• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.468-488
• /
• 2016

The paper proposes a novel framework for 3D face verification using dimensionality reduction based on highly distinctive local features in the presence of illumination and expression variations. The histograms of efficient local descriptors are used to represent distinctively the facial images. For this purpose, different local descriptors are evaluated, Local Binary Patterns (LBP), Three-Patch Local Binary Patterns (TPLBP), Four-Patch Local Binary Patterns (FPLBP), Binarized Statistical Image Features (BSIF) and Local Phase Quantization (LPQ). Furthermore, experiments on the combinations of the four local descriptors at feature level using simply histograms concatenation are provided. The performance of the proposed approach is evaluated with different dimensionality reduction algorithms: Principal Component Analysis (PCA), Orthogonal Locality Preserving Projection (OLPP) and the combined PCA+EFM (Enhanced Fisher linear discriminate Model). Finally, multi-class Support Vector Machine (SVM) is used as a classifier to carry out the verification between imposters and customers. The proposed method has been tested on CASIA-3D face database and the experimental results show that our method achieves a high verification performance.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.19-21
• /
• 2022

Anomaly detection using self-supervised learning typically generates synthetic data to learn to classify normal and abnormal, and uses real abnormal data as test data to measure anomaly detection performance. In a study using this method to generate synthetic data similar to normal data, anomaly detection was carried out by generating synthetic data by cutting and pasting a specific patch from the original image. In this way, the degree of similarity to normal data depends on the number and size of patches, which affects anomaly detection performance. In this paper, synthetic data were generated by varying patch sizes and numbers, and then similarity and analysis with normal data were conducted using a pre-trained model, and anomaly detection performance was measured by learning the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.8
• /
• pp.3962-3980
• /
• 2019

To deal with single sample face recognition, this paper presents a patch based semi-supervised linear regression (PSLR) algorithm, which draws facial variation information from unlabeled samples. Each facial image is divided into overlapped patches, and a regression model with mapping matrix will be constructed on each patch. Then, we adjust these matrices by mapping unlabeled patches to $[1,1,{\cdots},1]^T$. The solutions of all the mapping matrices are integrated into an overall objective function, which uses ${\ell}_{2,1}$-norm minimization constraints to improve discrimination ability of mapping matrices and reduce the impact of noise. After mapping matrices are computed, we adopt majority-voting strategy to classify the probe samples. To further learn the discrimination information between probe samples and obtain more robust mapping matrices, we also propose a multistage PSLR (MPSLR) algorithm, which iteratively updates the training dataset by adding those reliably labeled probe samples into it. The effectiveness of our approaches is evaluated using three public facial databases. Experimental results prove that our approaches are robust to illumination, expression and occlusion.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.6
• /
• pp.2748-2766
• /
• 2016

Compared with traditional patch-based sparse representation, recent studies have concluded that group-based sparse representation (GSR) can simultaneously enforce the intrinsic local sparsity and nonlocal self-similarity of images within a unified framework. This article investigates an accelerated split Bregman method (SBM) that is based on GSR which exploits image compressive sensing (CS). The computational efficiency of accelerated SBM for the measurement matrix of a partial Fourier matrix can be further improved by the introduction of a fast Fourier transform (FFT) to derive the enhanced algorithm. In addition, we provide convergence analysis for the proposed method. Experimental results demonstrate that accelerated SBM is potentially faster than some existing image CS reconstruction methods.

• Journal of Broadcast Engineering
• /
• v.21 no.2
• /
• pp.272-275
• /
• 2016

This paper presents a method of single image dehazing and surface-based feature detection for remote sensing images. In the conventional dark channel prior (DCP) algorithm, the resulting transmission map invariably includes some block artifacts because of patch-based processing. This also causes image blur. Therefore, a refined transmission map based on a hidden Markov random field and expectation-maximization algorithm can reduce the block artifacts and also increase the image clarity. Also, the proposed algorithm enhances the accuracy of image matching surface-based features in an remote sensing image. Experimental results confirm that the proposed algorithm is superior to conventional algorithms in image haze removal. Moreover, the proposed algorithm is suitable for the problem of image matching based on feature extraction.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.6
• /
• pp.48-60
• /
• 2011

Nowadays, the 3D community is actively researching on 3D imaging and free-viewpoint video (FVV). The free-viewpoint rendering in multi-view video, virtually move through the scenes in order to create different viewpoints, has become a popular topic in 3D research that can lead to various applications. However, there are restrictions of cost-effectiveness and occupying large bandwidth in video transmission. An alternative to solve this problem is to generate virtual views using a single texture image and a corresponding depth image. A critical issue on generating virtual views is that the regions occluded by the foreground (FG) objects in the original views may become visible in the synthesized views. Filling this disocclusions (holes) in a visually plausible manner determines the quality of synthesis results. In this paper, a new approach for handling disocclusions using depth based inpainting algorithm in synthesized views is presented. Patch based non-parametric texture synthesis which shows excellent performance has two critical elements: determining where to fill first and determining what patch to be copied. In this work, a noise-robust filling priority using the structure tensor of Hessian matrix is proposed. Moreover, a patch matching algorithm excluding foreground region using depth map and considering epipolar line is proposed. Superiority of the proposed method over the existing methods is proved by comparing the experimental results.

• Journal of the HCI Society of Korea
• /
• v.2 no.2
• /
• pp.11-18
• /
• 2007

We propose a novel method to conceal fiducial markers observed in augmented scenes using patch-based texture synthesis. Despite the efficiency for simple object recognition and tracking, the markers deliver inherent obtrusiveness. They do not only reduce immersiveness, but also severely degrade usability of augmented reality. The proposed method constructs alternative images in real time to overlay markers present in the sequence of images. The global characteristics of background textures are retained and the results are more adaptive to illumination changes.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.773-776
• /
• 1998

In this paper, we propose an efficient multi-view images coding algorithm which finds the optimal texture from the restricted number of multi-view images. The X-Y plane of the normalized object space is divided into triangular patches. The depth value of the node is determined by applying the block based disparity compensation method and then the texture of the each patch is extracted by applying the affine transformation patch is extracted by applying the affine transformation based disparity compensation method to the multi-view images. We restricted the number of images contributed to determining the texture comapred to traditional methods which use all the multi-view images in the texture extraction. Experimental results show that the SNR of images encoded by the proposed algorithm is better than that of imaes encoded by the traditional method by the amount about 0.2dB for the test sets of multi-view images called dragon, kid, city and santa. The recovered images from the encoded data by the proposed method show the better visual images than the recovered images from the encoded data by the traditional methods.

• Proceedings of the IEEK Conference
• /
• 2003.07e
• /
• pp.1747-1750
• /
• 2003

This paper proposes a multilevel vector error diffusion for fast and accurate color reproduction. Proposed method considered both hue angle and Euclidean distance during the multilevel vector error diffusion procedure to improve time complexity and output image quality In the error diffusion process, it can be determined whether error is diffused or not by comparing the vector norm and lightness value between original vector and error corrected vector of neighborhood pixels. For adaptive selection of output patch, this paper computes chroma value of error corrected vector and compares the hue angle between error corrected input vector and 64 primary color vectors.

• Journal of Information Processing Systems
• /
• v.15 no.6
• /
• 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.