3D Facial Similarity Measure Based on Geodesic Network and Curvatures

Abstract

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.

An automatic approach for classification and categorisation of lip morphological traits

“…The mean, max and min curvatures have been successfully utilised to classify philtrum morphology in the past [33]. The shape index and curvedness measures have been successfully applied in a variety of 3D face recognition applications [34–37]. In addition, the geodesic paths have been widely used in face recognition (FR) systems for faces with different poses and expressions (e.g., see [38–40]).…”

A Synthetic Feature Skull Descriptor for 3D Skull Similarity Measurement

“…Zhang et al [10] proposed a local shape descriptor Harmonic Wave Kernel Signature (HWKS) to measure 3D skull similarity by calculating the HWKS of the corresponding points of a pair of 3D skulls. Some works transformed the similarity of skulls into the similarity of its corresponding reconstructed 3D faces through craniofacial reconstruction [11][12][13][14]. e more similar the corresponding reconstructed faces are, the more similar the skulls are, but this similarity result is very dependent on the craniofacial reconstruction method.…”

“…Compute the SVD of WKDD wkdd svd(p) and wkdd svd(q) (12) Compute the CDF of WKDD wkdd cdf(p) and wkdd cdf(q) (13) SWKDD p ⟵ wkdd svd(p) * wkdd cdf(p) // computer the SWKDD p (14) SWKDD q ⟵ wkdd svd(q) * wkdd cdf(q) // computer the SWKDD q (15) Compute the skull similarity distance: D(skull p , skull q ) (16) end while ALGORITHM 1: SWKDD for skull similarity measure algorithm. 6 Mathematical Problems in Engineering subjective judgment.…”

A 3D morphometric perspective for facial gender analysis and classification using geodesic path curvature features

“…Zhao et al, in Ref. [23], used a geodesic network generated for each face with predetermined geodesics and iso-geodesics; they then computed the mean curvature, Gaussian curvature, shape index, and curvedness for each network point. The authors then utilised these features for automated 3D facial similarity measurement.…”