• Journal of Software Assessment and Valuation
• /
• v.16 no.2
• /
• pp.63-68
• /
• 2020

This paper proposes a face authentication system based on deep learning framework. The proposed system is consisted of face region detection and feature extraction using deep learning algorithm, and performed the face authentication using joint-bayesian matrix learning algorithm. The performance of proposed paper is evaluated by various face database , and the face image of one person consists of 2 images. The face authentication algorithm was performed by measuring similarity by applying 2048 dimension characteristic and combined Bayesian algorithm through Deep Neural network and calculating the same error rate that failed face certification. The result of proposed paper shows that the proposed system using deep learning and joint bayesian algorithms showed the equal error rate of 1.2%, and have a good performance compared to previous approach.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.2
• /
• pp.78-87
• /
• 2006

In this paper. we propose an effective mask estimation scheme for missing-feature reconstruction in order to achieve robust speech recognition under unknown noise environments. In the previous work. colored noise is used for training the mask classifer, which is generated from the entire frequency Partitioned signals. However it gives a limited performance under the restricted number of training database. To reflect the spectral events of more various background noise and improve the performance simultaneously. a new Bayesian classifier for mask estimation is proposed, which works independent of other frequency bands. In the proposed method, we employ the colored noise which is obtained by combining colored noises generated from each frequency band in order to reflect more various noise environments and mitigate the 'sparse' database problem. Combined with the cluster-based missing-feature reconstruction. the performance of the proposed method is evaluated on a task of noisy speech recognition. The results show that the proposed method has improved performance compared to the Previous method under white noise. car noise and background music conditions.

• Journal of the Korea Convergence Society
• /
• v.9 no.4
• /
• pp.47-55
• /
• 2018

In this paper, we propose a novel face recognition(FR) method that takes advantage of combining weighted deep local features extracted from multiple Deep Convolutional Neural Networks(DCNNs) learned with a set of facial local regions. In the proposed method, the so-called weighed deep local features are generated from multiple DCNNs each trained with a particular face local region and the corresponding weight represents the importance of local region in terms of improving FR performance. Our weighted deep local features are applied to Joint Bayesian metric learning in conjunction with Nearest Neighbor(NN) Classifier for the purpose of FR. Systematic and comparative experiments show that our proposed method is robust to variations in pose, illumination, and expression. Also, experimental results demonstrate that our method is feasible for improving face recognition performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.9
• /
• pp.1674-1680
• /
• 2017

In this paper, an embedded system for face authentication, which exploits high-dimensional local binary pattern (LBP) descriptor and joint Bayesian algorithm, is proposed. We also present a feasible embedded system for the proposed algorithm implemented with a Raspberry Pi 3 model B. Computer simulation for performance evaluation of the presented face authentication algorithm is carried out using a face database of 500 persons. The face data of a person consist of 2 images, one for training and the other for test. As performance measures, we exploit score distribution and face authentication time with respect to the dimensions of principal component analysis (PCA). As a result, it is confirmed that an embedded system having a good face authentication performance can be implemented with a relatively low cost under an optimized embedded environment.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.705-705
• /
• 2012

우리나라는 최근 여름철 태풍 및 집중호우로 인해 많은 토석류 및 산사태가 발생하고 있다. 작년 7월에도 집중호우로 인해 서울시 우면산 일대와 강원도 춘천에 많은 인적 물적 피해를 입었다. 해마다 반복되는 토석류나 산사태의 위험을 감소시키기 위해서는 보다 정확한 위험지역 예측모델을 필요로 한다. 본 연구는 토석류 및 산사태의 위험과 취약지역을 예측하기 위하여 GIS기반의 Weight of Evidence 기법을 적용하여 위험지역을 분석 하고자 한다. 2006년 태풍 에위니아에 의해 많은 토석류 피해를 입은 강원도 인제군 가리산일대를 대상으로 하였으며 토석류 및 산사태 위치 자료는 2005년, 2006년 토석류 발생 전후 항공사진의 중첩분석을 토대로 발생 지역을 추출하였다. 토석류 및 산사태발생에 영향을 미치는 지형, 지질, 토양, 수문, 임상 등의 인자들은 GIS를 이용하여 DB로 구축하였다. 베이시안 확률기법(Bayesian Method)에 기반 하여 구축된 DB와 결합하여 각각의 인자의 가중 값 W+, W-를 계산하여 상관관계를 분석하고 Weight of Evidence 기법을 적용하여 위험지역을 정량적으로 평가하고자 한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.04c
• /
• pp.359-361
• /
• 2003

정확한 암의 분류는 암의 진단 및 치료에 있어 매우 중요하지만, 암을 진단하기 위한 기존의 여러 방법들은 종종 불완전한 결과를 도출한다. 최근의 마이크로어레이 기술에 기반한 분자 수준의 진단은 정확하고 객관적이며 체계적인 암의 분류를 위한 방법론을 제시해준다. 유전자 발현 데이터는 일반적으로 수천개 이상의 유전자를 포함하는데, 유전자 발현 데이터의 모든 유전자가 암과 관련이 있는 것이 아니므로 정확한 암을 분류하기 위하여 중요한 유전자만을 추출하는 것이 바람직하다. 본 논문에서 음의 상관관계를 갖는 두 개의 이상적인 유전자 벡터를 정의한 후 이와 유사한 정도를 기준으로 중요한 유전자 집단을 추출하고, 각각을 신경망으로 학습하여 결합하는 신경망 쌍을 제안한다. 실험 결과는 음의 상관관계를 갖는 두 개의 유전자 집단이 암의 클래스를 잘 구분할 수 있음을 보여주었다. 이 유전자 집단을 특징으로 하여 각각 학습한 신경망을 베이시안 방법으로 결합한 결과, 벤치마크 데이터에 대하여 신경망 쌍이 개별 분류기에 비해 우수한 성능을 보임을 확인하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.265-267
• /
• 2002

본 논문에서는 적응적 정규화 자연기울기 학습법과 자연 프루닝(pruning) 방법의 결합을 통하여 일반화 성능이 우수만 신경망을 구성하고자 한다. 먼저 적응적 정규화 자연기울기 학습을 통하여 신경망의 가중치를 최적화 시키고, 자연 프루닝에 의하여 신경망의 구조를 단순화 시킨다. 이러한 모델들 중 최적의 모델은 베이시안 정보 기준에 의해 선택함으로써 일반화 성능이 우수만 신경망을 구성하는 방법을 제안한다 벤치마크 (benchmark) 데이터로 제안하는 방법과 유클리디안(Euclidean) 거리에 기반한 결합 방법과 자연 프루닝만을 적용한 방법을 비교함으로써 우수성을 검증한다.

• Journal of Korea Multimedia Society
• /
• v.6 no.1
• /
• pp.136-147
• /
• 2003

To achieve an optimal performance for a given problem, we need an integrative process of the parameter optimization via learning and the structure optimization via model selection. In this paper, we propose an efficient optimization method for improving generalization performance by considering the property of each sub-method and by combining them with common theoretical properties. First, weight parameters are optimized by natural gradient teaming with adaptive regularization, which uses a diverse error function. Second, the network structure is optimized by eliminating unnecessary parameters with natural pruning. Through iterating these processes, candidate models are constructed and evaluated based on the Bayesian Information Criterion so that an optimal one is finally selected. Through computational experiments on benchmark problems, we confirm the weight parameter and structure optimization performance of the proposed method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.14 no.5
• /
• pp.477-481
• /
• 2008

Place recognition is necessary for a mobile user to be provided with place-dependent information. This paper proposes real-time video based place recognition system that identifies users' current place while moving in the building. As for the feature extraction of a scene, there have been existing methods based on global feature analysis that has drawback of sensitive-ness for the case of partial occlusion and noises. There have also been local feature based methods that usually attempted object recognition which seemed hard to be applied in real-time system because of high computational cost. On the other hand, researches using statistical methods such as HMM(hidden Markov models) or bayesian networks have been used to derive place recognition result from the feature data. The former is, however, not practical because it requires huge amounts of efforts to gather the training data while the latter usually depends on object recognition only. This paper proposes a combined approach of global and local feature analysis for feature extraction to complement both approaches' drawbacks. The proposed method is applied to a mobile information system and shows real-time performance with competitive recognition result.

• Journal of the Institute of Convergence Signal Processing
• /
• v.12 no.2
• /
• pp.113-118
• /
• 2011

In this paper, we develop a speaker gender classification technique using collaborative sensor fusion for use in a wireless sensor network. The distributed sensor nodes remove the unwanted input data using the BER(Band Energy Ration) based voice activity detection, process only the relevant data, and transmit the hard labeled decisions to the fusion center where a global decision fusion is carried out. This takes advantages of power consumption and network resource management. The Bayesian sensor fusion and the global weighting decision fusion methods are proposed to achieve the gender classification. As the number of the sensor nodes varies, the Bayesian sensor fusion yields the best classification accuracy using the optimal operating points of the ROC(Receiver Operating Characteristic) curves_ For the weights used in the global decision fusion, the BER and MCL(Mutual Confidence Level) are employed to effectively combined at the fusion center. The simulation results show that as the number of the sensor nodes increases, the classification accuracy was even more improved in the low SNR(Signal to Noise Ration) condition.