• 한국정보통신학회논문지
• /
• 제9권7호
• /
• pp.1513-1517
• /
• 2005

본 논문에서는 얼굴영역을 검출하기위해 얼굴 피부색을 보다 효과적으로 모델링하기 위한 피부색 특성을 고려하여 밝기 성분을 제거한 Red, Blue, Green 채널을 모두 사용하는 Hue, Cb, Cg의 M배i-Channel 피부색 모델을 사용한다. 얼굴영역을 분리한 영상에 Harr 웨이블릿을 이용한 에지영상 추출과 얼굴영역의 특징벡터를 구하기 위하여 26개의 특징벡터를 사용한 효율적인 고차 국소 자동 상관함수를 사용하였다. 계산된 특징벡터는 BP 신경망의 학습을 통하여 얼굴인식을 위한 데이터로 사용된다. 시뮬레이션을 통해 제안된 알고리즘에 의한 인식률향상과 속도 향상을 입증한다.

• 한국멀티미디어학회논문지
• /
• 제6권6호
• /
• pp.1008-1014
• /
• 2003

본 논문에서는 보다 강인하면서 화질의 열화를 최소화할 수 있는 워터 마크의 은닉을 위 해 9/7 쌍직교 웨이브릿 변환영역에서의 지각적 동조 (tuned)특성과 정상상태 일반화 가우시안 (stationary generalized Gaussian) 모델에서의 NVF (noise visibility function)를 적용하는 방법을 제안한다 이 방법은 웨이브릿 영역에서 각 부대역에 대한 문턱값을 결정한 다음 지각적 중요 계수를 찾은 후 이 지각적 중요계수에만 적응적인 삽입강도를 갖는 워터마크를 은닉한다. 워터마크는 3레벨로 분해된 웨이브릿 변환영역에서 영상의 인간시각 시스템에서 계산된 JND값과 통계적 다해상도 특성을 기반으로 정상상태 일반화 가우시안 모델에 따라 각 계수들의 값에 따라 은닉된다. 실험 결과 제안한 방법에서 WF를 이용함으로써 에지나 텍스쳐 영역에 더 강하게 삽입할 수 있고 각 부대역에 대한 지각특성을 이용할 수 있어 우수한 비가시성과 강인성을 확인하였다.

• 한국정보처리학회논문지
• /
• 제7권5호
• /
• pp.1361-1369
• /
• 2000

For the implementation of 3D Sound Localization system, the binaural filtering by HRTFs is generally employed. But the HRTF filter is of high order and its coefficients for all directions have to be stored, which imposes a rather large memory requirement. To cope with this, research works have centered on obtaining low dimensional HRTF representations without significant loss of information and synthesizing the original HRTF efficiently, by means of feature extraction methods for multivariate dat including PCA. In these researches, conventional linear PCA was applied to the frequency domain HRTF data and using relatively small number of principal components the original HRTFs could be synthesized in approximation. In this paper we applied neural network based nonlinear PCA model (NLPCA) and the nonlinear PLS repression model (NLPLS) for this low dimensional HRTF modeling and analyze the results in comparison with the PCA. The NLPCA that performs projection of data onto the nonlinear surfaces showed the capability of more efficient HRTF feature extraction than linear PCA and the NLPLS regression model that incorporates the direction information in feature extraction yielded more stable results in synthesizing general HRTFs not included in the model training.

• 대한의용생체공학회:의공학회지
• /
• 제15권4호
• /
• pp.465-474
• /
• 1994

This study is concerned with a method which helps human to generate EMG signals accurately and consistently to make reliable design samples of function discriminator for prosthetic arm control. We intend to ensure a signal accuracy and consistency by training human as a signal generation source. For the purposes, we construct a human training system using a digital computer, which generates visual graphes to compare real target motion trajectory with the desired one, to observe EMG signals and their features. To evaluate the effect which affects a feature variance and a feature separability between motion classes by the human training system, we select 4 features such as integral absolute value, zero crossing counts, AR coefficients and LPC cepstrum coefficients. We perform a experiment four times during 2 months. The experimental results show that the hu- man training system is effective for accurate and consistent EMG signal generation and reduction of a feature variance, but is not correlated for a feature separability, The cepstrum coefficient is the most preferable among the used features for reduction of variance, class separability and robustness to a time varing property of EMG signals.

• 한국자동차공학회논문집
• /
• 제16권6호
• /
• pp.134-140
• /
• 2008

Preceding vehicle detection is a crucial issue for driver assistance system as well as for autonomous vehicle guidance function and it has to be performed with high reliability to avoid any potential collision. The vision-based preceded vehicle detection systems are regarded promising for this purpose because they require little infrastructure on a highway. However, the feasibility of these systems in passenger car requires accurate and robust sensing performance. In this paper, an preceded vehicle detection system is developed using stereo vision sensors. This system utilizes feature matching, epipoplar constraint and feature aggregation in order to robustly detect the initial corresponding pairs. After the initial detection, the system executes the tracking algorithm for the preceded vehicles including a leading vehicle. Then, the position parameters of the preceded vehicles or leading vehicles can be obtained. The proposed preceded vehicle detection system is implemented on a passenger car and its performances is verified experimentally.

• 한국산업정보학회논문지
• /
• 제6권2호
• /
• pp.16-22
• /
• 2001

본 논문에서는 화상자료의 특성인 이웃 화소간의 종속성을 표현하는데 적합한 깁스분포를 바탕으로 특징벡터를 추출하여 변형된 글자를 인식하는 새로운 방법을 제안하였다. 추출된 특징벡터는 이미지의 크기, 위치, 회전에 대하여 불변한 특성을 갖는 2차원 조건부 모멘트로 구성된다. 변형된 글자 인식을 위한 알고리즘은 특징벡터 추출하는 과정과 패턴을 인식하는 과정으로 구성하였다. (i) 특징벡터는 하나의 이미지에 대하여 추정된 조건부 깁스분포를 바탕으로 2차원 조건부 모멘트를 계산하여 추출한다. (ii) 변형된 문자 인식은 제안된 판별거리함수를 계산하여 최소거리를 산출한 미지의 변형된 문자를 원형문자로 인식한다. 제안된 방법에 대한 성능평가를 위하여, 생성된 훈련 데이터를 만들어 Workstation에서 실험 한 결과 96%이상의 인식성능이 있음을 밝혔다.

• 한국산업정보학회논문지
• /
• 제4권2호
• /
• pp.1-6
• /
• 1999

화상 데이터의 특성을 표현하는데 적합한 깁스분포를 바탕으로 특징벡터를 추출하여 패턴을 분류하는 새로운 알고리즘을 제안하였다. 특징벡터는 화상의 크기, 위치, 회전에 대해서 불변이며 접영에 대해서도 덜 민감한 특징을 갖는 2차원 모멘트들의 원소로 만들어진다. 알고리즘은 공간정보를 갖는 2차원 모멘트를 이용하여 특징벡터를 추출하는 과정과 거리함수를 이용하여 패턴을 분류하는 과정으로 구축하였다. 특징벡터는 깁스분포의 묘수를 추정하여 2차원 조건부 모멘트를 추출하여 구성한다. 패턴 분류 과정은 추출된 특징벡터로부터 제안된 판별거리함수를 계산하여 여러 원형 패턴 가운데 최소거리를 산출한 미지의 패턴을 원형패턴으로 분류한다. 제안된 방법의 성능을 검증하기 위하여 대문자와 소문자 52자로 구성된 훈련 데이터를 만들어 SUN ULTRA 10 워크스테이션에서 실험을 한 결과 98%이상의 분류성능이 있음을 밝혔다.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2005년도 한국컴퓨터종합학술대회 논문집 Vol.32 No.1 (B)
• /
• pp.226-228
• /
• 2005

Predicting the cellular location of an unknown protein gives valuable information for inferring the possible function of the protein. For more accurate Prediction system, we need a good feature extraction method that transforms the raw sequence data into the numerical feature vector, minimizing information loss. In this paper we propose new methods of extracting underlying features only from the sequence data by computing pairwise sequence alignment scores. In addition, we use composition based features to improve prediction accuracy. To construct an SVM ensemble from separately trained SVM classifiers, we propose specificity based weighted majority voting . The overall prediction accuracy evaluated by the 5-fold cross-validation reached $88.53\%$ for the eukaryotic animal data set. By comparing the prediction accuracy of various feature extraction methods, we could get the biological insight on the location of targeting information. Our numerical experiments confirm that our new feature extraction methods are very useful forpredicting subcellular localization of proteins.

• ETRI Journal
• /
• 제41권3호
• /
• pp.358-370
• /
• 2019

The main aim of this study is to select the optimal set of genes from microarray cancer datasets that contribute to the prediction of specific cancer types. This study proposes the enhancement of the feature selection filter algorithm based on Joe's normalized mutual information and its use for gene selection. The proposed algorithm is implemented and evaluated on seven benchmark microarray cancer datasets, namely, central nervous system, leukemia (binary), leukemia (3 class), leukemia (4 class), lymphoma, mixed lineage leukemia, and small round blue cell tumor, using five well-known classifiers, including the naive Bayes, radial basis function network, instance-based classifier, decision-based table, and decision tree. An average increase in the prediction accuracy of 5.1% is observed on all seven datasets averaged over all five classifiers. The average reduction in training time is 2.86 seconds. The performance of the proposed method is also compared with those of three other popular mutual information-based feature selection filters, namely, information gain, gain ratio, and symmetric uncertainty. The results are impressive when all five classifiers are used on all the datasets.

• ETRI Journal
• /
• 제46권4호
• /
• pp.648-659
• /
• 2024

Author verification is challenging because of the diversity in writing styles. We propose an enhanced handwriting verification method that combines handcrafted and automatically extracted features. The method uses a genetic algorithm to reduce the dimensionality of the feature set. We consider offline Bangla handwriting content and evaluate the proposed method using handcrafted features with a simple logistic regression, radial basis function network, and sequential minimal optimization as well as automatically extracted features using a convolutional neural network. The handcrafted features outperform the automatically extracted ones, achieving an average verification accuracy of 94.54% for 100 writers. The handcrafted features include Radon transform, histogram of oriented gradients, local phase quantization, and local binary patterns from interwriter and intrawriter content. The genetic algorithm reduces the feature dimensionality and selects salient features using a support vector machine. The top five experimental results are obtained from the optimal feature set selected using a consensus strategy. Comparisons with other methods and features confirm the satisfactory results.