• 말소리와 음성과학
• /
• 제3권2호
• /
• pp.65-70
• /
• 2011

Recently, audio-visual speech recognition (AVSR) has been studied to cope with noise problems in speech recognition. In this paper we propose a novel method of deciding weighting factors for audio-visual information fusion. We adopt the particle swarm optimization (PSO) to weighting factor determination. The AVSR experiments show that PSO-based normalized confidence measures (NCM) improve the rejection performance of mis-recognized words by 33%.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권6호
• /
• pp.2709-2729
• /
• 2016

Representation based classification, kernel method and sparse representation have received much attention in the field of face recognition. In this paper, we proposed an improved kernel principal component analysis method based on sparse representation to improve the accuracy and robustness for face recognition. First, the distances between the test sample and all training samples in kernel space are estimated based on collaborative representation. Second, S training samples with the smallest distances are selected, and Kernel Principal Component Analysis (KPCA) is used to extract the features that are exploited for classification. The proposed method implements the sparse representation under ℓ₂ regularization and performs feature extraction twice to improve the robustness. Also, we investigate the relationship between the accuracy and the sparseness coefficient, the relationship between the accuracy and the dimensionality respectively. The comparative experiments are conducted on the ORL, the GT and the UMIST face database. The experimental results show that the proposed method is more effective and robust than several state-of-the-art methods including Sparse Representation based Classification (SRC), Collaborative Representation based Classification (CRC), KCRC and Two Phase Test samples Sparse Representation (TPTSR).

• 한국음향학회지
• /
• 제19권5호
• /
• pp.9-12
• /
• 2000

음성 다이얼링 시스템은 화자의 음성을 인식하여 원하는 전화번호로 자동으로 전화를 걸어주는 시스템으로 주로 이동 전화나 휴대형 통신 장비에 유용하게 사용된다. 개인 음성 다이얼링 시스템의 경우, 다이얼링에 사용되는 모든 구문은 사용자가 선택하고 사용자의 음성을 사용하여 학습되어 음성 인식을 위한 HMM을 생성한다. 이러한 시스템은 화자독립 시스템 보다 매우 적은 메모리 공간과 계산량으로 구현이 가능하다. 그러나 이러한 시스템은 학습시 각 단어당 2-3개의 음성만을 사용하므로 음성인식 시스템의 성능을 개선하기 위한 각 상태에서의 상태지속분포을 추정하기는 매우 어렵다. 따라서 본 논문에서는 성능개선을 위한 후처리기를 제안하였다. 전화선을 통하여 구성된 데이터베이스를 이용한 실험에서 제안된 후처리기가 인식 시스템의 성능을 향상시킴을 확인하였다.

• 한국정보통신학회논문지
• /
• 제17권12호
• /
• pp.2793-2799
• /
• 2013

본 논문에서는 시간에 따라 변하는 잡음 환경에 강인한 음성 인식을 위해 효과적인 특징 보상 기법을 제안한다. 제안하는 기법에서는 기존의 Variational 모델 생성 기법의 모델 정확도를 향상시키고자 PCA를 도입한다. 제안된 기법은 다중 모델을 사용하는 PCGMM 기반의 특징 보상에 적용된다. 실험 결과는 제안한 PCA 기반의 Variational 모델 생성 기법이 배경 음악 환경의 다양한 SNR 조건에서 기존의 전처리 기법에 비하여 음성 인식 성능을 향상 시키는데 우수함을 입증한다. 제안한 모델 생성 기법이 기존의 Variational 모델 생성 방법에 비해 배경 음악 환경에서 평균 12.14%의 상대적 인식 성능 향상률을 나타낸다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권2호
• /
• pp.771-789
• /
• 2019

Text detection has been a popular research topic in the field of computer vision. It is difficult for prevalent text detection algorithms to avoid the dependence on datasets. To overcome this problem, we proposed a novel unsupervised text detection algorithm inspired by bootstrap learning. Firstly, the text candidate in a novel form of superpixel is proposed to improve the text recall rate by image segmentation. Secondly, we propose a unique text sample selection model (TSSM) to extract text samples from the current image and eliminate database dependency. Specifically, to improve the precision of samples, we combine maximally stable extremal regions (MSERs) and the saliency map to generate sample reference maps with a double threshold scheme. Finally, a multiple kernel boosting method is developed to generate a strong text classifier by combining multiple single kernel SVMs based on the samples selected from TSSM. Experimental results on standard datasets demonstrate that our text detection method is robust to complex backgrounds and multilingual text and shows stable performance on different standard datasets.

• 융합신호처리학회논문지
• /
• 제2권3호
• /
• pp.24-31
• /
• 2001

K-L 전개 방법은 특징의 차원을 효과적으로 압축하므로 인식 처리에서 계산량을 줄일 수 있는 방법으로 잘 알려져 있다. 본 논문에서는 한국어 인식 시스템의 인식 정도를 개선하기 위해, 음성의 특징 파라미터에 대하여 효과적으로 K-L전개를 적용하는 방법(K-L 계수)을 제안한다. 그리고 제안한 방법으로 얻어진 새로운 음성 특징 파라미터를 이용하여 화자 독립 연속 숫자음 인식실험을 수행하고, 기존의 Mel-cepstrum과 회귀계수의 인식 결과와 비 교, 분석하였다. 인식 실험 결과, 제안한 K-L 계수를 이용한 방법이 기존의 방법보다 높은 인식률을 얻어 제안한 방법의 유효성을 확인할 수 있었다.

• Journal of information and communication convergence engineering
• /
• 제14권1호
• /
• pp.51-56
• /
• 2016

In this paper, we present a three-dimensional (3-D) automatic target recognition system based on optical integral imaging reconstruction. In integral imaging, elemental images of the reference and target 3-D objects are obtained through a lenslet array or a camera array. Then, reconstructed 3-D images at various reconstruction depths can be optically generated on the output plane by back-projecting these elemental images onto a display panel. 3-D automatic target recognition can be implemented using computational integral imaging reconstruction and digital nonlinear correlation filters. However, these methods require non-trivial computation time for reconstruction and recognition. Instead, we implement 3-D automatic target recognition using optical cross-correlation between the reconstructed 3-D reference and target images at the same reconstruction depth. Our method depends on an all-optical structure to realize a real-time 3-D automatic target recognition system. In addition, we use a nonlinear correlation filter to improve recognition performance. To prove our proposed method, we carry out the optical experiments and report recognition results.

• 한국치위생학회지
• /
• 제12권5호
• /
• pp.1007-1015
• /
• 2012

Objectives : The purpose of this study was to survey Korean solders' oral healthcare recognition and perceived oral health concern. Methods : The data was collected from a questionnaire given 157 soldiers in Chungcheongnamdo. The data was analyzed into t-test, one-way ANOVA and Pearson's correlation analysis. Results : 25.5% replied that they were concerned about oral health. Soldiers who have received oral healthcare education exhibited higher recognition on the prevention of dental caries and periodontal disease. Moreover, those who have used oral hygiene devices also showed higher recognition on the prevention of dental caries and periodontal disease. The recognition of preventive effects on dental caries, in particular, showed a statistically significant difference (p<0.05). In regard to the relationship between oral health concern and recognition of oral healthcare, those who were more concerned about oral health were higher recognition of periodontal disease prevention(r=0.254, p<0.01). Conclusions : To improve concern and recognition of oral health for the members, the soldiers needs to develop oral health education and policy.

• 한국통신학회논문지
• /
• 제17권11호
• /
• pp.1199-1205
• /
• 1992

본 논문에서는 HMM(Hidden Markov Models)에서 문제점이 되는 개인차에의한 변동을 흡수하고, 적은 학습 데이타로서 인식률을 향상시키기 위하여 신경회로망을 이용한 NN-HMM(Neural Network Hidden Makov Models)에 의해 한국어 인식에 관하여 연구하였다. 이 방법은 HMM과 신경회로망의 출력을 각각 독립적인 인식값으로 가정하여 두 시스템의 확률곱으로 서로 보정되어 최대 인식확률의 음성모델을 인식하는 음성인식 시스템이다. 본 방법의 타당성을 평가하기 위하여 남, 여화자가 28개의 DDD 지역명을 발성한 음성데이타로 실험한 결과, 이산분포 HMM에 의한 방법에서는 91[%], 신경회로망에 의한 방법에서는 89[%], 제안된 방법에서는 95[%]의 향상된 인식률을 얻으므로써 인식성능의 우수함을 확인하였다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.458-464
• /
• 2022

Hazard recognition is considered as one of the pre-requisites for effective hazard management and injury prevention. However, in complex and changing environments, construction workers are often unable to identify all possible hazards that can occur in the jobsite. Therefore, identification of factors that impact hazard recognition in the work environment is necessary to reduce safety incidents as well as to develop strategies that can improve worker's hazard recognition performance. This study identified factors/problems that impact worker's hazard recognition abilities and suggested some potential technologies that can mitigate such problems. Literature reviews of journal articles and published reports related to hazard recognition studies were conducted to identify the factors. The study found out that the major factor responsible for affecting worker's hazard recognition abilities were human-related. Industry factors, Organizational factors and Physical factors of the site were the other factors identified from the study that impact worker's hazard recognition performances. The findings from the study can help site personnel recognize areas where effective measures can be directed towards worksite safety of workers while working in complex construction environments.