• 한국음향학회지
• /
• 제31권2호
• /
• pp.87-92
• /
• 2012

In this paper, a robust feature compensation method to deal with the environmental mismatch is proposed. The proposed method applies energy based weights according to the degree of speech presence to the Mean subtraction, Variance normalization, and ARMA filtering (MVA) processing. The weights are further smoothed by the moving average and maximum filters. The proposed feature compensation algorithm is evaluated on AURORA 2 task and distant talking experiment using the robot platform, and we obtain error rate reduction of 14.4 % and 44.9 % by using the proposed algorithm comparing with MVA processing on AURORA 2 task and distant talking experiment, respectively.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.869-872
• /
• 2000

Although many content-based image retrieval systems using shape feature have tried to cover rotation-, position- and scale-invariance between images, there have been problems to cover three kinds of variance at the same time. In this paper, we introduce new approach to extract shape feature from image using MBR(Minimum Bounding Rectangle). The proposed method scans image for extracting MBR information and, based on MBR information, compute contour information that consists of 16 points. The extracted information is converted to specific values by normalization and rotation. The proposed method can cover three kinds of invariance at the same time. We implemented our method and carried out experiments. We constructed R*_tree indexing structure, perform k-nearest neighbor search from query image, and demonstrate the capability and usefulness of our method.

• International journal of advanced smart convergence
• /
• 제7권4호
• /
• pp.40-49
• /
• 2018

We propose a more stable robust recognition algorithm which detects faces reliably even in cases where there are changes in lighting and angle of view, as well it satisfies efficiency in calculation and detection performance. We propose detects the face area alone after normalization through pre-processing and obtains a feature vector using (PCA). The feature vector is applied to LDA and using Euclidean distance of intra-class variance and inter class variance in the 2nd dimension, the final analysis and matching is performed. Experimental results show that the proposed method has a wider distribution when the input image is rotated $45^{\circ}$ left / right. We can improve the recognition rate by applying this feature value to a single algorithm and complex algorithm, and it is possible to recognize in real time because it does not require much calculation amount due to dimensional reduction.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.6028-6042
• /
• 2019

Since Sparse Nonnegative Matrix Factorization (SNMF) method can control the sparsity of the decomposed matrix, and then it can be adopted to control the sparsity of facial feature extraction and recognition. In order to improve the accuracy of SNMF method for facial feature recognition, new additive iterative rules based on the improved iterative step sizes are proposed to improve the SNMF method, and then the traditional multiplicative iterative rules of SNMF are transformed to additive iterative rules. Meanwhile, to further increase the sparsity of the basis matrix decomposed by the improved SNMF method, a threshold-sparse constraint is adopted to make the basis matrix to a zero-one matrix, which can further improve the accuracy of facial feature recognition. The improved SNMF method based on the additive iterative rules and threshold-sparse constraint is abbreviated as ASNMF, which is adopted to recognize the ORL and CK+ facial datasets, and achieved recognition rate of 96% and 100%, respectively. Meanwhile, from the results of the contrast experiments, it can be found that the recognition rate achieved by the ASNMF method is obviously higher than the basic NMF, traditional SNMF, convex nonnegative matrix factorization (CNMF) and Deep NMF.

• 한국음향학회지
• /
• 제23권8호
• /
• pp.583-589
• /
• 2004

포만트 등의 음향학적인 정보를 이용하지 않는 연속음성인식 (CSR)을 위한 벡터 양자화기 기반의 화자 정규화 방법을 제안한다. 이 방법은 앞서 제안한 간단한 숫자음 인식기를 위한 화자정규화 방법을 개선한 것으로, 코드북의 크기를 증가시켜 가면서 벡터양자화기를 반복적으로 학습시킴으로써 정규화된 코드북을 구한 다음, 치를 이용하여 시험용화자의 워핑계수를 추정한다. 코드북 생성과 워핑계수 추정을 위해 모음 음소의 집합과 자음과 모음을 포함한 모든 음소의 집합 등 두 가지 음소집합을 이용i,겨 실험하였으며, 추정한 워핑계수에 상응하는 구간선형 워핑함수를 이용하여 인식기의 학습과 시험에 사용될 특징벡터를 워핑하였다. TIMIT 코퍼스와 HTK toolkit을 이용한 음소인식 실험을 수행하여 제안하는 방법의 성능을 조사한 결과, 포만트를 이용한 워핑 방법과 비슷한 성능을 가짐을 확인하였다.

• 한국정보통신학회논문지
• /
• 제10권11호
• /
• pp.2039-2044
• /
• 2006

생물정보는 사람의 능력을 넘어 섰으며 데이터 마이닝과 같은 인공지능기법이 필수적으로 요구된다. 한번에 수천 개의 유전자 발현 정보를 획득할 수 있는 DNA마이크로어레이 기술은 대량의 생물정보를 가진 대표적인 신기술로 질병의 진단 및 예측에 있어 새로운 분석방법들과 연계하여 많은 연구가 진행 중이다. 이러한 새로운 기술들을 이용하여 유전자의 메 커니즘을 규명하는 것은 질병의 치료 및 신약의 개발에 많은 도움을 줄 것으로 기대 된다. 본 논문에서는 마이크로어레이 실험에서 다양한 원인에 의해 발생하는 잡음(noise)을 줄이 거나 제거하는 과정인 표준화과정을 거쳐 표준화 방법들의 성능 비교를 위해 특징 추출방법 인 베이지안(Bayesian) 방법을 이용하여 마이크로어레이 데이터의 분류 정확도를 비교 평가하여 Lowess 표준화 후 95.89%로 분류성능을 향상시킬 수 있음을 보였다.

• 정보처리학회논문지B
• /
• 제11B권3호
• /
• pp.267-274
• /
• 2004

본 논문은 다중 비디오카메라에서 색 정보를 이용한 특정 이동물체 추적 이동물체 추적 알고리듬을 제안한다. 제안된 방법은 다중 비디오카메라로부터 입력되는 영상의 RGB 칼라 좌표계를 HSI 칼라 좌표계로 변환한 후, 영상의 색조 영역만을 가지고 배경영상과 물체가 존재하는 영상에서 차영상 기법과 가산투영 기법을 사용하여 이동물체를 검출한다. 검출된 이동물체 영역의 색조는 0도부터 360도 사이에서 24단계로 정규화 된다. 정규화된 이동물체의 색조 분포도를 구한 후, 가장 높은 분포를 갖는 3개의 정규화 레벨과 3개의 정규화 레벨 사이의 간격을 이동물체의 특징파라미터로 사용하였다. 각 카메라간의 이동물체 동일성 관별은 이동물체 특징파라미터를 가지고 판별하고, 추적 감시하였다. 제안된 방법의 타당성을 검토하기 위하여 실내에 각기 다른 장소에 4대의 카메라를 각각 설치하여 이동물체의 대상을 사람으로 놓고, 특정사람을 감시한 결과 각 카메라에서 검출된 특정사람의 색조분포도 변화는 10％내를 유지함을 보였고, 특징 파라미터로 4대의 카메라에서 특정사람이 자동 추적감시 됨을 확인하였다.

• Journal of the Optical Society of Korea
• /
• 제18권4호
• /
• pp.317-329
• /
• 2014

In vision measurement systems based on structured light, the key point of detection precision is to determine accurately the central position of the projected laser line in the image. The purpose of this research is to extract laser line centers based on a decision function generated to distinguish the real centers from candidate points with a high recognition rate. First, preprocessing of an image adopting a difference image method is conducted to realize image segmentation of the laser line. Second, the feature points in an integral pixel level are selected as the initiating light line centers by the eigenvalues of the Hessian matrix. Third, according to the light intensity distribution of a laser line obeying a Gaussian distribution in transverse section and a constant distribution in longitudinal section, a normalized model of Hessian matrix eigenvalues for the candidate centers of the laser line is presented to balance reasonably the two eigenvalues that indicate the variation tendencies of the second-order partial derivatives of the Gaussian function and constant function, respectively. The proposed model integrates a Gaussian recognition function and a sinusoidal recognition function. The Gaussian recognition function estimates the characteristic that one eigenvalue approaches zero, and enhances the sensitivity of the decision function to that characteristic, which corresponds to the longitudinal direction of the laser line. The sinusoidal recognition function evaluates the feature that the other eigenvalue is negative with a large absolute value, making the decision function more sensitive to that feature, which is related to the transverse direction of the laser line. In the proposed model the decision function is weighted for higher values to the real centers synthetically, considering the properties in the longitudinal and transverse directions of the laser line. Moreover, this method provides a decision value from 0 to 1 for arbitrary candidate centers, which yields a normalized measure for different laser lines in different images. The normalized results of pixels close to 1 are determined to be the real centers by progressive scanning of the image columns. Finally, the zero point of a second-order Taylor expansion in the eigenvector's direction is employed to refine further the extraction results of the central points at the subpixel level. The experimental results show that the method based on this normalization model accurately extracts the coordinates of laser line centers and obtains a higher recognition rate in two group experiments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.367-369
• /
• 2004

In this paper we propose an effective and reliable hand detection method using neural network with ICA(Independent Component Analysis) Features. Many algorithms of hand detection have been proposed yet. Among them, ICA is the one of the interesting topics in image processing. ICA can not only separate mixed signals but also efficiently extract low-dimensional features in signals. ICA features are able to represent the characteristic of the images well. The object of this paper is to use effectively ICA that has above advantage. That is, by the proper number of Independent component the arithmetic speed is faster and by normalization of ICA feature the performance of detection is more reliable. For this, we adopt the algorithm, the Proportion of variance, which select the ICA feature by comparing the ratio of variance of ICA feature. By this method, we can extract the feature that is good at classifying hand and non-hand. Our experimental results show that by using ICA features, we obtained a better performance in hand detection than by only training NN on the image. And we can use hand detection system effectively and reliably by our proposal.

• Journal of Multimedia Information System
• /
• 제2권1호
• /
• pp.171-178
• /
• 2015

This article describes 3 dimensional (3D) face recognition system using histogram of oriented gradients (HOG) based on face curvature. The surface curvatures in the face contain the most important personal feature information. In this paper, 3D face images are recognized by the face components: cheek, eyes, mouth, and nose. For the proposed approach, the first step uses the face curvatures which present the facial features for 3D face images, after normalization using the singular value decomposition (SVD). Fisherface method is then applied to each component curvature face. The reason for adapting the Fisherface method maintains the surface attribute for the face curvature, even though it can generate reduced image dimension. And histogram of oriented gradients (HOG) descriptor is one of the state-of-art methods which have been shown to significantly outperform the existing feature set for several objects detection and recognition. In the last step, the linear discriminant analysis is explained for each component. The experimental results showed that the proposed approach leads to higher detection accuracy rate than other methods.