• 한국지능시스템학회논문지
• /
• 제14권6호
• /
• pp.783-788
• /
• 2004

영상에서 얼굴이 있는 위치를 찾거나 얼굴을 검출하기 위한 많은 방법들이 연구되고 있다. 영상에서 얼굴 검출은 얼굴의 크기, 얼굴이 있는 위치, 그리고 다양한 포즈, 조명 상태 등의 변화에 따라 달라진다 따라서 얼굴 검출과 인식에 있어서의 어려운 점은 얼굴의 크기와 위치, 거리, 조명, 포즈 때문에 나타나는 것이다. 본 논문에서는 다양한 얼굴 크기와 얼굴이 있는 위치 등에 강인한 얼굴 검출을 위해 피셔의 선형 판별 함수를 이용하는 방법을 제안한다. 선형 판별식을 이용하여 효과적으로 얼굴을 검출하기 위해서는 학습 방법 및 학습에 사용되는 데이터들의 구성이 중요하다. 그 이유는, 얼굴 검출을 위해 사용되는 학습 데이터들은 조명과 포즈에 영향을 받기 때문에 얼굴의 특징들을 반영하는 학습 데이터들의 구성이 중요하다. 따라서 본 논문에서는 복잡한 배경과 다양한 크기의 얼굴을 검출하기 위한 계층적인 방법을 제시하며, 효과적인 피셔 판별 분석을 위하여 얼굴과 비얼굴 학습 데이터의 효율적인 분류 방법을 제안한다.

• 한국축산식품학회지
• /
• 제29권1호
• /
• pp.132-139
• /
• 2009

본 연구에서는 1,300명의 소비자들이 직접 먹어보고 평가한 한우고기 데이터를 이용하여 쇠고기 맛 등급을 구분 해 내기 위한 판별분석 방법들을 비교하였다. 한우 관능평가의 주요 세 변수인 연도, 다즙성, 향미를 포함한 정준 판별분석과 대표적인 맛 변수로 여겨지는 전반적인 기호도 만을 이용하여 선형판별분석과 비모수 판별분석을 하였다. 전반적인 기호도와 같은 한 개의 변수만을 사용할 경우 두 가지 모두 비슷한 분류율을 나타내지만 선형판별 함수는 이해와 사용 측면에서 장점이 있었던 반면에 비모수적 방법은 커널함수와 띠폭에 대한 선택이 불편하지만 잘 선택하면 정확한 분류율을 높일 수 있는 장점이 있었다. 그러나 다른 정보를 가진 변수들이 있음에도 불구하고 한 개의 변수만을 이용한 판별 분석은 판별에 영향을 미치는 다른 중요한 변수들의 정보를 활용하지 못한다는 문제점이 있다. 한편, 정준판별분석의 경우 정준판별함수의 오분류율이 일변량 선형 판별함수와 비모수 판별함수의 오분류율에 비해 크게 떨어지지 않으면서 분포에 대한 특별한 가정이 필요하지 않아 통계적 가정이 까다롭지 않고 또한 맛에 중요한 요인인 연도, 다즙성, 향미의 세 개변수를 모두 사용하므로 맛 정보를 최대로 활용한다는 장점이 있었다. 따라서 본 연구결과 연도, 다즙성, 향미의 세가지 변수 정보를 모두 포함한 다변량 정준판별분석법을 이용하는 것이 맛 등급을 구분하는데 가장 적절할 것으로 판단되었다.

• Communications for Statistical Applications and Methods
• /
• 제4권1호
• /
• pp.49-63
• /
• 1997

We consider the problem of classifying a p x 1 observation into one of two multivariate normal populations when the training smaples contain a block of missing observation. A new classification procedure is proposed which is a linear combination of two discriminant functions, one based on the complete samples and the other on the incomplete samples. The new discriminant function is easy to use.

• 대한음성학회지:말소리
• /
• 제44호
• /
• pp.105-113
• /
• 2002

In Korean, each digit is monosyllable and some pairs are known to have high confusability, causing performance degradation of connected digit recognition systems. To improve the performance, in this paper, we employ various discriminant analyses (DA) including Linear DA (LDA), Weighted Pairwise Scatter LDA WPS-LDA), Heteroscedastic Discriminant Analysis (HDA), and Maximum Likelihood Linear Transformation (MLLT). We also examine several combinations of various DA for additional performance improvement. Experimental results show that applying any DA mentioned above improves the string accuracy, but the amount of improvement of each DA method varies according to the model complexity or number of mixtures per state. Especially, more than 20% of string error reduction is achieved by applying MLLT after WPS-LDA, compared with the baseline system, when class level of DA is defined as a tied state and 1 mixture per state is used.

• Journal of the Optical Society of Korea
• /
• 제12권2호
• /
• pp.88-92
• /
• 2008

This paper discusses a photon-counting linear discriminant analysis (LDA) with computational integral imaging (II). The computational II method reconstructs three-dimensional (3D) objects on the reconstruction planes located at arbitrary depth-levels. A maximum likelihood estimation (MLE) can be used to estimate the Poisson parameters of photon counts in the reconstruction space. The photon-counting LDA combined with the computational II method is developed in order to classify partially occluded objects with photon-limited images. Unknown targets are classified with the estimated Poisson parameters while reconstructed irradiance images are trained. It is shown that a low number of photons are sufficient to classify occluded objects with the proposed method.

• 말소리와 음성과학
• /
• 제9권2호
• /
• pp.85-94
• /
• 2017

Conventional speaker verification systems using time delay neural network, identity vector and probabilistic linear discriminant analysis (TDNN-Ivector-PLDA) are known to be very effective for verifying long-duration speech utterances. However, when test utterances are of short duration, duration mismatch between enrollment and test utterances significantly degrades the performance of TDNN-Ivector-PLDA systems. To compensate for the I-vector mismatch between long and short utterances, this paper proposes to use probabilistic linear discriminant analysis (PLDA) model adaptation with augmented data. A PLDA model is trained on vast amount of speech data, most of which have long duration. Then, the PLDA model is adapted with the I-vectors obtained from short-utterance data which are augmented by using vocal tract length perturbation (VTLP). In computer experiments using the NIST SRE 2008 database, the proposed method is shown to achieve significantly better performance than the conventional TDNN-Ivector-PLDA systems when there exists duration mismatch between enrollment and test utterances.

• 한국작물학회지
• /
• 제22권1호
• /
• pp.80-82
• /
• 1977

직선분리함수를 이용하여 소맥 Caribo monosomics 5A와 2D의 수형을 비교하므로써 직선분리함수의 농업에서의 이용성을 검토하였다. 직선분리함수를 계산하여 2가지 수형을 완전히 분리할 수 있었으며 그 결과는 전보 다변량동시분석법의 결과와 일치하였다. 직선분리함수의 의미의 확대해석으로 조사형질수를 감소시킬 수 있는 가능성을 검토 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권11호
• /
• pp.4502-4518
• /
• 2015

Fisher linear discriminant analysis (LDA) is one of the most popular projection techniques for feature extraction and has been widely applied in face recognition. However, it cannot be used when encountering the single sample per person problem (SSPP) because the intra-class variations cannot be evaluated. In this paper, we propose a novel method called local similarity based linear discriminant analysis (LS_LDA) to solve this problem. Motivated by the "divide-conquer" strategy, we first divide the face into local blocks, and classify each local block, and then integrate all the classification results to make final decision. To make LDA feasible for SSPP problem, we further divide each block into overlapped patches and assume that these patches are from the same class. To improve the robustness of LS_LDA to outliers, we further propose local similarity based median discriminant analysis (LS_MDA), which uses class median vector to estimate the class population mean in LDA modeling. Experimental results on three popular databases show that our methods not only generalize well SSPP problem but also have strong robustness to expression, illumination, occlusion and time variation.

• 전기학회논문지
• /
• 제63권4호
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• 한국근적외분광분석학회:학술대회논문집
• /
• 한국근적외분광분석학회 2001년도 NIR-2001
• /
• pp.1244-1244
• /
• 2001

In linear discriminant analysis there are two important properties concerning the effectiveness of discriminant function modeling. The first is the separability of the discriminant function for different classes. The separability reaches its optimum by maximizing the ratio of between-class to within-class variance. The second is the stability of the discriminant function against noises present in the measurement variables. One can optimize the stability by exploring the discriminant variates in a principal variation subspace, i. e., the directions that account for a majority of the total variation of the data. An unstable discriminant function will exhibit inflated variance in the prediction of future unclassified objects, exposed to a significantly increased risk of erroneous prediction. Therefore, an ideal discriminant function should not only separate different classes with a minimum misclassification rate for the training set, but also possess a good stability such that the prediction variance for unclassified objects can be as small as possible. In other words, an optimal classifier should find a balance between the separability and the stability. This is of special significance for multivariate spectroscopy-based classification where multicollinearity always leads to discriminant directions located in low-spread subspaces. A new regularized discriminant analysis technique, the principal discriminant variate (PDV) method, has been developed for handling effectively multicollinear data commonly encountered in multivariate spectroscopy-based classification. The motivation behind this method is to seek a sequence of discriminant directions that not only optimize the separability between different classes, but also account for a maximized variation present in the data. Three different formulations for the PDV methods are suggested, and an effective computing procedure is proposed for a PDV method. Near-infrared (NIR) spectra of blood plasma samples from mastitic and healthy cows have been used to evaluate the behavior of the PDV method in comparison with principal component analysis (PCA), discriminant partial least squares (DPLS), soft independent modeling of class analogies (SIMCA) and Fisher linear discriminant analysis (FLDA). Results obtained demonstrate that the PDV method exhibits improved stability in prediction without significant loss of separability. The NIR spectra of blood plasma samples from mastitic and healthy cows are clearly discriminated between by the PDV method. Moreover, the proposed method provides superior performance to PCA, DPLS, SIMCA and FLDA, indicating that PDV is a promising tool in discriminant analysis of spectra-characterized samples with only small compositional difference, thereby providing a useful means for spectroscopy-based clinic applications.