Baocai Yin

3D face recognition using local binary patterns

It is well recognized that expressions can significantly change facial geometry that results in a severe problem for robust 3D face recognition. So it is crucial for many applications that how to extract expression-robust features to describe 3D faces. In this paper, we develop a novel 3D face recognition algorithm using Local Binary Pattern (LBP) under expression varieties, which is an extension of the LBP operator widely used in ordinary facial analysis. First, to depict the human face more accurately and reduce the effect of facial local distortion for face recognition, a special feature-based 3D face division scheme is proposed. Then, the LBP representation framework for 3D faces is described, and the facial depth and normal information are extracted and encoded by LBP, to reduce the expression effect. For each face region, the statistical histogram is utilized to summarize the facial details, and accordingly three matching strategies are presented to address the recognition task. Finally, the proposed 3D face recognition algorithm is tested on BJUT-3D and FRGC v2.0 databases, achieves promising results, and concludes that it is feasible and valid to apply the LBP representation framework on 3D face recognition.

An improved active shape model for face alignment

In this paper, we present several improvements on conventional active shape models (ASM) for face alignment. Despite the accuracy and robustness of ASMs in image alignment, its performance depends heavily on the initial parameters of the shape model, as well as the local texture model for each landmark and the corresponding local matching strategy. In this work, to improve ASMs for face alignment, several measures are taken. First, salient facial features, such as the eyes and the mouth, are localized based on a face detector. These salient features are then utilized to initialize the shape model and provide region constraints on the subsequent iterative shape searching. Secondly, we exploit edge information to construct better local texture models for landmarks on the face contour. The edge intensity at the contour landmark is used as a self-adaptive weight when calculating the Mahalanobis distance between the candidate and reference profile. Thirdly, to avoid unreasonable shift from pre-localized salient features, landmarks around the salient features are adjusted before applying global subspace constraints. Experiments on a database containing 300 labeled face images show that the proposed method performs significantly better than traditional ASMs.

Gabor-based dynamic representation for human fatigue monitoring in facial image sequences

Human fatigue is an important reason for many traffic accidents. To improve traffic safety, this paper proposes a novel Gabor-based dynamic representation for dynamics in facial image sequences to monitor human fatigue. Considering the multi-scale character of different facial behaviors, Gabor wavelets are employed to extract multi-scale and multi-orientation features for each image. Then features of the same scale are fused into a single feature according to two fusion rules to extract the local orientation information. To account for the temporal aspect of human fatigue, the fused image sequence is divided into dynamic units, and a histogram of each dynamic unit is computed and combined as dynamic features. Finally, AdaBoost algorithm is exploited to select the most discriminative features and construct a strong classifier to monitor fatigue. The proposed method was tested on a wide range of human subjects of different genders, poses and illuminations under real-life fatigue conditions. Experimental results show the validity of the proposed method, and an encouraging average correct rate is achieved.

Color face recognition based on 2DPCA

This paper presents a novel color face recognition approach based on 2DPCA. A matrix-representation model, which encodes the color information directly, is proposed to describe the color face image. The matrix-representation model defines the pixel in color face image as the basic unit, the color information of the pixel as the basic component, and then represents the color face image efficiently in the format of matrix. Based on the representation model, color-Eigenfaces are computed for feature extraction using 2DPCA. Nearest neighborhood classification approach is adopted to identify the color face samples. Experimental results on CVL and CMU PIE color face database show the good performance of the proposed color face recognition approach.

Efficient Multiple-Description Image Coding Using Directional Lifting-Based Transform

This paper proposes an efficient two-description image coding technique. The two side descriptions of an image are generated by quincunx subsampling. The decoding from any side description is done by an interpolation process that exploits sample correlation. Although the quincunx subsampling is a natural choice for the best use of sample correlations in image multiple-description coding (MDC), each side description is not amenable to existing image coding techniques because the pixels are not aligned rectilinearly. We show how this difficulty can be overcome by an adaptive directional lifting (ADL) transform that is particularly suitable for decorrelating samples on the quincunx lattice. The ADL transform can be embedded into JPEG 2000 to construct a practical MD image encoder. Experimental results demonstrate that the proposed image MDC scheme can achieve good coding performance.

Color face recognition based on quaternion matrix representation

There are several methods to recognize and reconstruct a human face image. The principal component analysis (PCA) is a successful approach because of its effective extraction of the global feature and excellent reconstruction of face image. However, the crucial shortcomings of PCA are its low recognition rate and overfitting of feature extraction which leads to the dependence of training data on training samples. In this paper, a modified two-dimension principal component analysis (2DPCA) and bidirectional principal component analysis (BDPCA) methods based on quaternion matrix are proposed to recognize and reconstruct a color face image. In these methods, the spatial distribution information of color images is used to represent a color face, and the 2DPCA or BDPCA feature of color face image is extracted by reducing the dimensionality in both column and row directions. A method obtaining orthogonal eigenvector set of quaternion matrix is proposed. Numerous experiments show that the present approach based on quaternion matrix can effectively smooth the overfitting issue and substantially enhance the recognition rate.

MULTISCALE DYNAMIC FEATURES BASED DRIVER FATIGUE DETECTION

Driver fatigue is a significant factor in many traffic accidents. We propose a novel approach for driver fatigue detection from facial image sequences, which is based on multiscale dynamic features...

A hierarchical dense deformable model for 3D face reconstruction from skull

Abstract3D face reconstruction from skull has been investigated deeply by computer scientists in the past two decades because it is important for identification. The dominant methods construct 3D face from the soft tissue thickness measured at a set of landmarks on skull. The quantity and position of the landmarks are very vital for 3D face reconstruction, but there is no uniform standard for the selection of the landmarks. Additionally, the acquirement of the landmarks on skull is difficult without manual assistance. In this paper, an automatic 3D face reconstruction method based on a hierarchical dense deformable model is proposed. To construct the model, the skull and face samples are acquired by CT scanner and represented as dense triangle mesh. Then a non-rigid dense mesh registration algorithm is presented to align all the samples in point-to-point correspondence. Based on the aligned samples, a global deformable model is constructed, and three local models are constructed from the segmented patches of the eye, nose and mouth. For a given skull, the globe and local deformable models are iteratively matched with it, and the reconstructed facial surface is obtained by fusing the globe and local reconstruction results. To validate the presented method, a measurement in the coefficient domain of a face deformable model is defined. The experimental results indicate that the proposed method has good performance for 3D face reconstruction from skull.

Low Rank Representation on Grassmann Manifolds

Low-rank representation (LRR) has recently attracted great interest due to its pleasing efficacy in exploring low-dimensional subspace structures embedded in data. One of its successful applications is subspace clustering which means data are clustered according to the subspaces they belong to. In this paper, at a higher level, we intend to cluster subspaces into classes of subspaces. This is naturally described as a clustering problem on Grassmann manifold. The novelty of this paper is to generalize LRR on Euclidean space into the LRR model on Grassmann manifold. The new method has many applications in computer vision tasks. The paper conducts the experiments over two real world examples, clustering handwritten digits and clustering dynamic textures. The experiments show the proposed method outperforms a number of existing methods.

Hash-Based Block Matching for Screen Content Coding

By considering the increasing importance of screen contents, the high efficiency video coding (HEVC) standard includes screen content coding as one of its requirements. In this paper, we demonstrate that enabling frame level block searching in HEVC can significantly improve coding efficiency on screen contents. We propose a hash-based block matching scheme for the intra block copy mode and the motion estimation process, which enables frame level block searching in HEVC without changing the HEVC syntaxes. In the proposed scheme, the blocks sharing the same hash values with the current block are selected as prediction candidates. Then the hash-based block selection is employed to select the best candidates. To achieve the best coding efficiency, the rate distortion optimization is further employed to improve the proposed scheme by balancing the coding cost of motion vectors and prediction difference. Compared with HEVC, the proposed scheme achieves 21% and 37% bitrate saving with all intra and low delay configurations with encoding time reduction. Up to 59% bitrate saving can be achieved on sequences with large motions.