• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.435-438
• /
• 2008

본 논문에서는 애니메이션을 위해서 얼굴의 특징표현(Action Units)의 조합하는 방법으로 얼굴 모델링을 하기 위한 3D대응점(3D dense correspondence)을 찾는 방법을 제시한다. AUs는 표정, 감정, 발음을 나타내는 얼굴의 특징표현으로 통계적 방법인 PCA (Principle Component Analysis)를 이용하여 만들 수 있다. 이를 위해서는 우선 3D 모델상의 대응점을 찾는 것이 필수이다. 2D에서 얼굴의 주요 특징 점은 다양한 알고리즘을 이용하여 찾을 수 있지만 그것만으로 3D상의 얼굴 모델을 표현하기에는 적합하지 않다. 본 논문에서는 3D 얼굴 모델의 대응점을 찾기 위해 원기둥 좌표계 (Cylinderical Coordinates System)을 이용하여 3D 모델을 2D로 투사(Projection)시켜서 만든 2D 이미지간의 워핑(Warping) 을 통한 대응점을 찾아 역으로 3D 모델간의 대응점을 찾는다. 이것은 3D 모델 자체를 변환하는 것보다 적은 연산량으로 계산할 수 있고 본래 형상의 변형이 없다는 장점을 가지고 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2019.05a
• /
• pp.556-558
• /
• 2019

기존 초음파 지방간 분석은 Hepatorenal sonographic index(HI)를 사용하여 지방간을 진단하여 왔다. 이러한 HI 기법에서는 Hepato(간)과 Renal(신장), 두 부분의 영상데이터를 비교 활용하였다면, 본 논문에서는 신장의 영상데이터만을 이용하여, 이의 통계적 특징 벡터만을 활용하여 지방간을 진단을 함으로서 기존의 HI기반 분석대비 편리성과 정확도를 개선코자 Kidney Index(KI) 기반의 분석 기법을 제안한다. 본 논문에서 제안된 KI는 정상간과 지방간을 가진 실제 환자의 초음파 사진(정상간, 지방간 각 30명)을 학습 데이터를 구성하고, 이들 데이터군으로부터 특징 벡터들을 선별하여 머신러닝 기법 중 서포트 벡터 머신(Support Vector Machine)을 통해 학습시켜, 제안된 알고리즘의 유효성을 입증하였다.

• Journal of Broadcast Engineering
• /
• v.24 no.5
• /
• pp.791-801
• /
• 2019

The serial arc is one of factors causing electrical fires. Over past decades, various researches have been carried out to detect arc occurrences. Even though frequency analysis, wavelet and statistical features have been used, arc detection performance is degraded due to diverse arc waveforms. Therefore, there is a need to develop a method that could increase the feature dimension, thereby improving the detection performance. In this paper, we use variational mode decomposition (VMD) to obtain multiple decomposed signals and then extract statistical features from them. The features from VMD outperform those from no-VMD in terms of detection performance. Further, artificial neural network is employed as an arc classifier. Experiments validated that the use of VMD improves the classification accuracy by up to 4 percent, based on 14,000 training data.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.2
• /
• pp.180-186
• /
• 2004

The presence of noise in speech signals degrades the performance of recognition systems in which there are mismatches between the training and test environments. To make a speech recognizer robust, it is necessary to compensate these mismatches. In this paper, we studied about an improvement of stochastic feature extraction based on band-SNR for robust speech recognition. At first, we proposed a modified version of the multi-band spectral subtraction (MSS) method which adjusts the subtraction level of noise spectrum according to band-SNR. In the proposed method referred as M-MSS, a noise normalization factor was newly introduced to finely control the over-estimation factor depending on the band-SNR. Also, we modified the architecture of the stochastic feature extraction (SFE) method. We could get a better performance when the spectral subtraction was applied in the power spectrum domain than in the mel-scale domain. This method is denoted as M-SFE. Last, we applied the M-MSS method to the modified stochastic feature extraction structure, which is denoted as the MMSS-MSFE method. The proposed methods were evaluated on isolated word recognition under various noise environments. The average error rates of the M-MSS, M-SFE, and MMSS-MSFE methods over the ordinary spectral subtraction (SS) method were reduced by 18.6%, 15.1%, and 33.9%, respectively. From these results, we can conclude that the proposed methods provide good candidates for robust feature extraction in the noisy speech recognition.

• The Journal of the Korea Contents Association
• /
• v.3 no.1
• /
• pp.9-13
• /
• 2003

We propose a block motion estimation algorithm based on a statistical image feature for video sequences. The statistical feature of the reference block is obtained, then applied to select the candidate starting points (SPs) in the regular starting points pattern (SPP) by comparing the statistical feature of reference block with that of blocks which are spread ower regular SPP. The final SPs are obtained by their Mean Absolute Difference(MAD) value among the candidate SPs. Finally, one of conventional fast search algorithms, such as BRGDS, DS, and three-step search (TSS), has been applied to generate the motion vector of reference block using the final SPs as its starting points. The experimental results showed that the starting points from fine SPs were as dose as to the global minimum as we expected.

• Archives of design research
• /
• v.16 no.2
• /
• pp.99-110
• /
• 2003

After the industrial revolution, the design concepts have established by the basis of the ornament and styling and emphasized in the respect of characteristics of the art and manufacture. On the other side, theoretical research part of design has neglected. But, the modem concepts of design is changing into new concept that shares the attributes of various sides of sociology, cultural sciences, engineering and business adminstration study. In accordance with the change of design concept, the utility frequency of the statistical method is increasing in the ares of design. In this paper, we evaluated the adequacy of statistical method of the design papers that were published in the Journal of Korean Society of Design Science.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.3
• /
• pp.71-78
• /
• 2011

This paper propose image steganalysis scheme based on independence between parent and child subband on the multi-layer wavelet domain. The proposed method decompose cover and stego images into 12 subbands by applying 3-level Haar UWT(Undecimated Wavelet Transform), analyze statistical independency between parent and child subband. Because this independency is appeared more difference in stego image than in cover image, we can use it as feature to differenciate between cover and stego image. Therefore we extract 72D features by calculation first 3 order statistical moments from joint characteristic function between parent and child subband. Multi-layer perceptron(MLP) is applied as classifier to discriminate between cover and stego image. We test the performance of proposed scheme over various embedding rates by the LSB, SS, BSS embedding method. The proposed scheme outperforms the previous schemes in detection rate to existence of hidden message as well as exactness of discrimination.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.463-465
• /
• 2002

본 논문은 필기한자 인식의 성능 향상을 위한 개선된 윤곽선 방향 특징 추출에 대한 연구이다. 제안한 특징 추출은 기존의 방법에서 나타나는 계단현상을 완화함으로써 한자의 기본 요소인 획의 방향을 표현하는 통계적 성질을 두드러지게 하였다. 한국학 고문헌 상에 나타나는 필기 한자들을 대상으로 한 실험에서, 제안한 특징의 변별력이 뛰어나고, 오인식률이 감소하였음을 보였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10a
• /
• pp.30-32
• /
• 1999

내용 기반 이미지 데이터베이스의 검색을 위해서 low-level 특징에 기반한 방법들이 연구되고 있다. 본 논문에서는 웨이브릿 변환에 기반한 색상과 질감 특징을 이용한 내용기반 이미지 검색 시스템을 제안한다. 다양한 색상 정보로부터 추출한 인덱스 키와 웨이브릿 변환에 의해 추출한 질감 특징을 통계적 확률 분석 방법에 적용시킨 검색 시스템이다. 이러한 색상과 질감에 대한 효과적인 조합으로 보다 효율적이고 정확성 높은 결과를 도출함을 실험을 통하여 제시한다.

• Proceedings of the Korean Institute of Communication Sciences Conference
• /
• 1996.06a
• /
• pp.76-79
• /
• 1996