• 한국HCI학회:학술대회논문집
• /
• 한국HCI학회 2009년도 학술대회
• /
• pp.197-202
• /
• 2009

Active Appearance Models(AAMs)은 얼굴인식, 얼굴추적, 표정인식 뿐만 아니라 눈동자 추적과 같은 분야에도 적용되어 좋은 성능을 보여 주었다. 보통 AAM 을 생성하기 위해서는 얼굴 영상과 얼굴의 특징을 나타내는 점으로 구성된 매쉬로 이루어 지는 트레이닝 셋이 필요하다. AAM fitting algorithm 은 학습한 얼굴과 유사한 얼굴을 Fitting 할 때에는 뛰어난 성능을 보이지만 조명에 의한 그림자 또는 액세서리에 의한 얼굴의 피부 가림과 같이 전체 얼굴이 잘 나타나지 않는 불완전한 영상의 Fitting 은 입력영상과 템플릿 영상간의 오차가 커지기 때문에 실패할 가능성이 매우 높다. 본 논문에서 우리는 AAMs 에서 사용되는 PCA를 Higher-order Singular Value Decomposition(HOSVD)로 대체하여 이 문제를 보완하는 강화된 AAM 을 제안한다. 제안된 AAM 에는 기존에 사용하던 고유벡터와 함께 HOSVD 를 통해 획득할 수 있는 Eigen-Modes 를 추가하여 사용한다. 또한 우리는 Yale Face Database를 이용한 평가를 통해 제안된 AAM 이 기존 AAM 보다 불완전한 영상에 효과적으로 대응하는 것을 보여준다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권12호
• /
• pp.5826-5841
• /
• 2019

In our previous research, we proposed a tag emotion-based item recommendation scheme. The ternary associations among users, items, and tags are described as a three-order tensor in order to capture the emotions in tags. The candidates for recommendation are created based on the latent semantics derived by a high-order singular value decomposition technique (HOSVD). However, the tensor is very sparse because the number of tagged items is smaller than the amount of all items. The previous research do not consider the previous behaviors of users and items. To mitigate the problems, in this paper, the item-based collaborative filtering scheme is used to build an extended data. We also apply the probabilistic ranking algorithm considering the user and item profiles to improve the recommendation performance. The proposed method is evaluated based on Movielens dataset, and the results show that our approach improves the performance compared to other methods.

• Journal of Information Processing Systems
• /
• 제12권1호
• /
• pp.46-56
• /
• 2016

Dynamic textures are videos that exhibit a stationary property with respect to time (i.e., they have patterns that repeat themselves over a large number of frames). These patterns can easily be tracked by a linear dynamic system. In this paper, a model that identifies the underlying linear dynamic system using wavelet coefficients, rather than a raw sequence, is proposed. Content based threshold filtering based on Set Partitioning in a Hierarchical Tree (SPIHT) helps to get another representation of the same frames that only have low frequency components. The main idea of this paper is to apply SPIHT based threshold filtering on different bands of wavelet transform so as to have more significant information in fewer parameters for singular value decomposition (SVD). In this case, more flexibility is given for the component selection, as SVD is independently applied to the different bands of frames of a dynamic texture. To minimize the time complexity, the proposed model is implemented on a graphics processing unit (GPU). Test results show that the proposed dynamic system, along with a discrete wavelet and SPIHT, achieve a highly compact model with better visual quality, than the available LDS, Fourier descriptor model, and higher-order SVD (HOSVD).