• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.163-167
• /
• 2009

3D human body scan technique is known to be practically useful in industrial field as the technique becomes more precise and cheaper. Landmark extraction is essential for full utilization of the scan data. In this paper, we suggest an algorithm for automatic landmark extraction. For this purpose, we perform markerless matching to the target data using PCA analysis and quasi-Newton optimization. Landmarks are extracted from the topology of resulting body.

• YAKHAK HOEJI
• /
• v.37 no.2
• /
• pp.119-123
• /
• 1993

A spectrophotomertic method is proposed for the determination of antihistamines. The method is based on solvent extraction of the ion pair formed between antihistamines and colored picric acid into chloroform. The binding state of antihistamines-picric acid complexes were presumed by IR and $^{1}$H-NMR spectra as intermolecular hydrogen bonding. This method was applicable to the determination of antihistamines in the pharamaceutical preparations.

• Korean Journal of Food Science and Technology
• /
• v.26 no.1
• /
• pp.44-50
• /
• 1994

In order to develop an effective extraction method of sea mustard, five different methods of boiling in 0.5% $Na_{2}EDTA(A)$, in 0.1 N HCI(B), in 0.5% $Na_{2}EDTA$ and 0.1 N HCI(C) and hydrolysis with two different polysaccharides-hydrolyzing enzymes of Celluclast(method D) and Ultrazyme(method E) prior to boiling in 0.5% $Na_{2}EDTA$ and 0.1 N HCI were studied. The highest yields of solids(63.14%) and protein(26.39%) from the extract were obtained by method D. The concentration of amino-N was significantly improved by method C(870 ppm) followed by method D(770 ppm), B(570 ppm) and A(480 ppm) compared to the control(270 ppm). Total free amino acids, mainly alanine, glutamic, and aspartic acids, were greatly increased by methods of A(8.88 mg%), D(4.14 mg%) and E(4.18 mg%) which were $2.5{\sim}5.1$ times higher than those in control(1.71 mg%). The sensory characteristics showed that extract D was significantly low in intensity of fishy odor and high in seaweed taste. Therefore, method D was suggested as the effective extraction method.

• Journal of the HCI Society of Korea
• /
• v.1 no.2
• /
• pp.27-33
• /
• 2006

This paper presents a new approach to translation and rotation invariant feature extraction for image texture retrieval. For the rotation invariant feature extraction, we invent angular projection along angular frequency in Polar coordinate system. The translation and rotation invariant feature vector for representing texture images is constructed by the averaged magnitude and the standard deviations of the magnitude of the Fourier transform spectrum obtained by the proposed angular projection. In order to easily implement the angular projection, the Radon transform is employed to obtain the Fourier transform spectrum of images in the Polar coordinate system. Then, angular projection is applied to extract the feature vector. We present our experimental results to show the robustness against the image rotation and the discriminatory capability for different texture images using MPEG-7 data set. Our Experiment result shows that the proposed rotation and translation invariant feature vector is effective in retrieval performance for the texture images with homogeneity, isotropy and local directionality.

• 한국HCI학회:학술대회논문집
• /
• 2006.02a
• /
• pp.699-704
• /
• 2006

본 논문은 회전 및 천이불변 이미지 텍스처 검색의 새로운 방식을 소개한다. 주파수 영역의 극좌표계에서 동일한 공간 주파수에서 각도 방향으로 투영을 하는 각도 투영법을 제안하며, 제안된 각도 투영법을 이용하여 주파수 영역에서 푸리에 계수이 합과 표준편차를 특징벡터로 이용한다. 각도 투영법을 쉽게 구현하기 위해 극좌표계에서 라돈변환이 수행된다. 실험 시 MPEG-7 데이터를 이용하였으며 그 결과는 여러 텍스처 이미지를 검색하는데 있어서 특징을 잘 구별해 내는 결과를 보여준다. 또한 제안된 회전 및 천이불변 특징 추출 알고리듬은 등방성 텍스처나 국부적인 방향성을 보이는 텍스처 영상 검색에도 효율적인 검색률을 보인다.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.487-492
• /
• 2008

Facial expression recognition is an intensive research area for designing Human Computer Interfaces. In this work, we present a new facial expression recognition system utilizing Enhanced Independent Component Analysis (EICA) for feature extraction and discrete Hidden Markov Model (HMM) for recognition. Our proposed approach for the first time deals with sequential images of emotion-specific facial data analyzed with EICA and recognized with HMM. Performance of our proposed system has been compared to the conventional approaches where Principal and Independent Component Analysis are utilized for feature extraction. Our preliminary results show that our proposed algorithm produces improved recognition rates in comparison to previous works.

• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.44-49
• /
• 2007

반짝이는 특성의 물체에 대해 이미지를 기반으로 색을 추출하는 경우 반짝이는 특성을 포함하면서 내재되어 있는 색 특성을 표현하기 위해 색 곡선(color line)을 이용한다. 이 경우 추출하려는 색이 왜곡되지 않은 가장 적합한 이미지를 선정하는 방법이 필요하다. 이를 위해서 실감모델링을 위해 색 곡선을 기반으로 색을 추출하는 방법을 제시하고 제시된 방법을 위해 색을 추출하기 가장 적합한 이미지를 선정하는 기준을 색포화율(color saturation ratio)을 통해 제안한다. 색포화율이란 색을 구성하는 요소 중에서 최소한 하나 이상의 색이 포화된 픽셀들을 최대 색거리를 가진 픽셀들로 간주하여 계산된 색거리의 총합에 대해 최소한 하나 이상의 색이 포화된 픽셀들의 색거리 총합의 비율를 의미한다. 이상적으로 이 비율이 최소가 되면 하이라이트를 제외한 어떤 픽셀도 포화되지 않기 때문에 반짝이는 특성을 가진 물체의 색을 추출하기 위해 촬영된 이미지는 하이라이트를 제외한 모든 색이 왜곡되지 않은 가장 적합한 이미지가 생성된다. 또한, 이렇게 선정된 이미지에서 추출된 색의 효율성을 보이기 위해 색 공간과 이미지 상에서 다양한 형태의 응용 결과를 제시하였다.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.2083-2085
• /
• 2009

Brain Computer Interface (BCI) is a communication pathway between devices (computers) and human brain. It treats brain signals in real-time basis and discriminates some information of what human brain is doing. In this work, we develop a EEG BCI system using a feature extraction such as common spatial pattern (CSP) and a classifier using Fisher linear discriminant analysis (FLDA). Two-class EEG motor imagery movement datasets with both cued and uncued are tested to verify its feasibility.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.642-645
• /
• 2009

Brain Computer Interface (BCI) is a communication pathway between devices (computers) and human brain. It treats brain signals in real-time basis and discriminates some information of what human brain is doing. In this work, we develop a EEG BCI system using a feature extraction such as common spatial pattern (CSP) and a classifier using Fisher linear discriminant analysis (FLDA). Two-class EEG motor imagery movement datasets with both cued and uncued are tested to verify its feasibility.

• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2000.11a
• /
• pp.194-198
• /
• 2000

본 논문은 특별한 마커를 사용하지 않고 연속되는 영상들에서 사람의 2차원 움직임 정보를 추출하는 알고리즘을 제안한다. 사람의 움직임 정보 추출을 위해 색상, 움직임, 윤곽선, 그리고 사용자의 개인적인 특성을 반영하는 신체적인 특성 정보를 이용한다. 본 논문에서 제안하는 방법은 사람의 움직임 정보를 이용한 가상 캐릭터의 제어와 같은 마커를 사용하지 않는 다양한 HCI 응용분야에 사용될 수 있다.