• 한국정보통신학회논문지
• /
• 제23권6호
• /
• pp.682-689
• /
• 2019

부분 기반 영상 표현(part-based image representation)에서는 영상의 부분적인 모습을 기저 벡터로 표현하고 기저 벡터의 선형 조합으로 영상을 분해하며, 이 때 기저 벡터의 계수가 곧 물체의 부분적인 특징을 의미하게 된다. 본 논문에는 부분 기반 영상 표현 기법인 비음수 행렬 분해(non-negative matrix factorization, NMF)를 이용하여 얼굴 영상을 표현하고 신경망 기법을 적용하여 가려진 얼굴을 인식하는 얼굴 인식을 제안한다. 표준 비음수 행렬 분해, 투영 경사 비음수 행렬 분해, 직교 비음수 행렬 분해를 이용하여 얼굴 영상을 표현하였고, 각 기법의 성능을 비교하였다. 인식기로는 학습벡터양자화 신경망을 사용하였으며, 인식기에서의 거리 척도로는 유클리디언 거리를 사용하였다. 실험 결과, 전통적인 얼굴 인식 방법에 비하여 제안한 기법이 가려진 얼굴 인식에 보다 강인함을 보인다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권4호
• /
• pp.1463-1480
• /
• 2014

It is well known that sparse code is effective for feature extraction of face recognition, especially sparse mode can be learned in the kernel space, and obtain better performance. Some recent algorithms made use of single kernel in the sparse mode, but this didn't make full use of the kernel information. The key issue is how to select the suitable kernel weights, and combine the selected kernels. In this paper, we propose a novel multiple kernel sparse representation based classification for face recognition (MKSRC), which performs sparse code and dictionary learning in the multiple kernel space. Initially, several possible kernels are combined and the sparse coefficient is computed, then the kernel weights can be obtained by the sparse coefficient. Finally convergence makes the kernel weights optimal. The experiments results show that our algorithm outperforms other state-of-the-art algorithms and demonstrate the promising performance of the proposed algorithms.

• 정보과학회 논문지
• /
• 제44권3호
• /
• pp.295-305
• /
• 2017

얼굴 외형은 조명의 영향을 크게 받기 때문에 조명 변화는 얼굴 인식 시스템의 성능을 저하시키는 요인 중 하나이다. 본 논문에서는 non-alpha Weberface(non-alpha WF)와 히스토그램 평활화를 결합하여 조명 변화에 강건한 얼굴 표현 방법을 제안한다. 먼저, 입력 얼굴 영상에 대해 명암 대비 조절 파라미터를 적용하지 않은 non-alpha WF를 생성한다. 이후, non-alpha WF의 히스토그램 분포를 전역적으로 균일하게 하고 명암 대비를 향상시키기 위해 히스토그램 평활화를 수행한다. 제안하는 방법을 통해 전처리된 얼굴 영상으로부터 저차원 판별 특징을 추출하기 위해 $(2D)^2PCA$를 적용한다. Extended Yale B 및 CMU PIE 얼굴 데이터베이스에 대해 실험한 결과, 제안하는 방법으로 각각 93.31%와 97.25%의 평균 인식률을 얻었다. 또한, 제안하는 방법은 기존 WF뿐만 아니라 여러 조명 처리 방법들과 비교하여 향상된 인식 성능을 보였다.

• 대한인간공학회지
• /
• 제12권1호
• /
• pp.57-73
• /
• 1993

In this paper, methods of human figure representation in computer graphics are described. Many applications of the human figure representation are found in areas including industry, advertisement, and cartoon production and further research for the methods that show the human figure more realistically is ex- pected. Two analytic methods for human model, kinematics and dynamics, are ex- plained and the characteristics of the man-machine interface systems that include human figure representation are presented. Various techniques of the human figure representation based on kinematics or(and) dynamics are discussed and representation methods of human body segments such as hand, face, spine are introduced in this paper.

• Journal of information and communication convergence engineering
• /
• 제9권2호
• /
• pp.207-211
• /
• 2011

This paper presents a method for facial feature representation and recognition from the Covariance Matrices of the Gabor-filtered images. Gabor filters are a very powerful tool for processing images that respond to different local orientations and wave numbers around points of interest, especially on the local features on the face. This is a very unique attribute needed to extract special features around the facial components like eyebrows, eyes, mouth and nose. The Covariance matrices computed on Gabor filtered faces are adopted as the feature representation for face recognition. Geodesic distance measure is used as a matching measure and is preferred for its global consistency over other methods. Geodesic measure takes into consideration the position of the data points in addition to the geometric structure of given face images. The proposed method is invariant and robust under rotation, pose, or boundary distortion. Tests run on random images and also on publicly available JAFFE and FRAV3D face recognition databases provide impressively high percentage of recognition.

• 한국통신학회논문지
• /
• 제36권7C호
• /
• pp.428-434
• /
• 2011

Recently, subspace analysis has raised its performance to a higher level through the adoption of kernel-based nonlinearity. Especially, the radial basis function, based on its nonparametric nature, has shown promising results in face recognition. However, due to the endemic small sample size problem of face data, the conventional kernel-based feature extraction methods have difficulty in data representation. In this paper, we introduce a novel variant of the RBF kernel to alleviate this problem. By adopting the concept of the nearest feature line classifier, we show both effectiveness and generalizability of the proposed method, particularly regarding the small sample size issue.

• Journal of Information Processing Systems
• /
• 제15권6호
• /
• pp.1449-1461
• /
• 2019

Face sketch synthesis plays an important role in public security and digital entertainment. In this paper, we present a novel face sketch synthesis method via local similarity and nonlocal similarity regularization terms. The local similarity can overcome the technological bottlenecks of the patch representation scheme in traditional learning-based methods. It improves the quality of synthesized sketches by penalizing the dissimilar training patches (thus have very small weights or are discarded). In addition, taking the redundancy of image patches into account, a global nonlocal similarity regularization is employed to restrain the generation of the noise and maintain primitive facial features during the synthesized process. More robust synthesized results can be obtained. Extensive experiments on the public databases validate the generality, effectiveness, and robustness of the proposed algorithm.

• 대한전기학회논문지
• /
• 제41권8호
• /
• pp.922-931
• /
• 1992

This paper presents an efficient algorithm for converting the boundary representation of a polyhedron to its corresponding octree representation which is convenient for detecting intersection between objects. In order to determine the states of octants efficiently and quickly, our algorithm consists of three basic processes which use the bounding box, the infinite plane and the projection. In our conversion algorithm, the states of octants are determined by performing one of these three processes according to the intersecting pattern of an octant with a polyhedron, instead of by performing only a face-to-face intersection test repeatedly. In particular, states of 8 suboctants are determined completely by performing the process using only the infinite plane, when the given octant is intersected with only a patch of the polyhedron. Finally, by using a 3D display method and a volume ratio method, it is confirmed that the octree converted by out algorithm is accurate. It is also confirmed that the conversion time is reduced in our algorithm.

• 한국지능시스템학회논문지
• /
• 제25권4호
• /
• pp.412-417
• /
• 2015

Kinect sensor has two output data which are produced from red green blue (RGB) sensor and depth sensor, it is called color image and depth map, respectively. Although this device's prices are cheapest than the other devices for three-dimensional (3D) reconstruction, we need extra work for reconstruct a smooth 3D data and also have semantic meaning. It happened because the depth map, which has been produced from depth sensor usually have a coarse and empty value. Consequently, it can be make artifact and holes on the surface, when we reconstruct it to 3D directly. In this paper, we present a method for solving this problem by using implicit surface representation. The key idea for represent implicit surface is by using radial basis function (RBF) and to avoid the trivial solution that the implicit function is zero everywhere, we need to defined on-surface point and off-surface point. Based on our simulation results using captured face as an input, we can produce smooth 3D face and fill the holes on the 3D face surface, since RBF is good for interpolation and holes filling. Modified anisotropic diffusion is used to produced smoothed surface.

• 전자공학회논문지
• /
• 제54권3호
• /
• pp.55-62
• /
• 2017

비음수 행렬 분해 기법(non-negative matrix factorization)은 대표적인 부분 영역 기반 표현 기법의 하나로 영상의 부분적인 특징을 나타내는 기저 벡터의 선형 조합으로 영상을 표현하는 기법이다. 본 논문에서는 여러 가지 비음수 행렬 분해 기법을 이용하여 얼굴 영상을 표현하고, 추출된 특징을 기반으로 학습 벡터 양자화를 이용하여 얼굴 인식을 수행하였다. 추출된 각 기법의 기저 벡터를 비교하여 각 기법의 특징을 분석하였다. 또한 NMF 기법들의 인식율 검증을 통해 비음수 행렬 기법의 얼굴 인식에 대한 활용 가능성을 확인하였다.