Fuqing Duan

Active contour model combining region and edge information

A novel active contour model is proposed by combining region and edge information. Its level set formulation consists of the edge-related term, the region-based term and the regularization term. The edge-related term is derived from the image gradient, and facilitates the contours evolving into object boundaries. The region-based term is constructed using both local and global statistical information, and related to the direction and velocity of the contour propagation. The last term ensures stable evolution of the contours. Finally, a Gaussian convolution is used to regularize the level set function. In addition, a new quantitative metric named modified root mean squared error is defined, which can be used to evaluate the final contour more accurately. Experimental results show that the proposed method is efficient and robust, and can segment homogenous images and inhomogenous images with the initial contour being set freely.

A new linear algorithm for calibrating central catadioptric cameras

In this paper, a novel linear calibration algorithm based on lines is presented for central catadioptric cameras. We firstly derive the relationship between the projection on the viewing sphere of a space point and its catadioptric image. And then by the relationship we establish a group of linear constraints on the catadioptric parameters from the catadioptric projections of spatial lines. By using these linear constraints, any central catadioptric camera can be fully calibrated from a single view of three or more lines without prior knowledge on the camera. Extensive experiments show this algorithm can improve the calibrations robustness.

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.

Pose determination and plane measurement using a trapezium

In this paper, a new affine invariant of trapezia is introduced, and the projection of trapezia is deduced from this invariant. Known the lengths of the two parallel sides of a trapezium, pose estimation and plane measurement can be realized in a very simple way from the projection of the trapezium. Experiments on simulated and real images show that the approach is robust and accurate. Two parallel lines, which can determine a trapezium, are not rare in many structured scenes, the proposed method has wide applicability.

Craniofacial reconstruction based on multi-linear subspace analysis

Craniofacial reconstruction aims to estimate an individual’s facial appearance from its skull. It can be applied in many multimedia services such as forensic medicine, archaeology, face animation etc. In this paper, a statistical learning based method is proposed for 3D craniofacial reconstruction. In order to well represent the craniofacial shape variation and better utilize the relevance between different local regions, two tensor models are constructed for the skull and the face skin respectively, and multi-linear subspace analysis is used to extract the craniofacial subspace features. A partial least squares regression (PLSR) based mapping from skull subspace to skin subspace is established with the attributes such as age and BMI being considered. For an unknown skull, the 3D face skin is reconstructed using the learned mapping with the help of the skin tensor model. Compared with some other statistical learning based method in literature, the proposed method more directly and properly reflects the shape relationship between the skull and the face. In addition, the proposed method has little manual intervention. Experimental results show that the proposed method is valid.

8-point algorithm revisited: factorized 8-point algorithm

In this paper, a novel algorithm for the fundamental matrix estimation, called factorized 8-point algorithm, is presented. The factorized 8-point algorithm is composed of three steps: (1) The measurement matrix in the traditional 8-point algorithm is decomposed into two factor matrices; (2) By introducing some auxiliary variables, a new linear minimization problem is formed, where every element of its associated measurement matrix is simply either a measurement datum or a constant; (3) The fundamental matrix is determined by solving this minimization problem by a least squares method. Like the traditional 8-point algorithm and Hartleys normalized 8-point algorithm, the factorized 8-point algorithm is also completely linear. But unlike the normalized 8-point algorithm, the factorized 8-point algorithm does not need any pre-normalization step. Since every element of the measurement matrix in the factorized 8-point algorithm is a measurement datum or a constant, no amplification of measurement error is involved; the factorized 8-point algorithm can boost effectively the robustness of the estimation. Large numbers of experiments show that the factorized 8-point algorithm consistently outperforms the traditional 8-point algorithm. In addition, although the factorized 8-point algorithm is specially designed for fundamental matrix estimation, its basic principle can be generalized to other estimation problems in computer vision, such as camera projection matrix estimation, homography estimation, focus of expansion estimation, and trifocal tensor estimation.

A vessel active contour model for vascular segmentation.

This paper proposes a vessel active contour model based on local intensity weighting and a vessel vector field. Firstly, the energy function we define is evaluated along the evolving curve instead of all image points, and the function value at each point on the curve is based on the interior and exterior weighted means in a local neighborhood of the point, which is good for dealing with the intensity inhomogeneity. Secondly, a vascular vector field derived from a vesselness measure is employed to guide the contour to evolve along the vessel central skeleton into thin and weak vessels. Thirdly, an automatic initialization method that makes the model converge rapidly is developed, and it avoids repeated trails in conventional local region active contour models. Finally, a speed-up strategy is implemented by labeling the steadily evolved points, and it avoids the repeated computation of these points in the subsequent iterations. Experiments using synthetic and real vessel images validate the proposed model. Comparisons with the localized active contour model, local binary fitting model, and vascular active contour model show that the proposed model is more accurate, efficient, and suitable for extraction of the vessel tree from different medical images.

3D face reconstruction from skull by regression modeling in shape parameter spaces

Abstract Craniofacial reconstruction is to estimate a person׳s face model from the skull. It can be applied in many fields such as forensic medicine, face animation. In this article, a regression modeling based method for craniofacial reconstruction is proposed, in which a statistical shape model is built for skulls and faces, respectively, and the relationship between them is extracted in the shape parameter spaces through partial least squares regression (PLSR). Craniofacial reconstruction is realized by using the relationship and the face statistical shape model. To better represent craniofacial shape variations and boost the reconstruction, both the skull and face are divided into five corresponding feature regions, and a mapping from each skull region to the corresponding face region is established. For an unknown skull, the five face regions are obtained through the five mappings, and the face is recovered by stitching the five face regions. The attributes such as age and body mass index (BMI) can be added into the mappings to achieve the face reconstruction with different attributes. Compared with other statistical learning based methods in literature, the proposed method more directly and reasonably reflects the relationship that the face shape is determined by the skull and influenced by some attributes. In addition, the proposed method does not need to locate landmarks, whose quantity and accuracy can highly affect the reconstruction. Experimental results validate the proposed method.

Automatic Sex Determination of Skulls Based on a Statistical Shape Model

Sex determination from skeletons is an important research subject in forensic medicine. Previous skeletal sex assessments are through subjective visual analysis by anthropologists or metric analysis of sexually dimorphic features. In this work, we present an automatic sex determination method for 3D digital skulls, in which a statistical shape model for skulls is constructed, which projects the high-dimensional skull data into a low-dimensional shape space, and Fisher discriminant analysis is used to classify skulls in the shape space. This method combines the advantages of metrical and morphological methods. It is easy to use without professional qualification and tedious manual measurement. With a group of Chinese skulls including 127 males and 81 females, we choose 92 males and 58 females to establish the discriminant model and validate the model with the other skulls. The correct rate is 95.7% and 91.4% for females and males, respectively. Leave-one-out test also shows that the method has a high accuracy.

RANSAC based ellipse detection with application to catadioptric camera calibration

In this paper, a simple method for ellipse detection is proposed and applied in central catadioptric camera calibration. It consists of two phases. Firstly it locates ellipse center candidates using center symmetry of ellipses, and the detected edge points are grouped into several subsets according to the center candidates. Then all the ellipses are fitted by performing RANSAC for each subset. We also present an approach for calibrating a central catadioptric camera based on the bounding ellipse of the catadioptric image. Using the proposed ellipse detection method, we can easily detect the bounding ellipse. As a result, a simple self-calibration can be realized, which can be used in some applications where high accuracy of the calibration is not required. Experiments show the proposed method is effective.