Publications (5)0 Total impact
- [Show abstract] [Hide abstract]
ABSTRACT: Facial occlusions such as eyeglasses, hairs and beards decrease the performance of face recognition algorithms. To improve the performance of face recognition algorithms, this paper proposes a novel framework of face recognition combined with the occluded-region detection method. In this paper, we detect occluded regions using Fast-Weighted Principal Component Analysis (FW-PCA) and use the occluded regions as weights for matching face images. To demonstrate the effectiveness of the proposed framework, we use two face recognition algorithms: Local Binary Patterns (LBP) and Phase-Only Correlation (POC). Experimental evaluation using public face image databases indicates performance improvement of the face recognition algorithms for face images with natural and artificial occlusions.
Conference Paper: Restoring occluded regions using FW-PCA for face recognition[Show abstract] [Hide abstract]
ABSTRACT: Occlusions in face images such as eyeglasses, hairs and whiskers decrease the performance of face recognition algorithms. Addressing this problem, this paper proposes a method for restoring occluded regions in face images. The proposed method employs Fast Weighted Principal Component Analysis (FW-PCA), which computes PCA only with effective pixels. The use of FW-PCA makes it possible to detect and restore occluded regions in face images. Through a set of experiments using public face databases, we demonstrate the effectiveness of the proposed method compared with the conventional methods.
Conference Paper: Reconstructing occluded regions using fast weighted PCA[Show abstract] [Hide abstract]
ABSTRACT: Reconstructing occluded regions of the object is to automatically detect the occluded regions and background in the image and reconstruct these regions using image interpolation. This paper proposes a novel occluded region reconstruction method using Fast Weighted Principal Component Analysis (FW-PCA). The computation time of the weighted PCA can be reduced by using only the effective regions when calculating the principal component scores. The occluded regions are accurately detected by recursively updating the weight for each pixel in the image using FW-PCA. Then, the occluded regions can be reconstructed using the final weight. Thorough a set of experiments, we demonstrate that the proposed method exhibits higher performance than the conventional method.
Conference Paper: Fast image inpainting using similarity of subspace method.[Show abstract] [Hide abstract]
ABSTRACT: Image inpainting is a technique for estimating missing pixel values in an image by using the pixel value information obtained from neighbor pixels of a missing pixel or the prior knowledge derived from learning the object class. In this paper, we propose a fast and accurate image inpainting method using similarity of the subspace. The proposed method generates the subspace from many images related to the object class in the learning step and estimates the missing pixel values of the input image belonging to the same object class so as to maximize the similarity between the input image and the subspace in the inpainting step. Through a set of experiments, we demonstrate that the proposed method exhibits excellent performance in terms of both inpainting accuracy and computation time compared with conventional algorithms.
Conference Paper: Face recognition using phase-based correspondence matching[Show abstract] [Hide abstract]
ABSTRACT: This paper proposes a 2D face recognition algorithm using phase-based correspondence matching. The phase information obtained from 2D DFT (Discrete Fourier Transform) of images contains important information of image representation. The phase-based image matching is successfully applied to sub-pixel image registration tasks for computer vision applications and image recognition tasks for biometric authentication applications. Hierarchical block matching using phase information, i.e, phase-based correspondence matching, can find the corresponding points on the input image from the reference points on the registered image with sub-pixel accuracy. For face recognition, the phase-based correspondence matching is useful for minute change of texture, such as facial expression change, illumination change, etc. Experimental evaluation using the CSU Face Identification Evaluation System with the FERET database demonstrates efficient recognition performance of the proposed algorithm compared with the conventional face recognition algorithms.