Taorui Jia

Special Section on CAD/Graphics 2013: Multi-branched cerebrovascular segmentation based on phase-field and likelihood model

Angiograms have been extensively used by neurosurgeons for vascular and non-vascular pathology. Indeed, examining the cerebral vessel network is helpful in revealing arteriosclerosis, diabetes, hypertension, cerebrovascular diseases and strokes. Thus, accurate segmentation of blood vessels in the brain is of major importance to radiologists. Many algorithms have been proposed for blood vessel segmentation. Although they work well for segmenting major parts of vessels, these techniques cannot handle challenging problems including (a) segmentation of thinner blood vessels due to low contrast around thin blood vessels; (b) inhomogeneous intensities, which lead to inaccurate segmentation. In order to tackle these challenges, we developed a new Allen Cahn (AC) equation and likelihood model to segment blood vessels in angiograms. Its level set formulation combines length, region-based and regularization terms. The length term is represented by the AC equation with a double well potential. The region-based term combines both local and global statistical information, where the local part deals with the intensity inhomogeneity, and the global part solves the low contrast problem. Finally, the regularization term ensures the stability of contour evolution. Experimental results show that the proposed method is both efficient and robust, and is able to segment inhomogeneous images with an arbitrary initial contour. It outperforms other methods in detecting finer detail.

3D Facial Similarity Measure Based on Geodesic Network and Curvatures

Automated 3D facial similarity measure is a challenging and valuable research topic in anthropology and computer graphics. It is widely used in various fields, such as criminal investigation, kinship confirmation, and face recognition. This paper proposes a 3D facial similarity measure method based on a combination of geodesic and curvature features. Firstly, a geodesic network is generated for each face with geodesics and iso-geodesics determined and these network points are adopted as the correspondence across face models. Then, four metrics associated with curvatures, that is, the mean curvature, Gaussian curvature, shape index, and curvedness, are computed for each network point by using a weighted average of its neighborhood points. Finally, correlation coefficients according to these metrics are computed, respectively, as the similarity measures between two 3D face models. Experiments of different persons’ 3D facial models and different 3D facial models of the same person are implemented and compared with a subjective face similarity study. The results show that the geodesic network plays an important role in 3D facial similarity measure. The similarity measure defined by shape index is consistent with human’s subjective evaluation basically, and it can measure the 3D face similarity more objectively than the other indices.

Novel correspondence-based approach for consistent human skeleton extraction

This paper presents a novel base-points-driven shape correspondence (BSC) approach to extract skeletons of articulated objects from 3D mesh shapes. The skeleton extraction based on BSC approach is more accurate than the traditional direct skeleton extraction methods. Since 3D shapes provide more geometric information, BSC offers the consistent information between the source shape and the target shapes. In this paper, we first extract the skeleton from a template shape such as the source shape automatically. Then, the skeletons of the target shapes of different poses are generated based on the correspondence relationship with source shape. The accuracy of the proposed method is demonstrated by presenting a comprehensive performance evaluation on multiple benchmark datasets. The results of the proposed approach can be applied to various applications such as skeleton-driven animation, shape segmentation and human motion analysis.

Craniofacial Reconstruction Evaluation by Geodesic Network

Craniofacial reconstruction is to estimate an individuals face model from its skull. It has a widespread application in forensic medicine, archeology, medical cosmetic surgery, and so forth. However, little attention is paid to the evaluation of craniofacial reconstruction. This paper proposes an objective method to evaluate globally and locally the reconstructed craniofacial faces based on the geodesic network. Firstly, the geodesic networks of the reconstructed craniofacial face and the original face are built, respectively, by geodesics and isogeodesics, whose intersections are network vertices. Then, the absolute value of the correlation coefficient of the features of all corresponding geodesic network vertices between two models is taken as the holistic similarity, where the weighted average of the shape index values in a neighborhood is defined as the feature of each network vertex. Moreover, the geodesic network vertices of each model are divided into six subareas, that is, forehead, eyes, nose, mouth, cheeks, and chin, and the local similarity is measured for each subarea. Experiments using 100 pairs of reconstructed craniofacial faces and their corresponding original faces show that the evaluation by our method is roughly consistent with the subjective evaluation derived from thirty-five persons in five groups.

Isometric Shape Matching Based on the Geodesic Structure and Minimum Cost Flow

Non-rigid 3D shape correspondence is a fundamental and challenging problem. Isometric correspondence is an important topic because of its wide applications. But it is a NP hard problem if you detect the mapping directly. In this paper, we propose a novel approach to find the correspondence between two (nearly) isometric shapes. Our method is based on the geodesic structure of the shape and minimum cost flow. Firstly, several pre-computed base vertices are initialized for embedding the shapes into Euclidian space, which is constructed by the geodesic distances. Then we construct a network flow with the points of the two shapes and another two virtual points, source point and sink point. The arcs of the network flow are the edges between each point on two shapes. And the L2 distances in the k dimensional Euclidian embedding space are taken as the arc costs and a capacity value is added on each point in the above network flow. At last we solve the correspondence problem as a minimum cost max flow problem (MCFP) with shortest path faster algorithm (SPFA). Experiments show that our method is accurate and efficient.

Scale-Invariant Heat Kernel Mapping

In shape analysis, scaling factors have a great influence on the results of non-rigid shape retrieval and comparison. In order to eliminate the scale ambiguity in shape acquisition and other cases, a method with scale-invariant property is required for shape analysis. The mapping method previously proposed only preserves geodesic distances between pair wise points. In this paper, a Scale-invariant Heat Kernel Mapping (SIHKM) method is introduced, which bases on the Scale-invariant Heat Kernel (SIHK) that handles various types of 3D shapes with different kinds of scaling transformations. SIHK is the generalization of the Heat Kernel and related to the heat diffusion behavior on shape. By using the SIHK, we retrieve intrinsic information from the scaled shapes while ignoring the impact of their scaling. SIHKM method maintains the heat kernel between two corresponding points on the shape with scaling deformations, including scaling transformation only, isometric deformation and scaling, and local scaling on shapes. The proof of the theory and experiments are given in this work. The experiments are performed on the TOSCA dataset, which show that our proposed method achieves good robustness and effectiveness to scaled shape analysis.

Isometric Shape Correspondence Based on the Geodesic Structure

Non-rigid 3D shape correspondence is a fundamental and challenging problem. Isometric correspondence is an important topic because of its wide applications. But it is a NP hard problem if detecting the mapping directly. In this paper, we propose a novel approach to find the correspondence between two nearly isometric shapes. Our method is based on the geodesic structure of the shape and minimum cost flow. Firstly, several pre-computed base vertices are initialized for embedding the shapes into Euclidian space, which is constructed by the geodesic distances. Then we select a serials of sample point sets with FPS. After that, we construct some network flows separately with the level point sets of the two shapes and another two virtual points, source point and sink point. The arcs of the network flow are the edges between each point on two shapes. And the

A Scale-Invariant Diffusion Distance for Non-rigid Shape Analysis

L_2