on an HFC(hydrid fault classifier) which consists of an FCART2(fault classifier by ART2 neural network) and an FCFM(fault classifier by fault models) which operate in parallel to isolate faults. The proposed algorithm is functionally composed of three main parts-parameter estimation, fault detection, and isolation. When a change in the system occurs, the estimated parameters go through a transition zone in which errors between the system output and the stimated output and the estimated output cross a predetermined thrseshold, and in this zone the estimated parameters are tranferred to the FCART2 for fault isolation. On the other hand, once a fault in the system is detected, the FCFM statistically isolates the fault by using the error between ach fault model out put and the system output. From the computer simulation resutls, it is verified that the proposed model-based FDI algorithm can be performed successfully to detect and isolate faults in a position control system of a DC motor.

• Journal of Electrical Engineering and Technology
• /
• 제12권1호
• /
• pp.363-372
• /
• 2017

This paper presents a novel face recognition algorithm based on the deep convolution neural network and key point detection jointed local binary pattern methodology to enhance the accuracy of face recognition. We firstly propose the modified face key feature point location detection method to enhance the traditional localization algorithm to better pre-process the original face images. We put forward the grey information and the color information with combination of a composite model of local information. Then, we optimize the multi-layer network structure deep learning algorithm using the Fisher criterion as reference to adjust the network structure more accurately. Furthermore, we modify the local binary pattern texture description operator and combine it with the neural network to overcome drawbacks that deep neural network could not learn to face image and the local characteristics. Simulation results demonstrate that the proposed algorithm obtains stronger robustness and feasibility compared with the other state-of-the-art algorithms. The proposed algorithm also provides the novel paradigm for the application of deep learning in the field of face recognition which sets the milestone for further research.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권10호
• /
• pp.4976-4994
• /
• 2018

The diffusion-based salient object detection methods have shown excellent detection results and more efficient computation in recent years. However, the current diffusion-based salient object detection methods still have disadvantage of detecting the object appearing at the image boundaries and different scales. To address the above mentioned issues, this paper proposes a multi-scale diffusion-based salient object detection algorithm with background and objectness seeds. In specific, the image is firstly over-segmented at several scales. Secondly, the background and objectness saliency of each superpixel is then calculated and fused in each scale. Thirdly, manifold ranking method is chosen to propagate the Bayessian fusion of background and objectness saliency to the whole image. Finally, the pixel-level saliency map is constructed by weighted summation of saliency values under different scales. We evaluate our salient object detection algorithm with other 24 state-of-the-art methods on four public benchmark datasets, i.e., ASD, SED1, SED2 and SOD. The results show that the proposed method performs favorably against 24 state-of-the-art salient object detection approaches in term of popular measures of PR curve and F-measure. And the visual comparison results also show that our method highlights the salient objects more effectively.

• 한국운동역학회지
• /
• 제21권1호
• /
• pp.85-95
• /
• 2011

Three-dimensional(3D) motion analysis is a useful tool for analyzing sports performance. During the last few decades, advances in motion analysis equipment have enabled us to perform more and more complicated biomechanical analyses. Nevertheless, considering the complexity of biomechanical models and the amount of data recorded from the motion analysis system, subsequent processing of these data is required for event-specific motion analysis. The purpose of this study was to develop a basic golf swing analysis algorithm using a state-of-the-art VICON motion analysis system. The algorithm was developed to facilitate golf swing analysis, with special emphasis on 3D motion analysis and high-speed motion capture, which are not easily available from typical video camera systems. Furthermore, the developed algorithm generates golf swing-specific kinematic and kinetic variables that can easily be used by golfers and coaches who do not have advanced biomechanical knowledge. We provide a basic algorithm to convert massive and complicated VICON data to common golf swing-related variables. Future development is necessary for more practical and efficient golf swing analysis.

• 한국게임학회 논문지
• /
• 제17권1호
• /
• pp.7-16
• /
• 2017

3D 게임그래픽 표현기술은 게임콘텐츠발전과 함께 콘텐츠 분야에서 중요한 요소가 되었다. 특히 게임 캐릭터 표현 기술은 사실적인 그래픽 기술과 시각적인 즐거움을 주는 것 이외에 게임을 진행하는 게임에 대한 몰입도의 중간 단계역할을 하며 플레이어가 마치 게임 속에서 영웅적인 모험을 즐길 수 있도록 착각을 만들어 낸다. 3D 게임에 있어서 게임캐릭터의 높은 완성도는 개발과정 가운데 캐릭터 설정작업의 세심한 디테일작업과 신중함이 주요요인으로 작용한다[3]. 본 논문에서는 게임구현을 위하여 인지적 AI 알고리즘이 적용된 3D 유니티 게임 엔진을 사용하여 radiosity의 수학적인 모델과 기본적인 radiosity 모델, 점진적 개선 radiosity 모델 기법을 방법론을 소개하고, 모바일 게임에 적용한 캐릭터 표현기법을 제안하려고 한다. 게임엔진에 실제적으로 적용하여보니 렌더링과정과 모의실험에서 표면의 투영도는 게임콘텐츠 환경의 조명도에 따라 변화됨을 발견 할 수 있어서, 전체적으로 질 높은 게임캐릭터가 완성되었음이 확인 되었다.

• ETRI Journal
• /
• 제35권3호
• /
• pp.542-545
• /
• 2013

State-of-the-art voice codecs have been developed to extend the input bandwidth to enhance quality while maintaining interoperability with a legacy codec. Most of them employ a modified discrete cosine transform (MDCT) for coding their extended band. We propose a source filter model-based coding algorithm of MDCT spectral coefficients, apply it to the ITU-T G.711.1 super wideband (SWB) extension codec, and subjectively test it to validate the model. A subjective test shows a better quality over the standardized SWB codec.

• 한국정보통신학회:학술대회논문집
• /
• 한국해양정보통신학회 2004년도 SMICS 2004 International Symposium on Maritime and Communication Sciences
• /
• pp.1-5
• /
• 2004

In this paper, we propose a novel approach for evolving the architecture of a multi-layer neural network. Our method uses combined ART1 algorithm and Max-Min neural network to self-generate nodes in the hidden layer. We have applied the. proposed method to the problem of recognizing ID number in student identity cards. Experimental results with a real database show that the proposed method has better performance than a conventional neural network.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 II
• /
• pp.823-826
• /
• 2003

FPGA-based logic emulator with lane gate capacity generally comprises a large number of FPGAs connected in mesh or crossbar topology. However, gate utilization of FPGAs and speed of emulation are limited by the number of signal pins among FPGAs and the interconnection architecture of the logic emulator. The time-multiplexing of interconnection wires is required for multi-FPGA system incorporating several state-of-the-art FPGAs. This paper proposes a circuit partitioning algorithm called SCATOMi(SCheduling driven Algorithm for TOMi)for multi-FPGA system incorporating four to eight FPGAs where FPGAs are interconnected through TOMi(Time-multiplexed, Off-chip, Multicasting interconnection). SCATOMi improves the performance of TOMi architecture by limiting the number of inter-FPGA signal transfers on the critical path and considering the scheduling of inter-FPGA signal transfers. The performance of the partitioning result of SCATOMi is 5.5 times faster than traditional partitioning algorithms. Architecture comparison show that the pin count is reduced to 15.2%-81.3% while the critical path delay is reduced to 46.1%-67.6% compared to traditional architectures.