• Journal of KIISE:Software and Applications
• /
• v.34 no.5
• /
• pp.476-486
• /
• 2007

This paper proposes a resolution enhancement method which can reconstruct high-resolution facial images from single-frame, low-resolution facial images. The proposed method is derived from example-based reconstruction methods and the morphable face model. In order to improve the performance of the example-based reconstruction, we propose the region-based reconstruction method which can maintain the characteristics of local facial regions. Also, in order to use the capability of the morphable face model to face resolution enhancement problems, we define the extended morphable face model in which an extended face is composed of a low-resolution face, its interpolated high-resolution face, and the high-resolution equivalent, and then an extended face is separated by an extended shape vector and an extended texture vector. The encouraging results show that the proposed methods can be used to improve the performance of face recognition systems, particularly to enhance the resolution of facial images captured from visual surveillance systems.

• Proceedings of the Korean Information Science Society Conference
• /
• 2000.04b
• /
• pp.583-585
• /
• 2000

본 논문에서는 적은 수의 특징점을 이용한 얼굴 복원 방법을 제안한다. 먼저 얼굴을 형태와 질갑 프로토타입들의 선형 중첩으로 모형화한 다음, 특징점에서의 형태와 질감정보만을 가지고 각각의 얼굴이 요구하는 변형의 근사값을 찾는다. 본 논문에서는 이러한 under-determined 조건에서 최소 제곱법(least square minimization method)을 사용하여 최적값을 얻는다. 실험을 통하여 적은 수의 특징점을 이용하여 2차원 얼굴 영상을 효율적으로 복원할 수 있음을 검증하였다. 우리는 제안된 얼굴 영상을 압축하거나 겹침이나 잡영에 의해 손상된 영상으로부터 원래의 전체 정보를 복원하는데 중요한 역할을 할 수 있을 것으로 기대한다.

• Journal of KIISE:Software and Applications
• /
• v.34 no.3
• /
• pp.266-274
• /
• 2007

This paper proposes a new reconstruction method of high-resolution facial image from a low-resolution facial image based on top-down machine learning and recursive error back-projection. A face is represented by a linear combination of prototypes of shape and that of texture. With the shape and texture information of each pixel in a given low-resolution facial image, we can estimate optimal coefficients for a linear combination of prototypes of shape and those that of texture by solving least square minimizations. Then high-resolution facial image can be obtained by using the optimal coefficients for linear combination of the high-resolution prototypes. In addition, a recursive error back-projection procedure is applied to improve the reconstruction accuracy of high-resolution facial image. The encouraging results of the proposed method show that our method can be used to improve the performance of the face recognition by applying our method to reconstruct high-resolution facial images from low-resolution images captured at a distance.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10c
• /
• pp.452-454
• /
• 1998

본 논문에서는 MPEG 압축 비디오 상에서 얼굴 영역을 추출하고 이를 인식하는 방법에 대하여 제안한다. 제안된 방법은 크게 MPEG 압축 비디오의 처리를 위한 축소된 DC 영상의 구성 단계, 축소된 DC 영상에서의 얼굴 영역 추출 단계, 그리고 얼굴 영역이 추출된 프레임에 대한 압축 복원 및 얼굴 인식의 3단계로 구성되어있다. DC 영상의 구성 단계에서는 압축 복원 없이 DCT 계수의 DC 값과 2개의 AC 값만을 사용하여 부분적인 2차원 역 DCT 변환을 이용한 방법을 사용하였으며, 얼굴 영역 추출 단계에서는 DC 영상에 대해 얼굴의 색상 및 형태 정보를 이용한 얼굴 후보 영역 추출 방법과 K-L 변환 및 역 변환의 오차에 의한 얼굴 영역 추출 방법을 사용하였다. 얼굴 인식 단계에서는 얼굴 영역이 추출된 프레임에 대하여 GOP 단위의 압축 복원을 수행한 후 고유 얼굴 영상을 이용한 방법으로 얼굴 인식을 수행하였다. 제안된 방법의 성능을 검증하기 위하여 뉴스와 드라마 MPEG 비디오를 대상으로 실험을 수행하였으며, 실험 결과 제안된 방법이 효율적임을 알 수 있었다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.5
• /
• pp.72-83
• /
• 2011

In this paper, we propose a method to detect and recover the occluded parts of face images using the correlation between pairs of pixels. In a training stage, correlation coefficients between every pairs of pixels are calculated using the occlusion-free face images. Once a new occluded face image is shown, the occluded area is detected and recovered using the correlation coefficients obtained in the training stage. We compare the performance of the proposed method with the conventional method based on PCA. The results show that the proposed method detects and recovers occluded area with much smaller noises than the conventional PCA based method. Moreover, recovered images by the proposed method were more smooth with reduced blurring effect.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.122-131
• /
• 2011

A widely used single image-based 3D face reconstruction method, 3D morphable shape model, reconstructs an accurate 3D facial shape when 2D facial feature points are correctly extracted from an input face image. However, in the case that a user's cooperation is not available such as a real-time 3D face reconstruction system, this method can be vulnerable to the errors of automatic facial feature point extraction. In order to solve this problem, we automatically classify extracted facial feature points into two groups, erroneous and correct ones, and then reconstruct a 3D facial shape by using only the correctly extracted facial feature points. The experimental results showed that the 3D reconstruction performance of the proposed method was remarkably improved compared to that of the previous method which does not consider the errors of automatic facial feature point extraction.

• Journal of Korea Multimedia Society
• /
• v.7 no.3
• /
• pp.308-318
• /
• 2004

A subject to recognize the damaged facial image is becoming an important issue in commercialization of automatic face recognition. The method to recognize a face on a damaged image is divided into two types. The one is to recognize remainders after removing the damaged information and the other is to recognize a total face after recovering the damaged information. On this paper, we present the reconstruction method by analyzing the main materials after extracting the damaged region through Kohonen network. The suggested algorithm in this paper estimates feature vectors of the damaged region using eigen-faces in PCA and then reconstructs the damaged image. This allows also the reconstruction under the untrained images. Through testing the artificial images where the eye and the mouth which have many effects to face recognition are damaged, the recognition rate of the proposed results showed similar results with the method which used Kohonen network, and improved about 11.8% more than symmetrical property method. Also, in case of the untrained image, our results improved about 14% more than that of the Kohonen method and about 7% more than that of the symmetrical property method.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.1
• /
• pp.103-110
• /
• 2011

A widely used 3D face reconstruction method, structure from motion(SfM), shows robust performance when frontal, left, and right face images are used. However, this method cannot reconstruct a self-occluded facial part correctly when only one side view face images are used because only partial facial feature points can be used in this case. In order to solve the problem, the proposed method exploit a constrain that is bilateral symmetry of human faces in order to generate bilateral facial feature points and use both input facial feature points and generated facial feature points to reconstruct a 3D face. For quantitative evaluation of the proposed method, 3D faces were obtained from a 3D face scanner and compared with the reconstructed 3D faces. The experimental results show that the proposed 3D face reconstruction method based on both facial feature points outperforms the previous 3D face reconstruction method based on only partial facial feature points.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2903-2905
• /
• 2005

많은 경우, 부분 손상된 얼굴 영상을 복원해야 할 필요가 있다. 대표적인 예로는 감시카메라에 찍힌 범인의 얼굴 영상이 이에 속한다. 이런 경우 얼굴의 중요한 부분이 가려져 있기 때문에 자동 얼굴 인식 시스템이나 사람의 관찰로는 그 부분을 인식하기는 매우 어렵다. 이 논문에서는 어려움을 극복하기 위해 새롭게 개발된 SVDD기반 노이즈 제거 기법을 부분 손상된 얼굴 영상에 적용한 문제를 고려해 보았다.

• The KIPS Transactions:PartB
• /
• v.9B no.5
• /
• pp.563-570
• /
• 2002

Robust extraction of 3D facial features and global motion information from 2D image sequence for the MPEG-4 SNHC face model encoding is described. The facial regions are detected from image sequence using multi-modal fusion technique that combines range, color and motion information. 23 facial features among the MPEG-4 FDP (Face Definition Parameters) are extracted automatically inside the facial region using color transform (GSCD, BWCD) and morphological processing. The extracted facial features are used to recover the 3D shape and global motion of the object using paraperspective camera model and SVD (Singular Value Decomposition) factorization method. A 3D synthetic object is designed and tested to show the performance of proposed algorithm. The recovered 3D motion information is transformed into global motion parameters of FAP (Face Animation Parameters) of the MPEG-4 to synchronize a generic face model with a real face.