scholarly journals 3D Palmprint Recognition Using Dempster-Shafer Fusion Theory

2015 ◽  
Vol 2015 ◽  
pp. 1-7 ◽  
Author(s):  
Jianyun Ni ◽  
Jing Luo ◽  
Wubin Liu

This paper proposed a novel 3D palmprint recognition algorithm by combining 3D palmprint features using D-S fusion theory. Firstly, the structured light imaging is used to acquire the 3D palmprint data. Secondly, two types of unique features, including mean curvature feature and Gaussian curvature feature, are extracted. Thirdly, the belief function of the mean curvature recognition and the Gaussian curvature recognition was assigned, respectively. Fourthly, the fusion belief function from the proposed method was determined by the Dempster-shafer (D-S) fusion theory. Finally, palmprint recognition was accomplished according to the classification criteria. A 3D palmprint database with 1000 range images from 100 individuals was established, on which extensive experiments were performed. The results show that the proposed method 3D palmprint recognition is much more robust to illumination variations and condition changes of palmprint than MCR and GCR. Meanwhile, by fusing mean curvature and Gaussian curvature feature, the experimental results are promising (the average equal error rate of 0.404%). In the future, imaging technique needs further improvement for a better recognition performance.

1985 ◽  
Vol 100 ◽  
pp. 135-143 ◽  
Author(s):  
Kazuyuki Enomoto

Let ϕ: M → RN be an isometric imbedding of a compact, connected surface M into a Euclidean space RN. ψ is said to be umbilical at a point p of M if all principal curvatures are equal for any normal direction. It is known that if the Euler characteristic of M is not zero and N = 3, then ψ is umbilical at some point on M. In this paper we study umbilical points of surfaces of higher codimension. In Theorem 1, we show that if M is homeomorphic to either a 2-sphere or a 2-dimensional projective space and if the normal connection of ψ is flat, then ψ is umbilical at some point on M. In Section 2, we consider a surface M whose Gaussian curvature is positive constant. If the surface is compact and N = 3, Liebmann’s theorem says that it must be a round sphere. However, if N ≥ 4, the surface is not rigid: For any isometric imbedding Φ of R3 into R4 Φ(S2(r)) is a compact surface of constant positive Gaussian curvature 1/r2. We use Theorem 1 to show that if the normal connection of ψ is flat and the length of the mean curvature vector of ψ is constant, then ψ(M) is a round sphere in some R3 ⊂ RN. When N = 4, our conditions on ψ is satisfied if the mean curvature vector is parallel with respect to the normal connection. Our theorem fails if the surface is not compact, while the corresponding theorem holds locally for a surface with parallel mean curvature vector (See Remark (i) in Section 3).


2006 ◽  
Vol 37 (3) ◽  
pp. 221-226 ◽  
Author(s):  
Dae Won Yoon

In this paper, we mainly investigate non developable ruled surface in a 3-dimensional Euclidean space satisfying the equation $K_{II} = KH$ along each ruling, where $K$ is the Gaussian curvature, $H$ is the mean curvature and $K_{II}$ is the second Gaussian curvature.


2020 ◽  
Author(s):  
Chuanzhang Wu ◽  
Baixiao Chen

Abstract We address the recognition problem of velocity gate pull-off (VGPO) jamming from the target echo signal for the velocity automatic tracking system. To this end, we resort to the discrete chirp-Fourier transform (DCFT) to jointly estimate the chirp rates and frequencies of the target and jamming signals. Firstly, the scaling characteristic of the DCFT algorithm is explored. Then we highlight the quantitative effect of the VGPO jamming signal by analyzing the jointly estimated result in each pulse. The effective effect indicates that the relationship between the estimated chirp rate and the pulse is similar to that between the frequency offset of VGPO jamming and the time when the estimated frequency is unchanged. Finally, by utilizing the analytical result and extracting the feature of the mean square to variance ratio (MSVR) of the normalized estimated chirp rate, the VGPO jamming can be recognized. Simulation results show that, for a time when the estimated frequency is unchanged, the MSVR of VGPO jamming decreases with the pulse numbers increases, and is always larger than that of a target which is steady. Comparing to other methods, the proposed method can correctly recognize the jamming signal with jamming-to-noise ratio (JNR) 5dB which shows better recognition performance, and is also effective within a shorter period.


2011 ◽  
Vol 2011 ◽  
pp. 1-11 ◽  
Author(s):  
Yılmaz Tunçer ◽  
Dae Won Yoon ◽  
Murat Kemal Karacan

We study tubular surfaces in Euclidean 3-space satisfying some equations in terms of the Gaussian curvature, the mean curvature, the second Gaussian curvature, and the second mean curvature. This paper is a completion of Weingarten and linear Weingarten tubular surfaces in Euclidean 3-space.


2021 ◽  
Vol 29 (1) ◽  
pp. 219-233
Author(s):  
Neslihan Ulucan ◽  
Mahmut Akyigit

Abstract In this paper, offset ruled surfaces in these spaces are defined by using the geometry of ruled surfaces in Euclidean space with density. The mean curvature and Gaussian curvature of these surfaces are studied. In addition, the relationships between the mean curvature and mean curvature with density, and the Gaussian curvature and the Gaussian curvature with density of the offset ruled surfaces in E 3 with density e z and e − x 2− y 2 are given.


Symmetry ◽  
2018 ◽  
Vol 10 (9) ◽  
pp. 398 ◽  
Author(s):  
Erhan Güler ◽  
Hasan Hacısalihoğlu ◽  
Young Kim

We study and examine the rotational hypersurface and its Gauss map in Euclidean four-space E 4 . We calculate the Gauss map, the mean curvature and the Gaussian curvature of the rotational hypersurface and obtain some results. Then, we introduce the third Laplace–Beltrami operator. Moreover, we calculate the third Laplace–Beltrami operator of the rotational hypersurface in E 4 . We also draw some figures of the rotational hypersurface.


Mathematics ◽  
2019 ◽  
Vol 7 (8) ◽  
pp. 703 ◽  
Author(s):  
Jinhua Qian ◽  
Mengfei Su ◽  
Xueshan Fu ◽  
Seoung Dal Jung

Canal surfaces are defined and divided into nine types in Minkowski 3-space E 1 3 , which are obtained as the envelope of a family of pseudospheres S 1 2 , pseudohyperbolic spheres H 0 2 , or lightlike cones Q 2 , whose centers lie on a space curve (resp. spacelike curve, timelike curve, or null curve). This paper focuses on canal surfaces foliated by pseudohyperbolic spheres H 0 2 along three kinds of space curves in E 1 3 . The geometric properties of such surfaces are presented by classifying the linear Weingarten canal surfaces, especially the relationship between the Gaussian curvature and the mean curvature of canal surfaces. Last but not least, two examples are shown to illustrate the construction of such surfaces.


Author(s):  
Sezai Kızıltuğ ◽  
Mustafa Dede ◽  
Cumali Ekici

In this paper, we define tubular surface by using a Darboux frame instead of a Frenet frame. Subsequently, we compute the Gaussian curvature and the mean curvature of the tubular surface with a Darboux frame. Moreover, we obtain some characterizations for special curves on this tubular surface in a Galilean 3-space.


Author(s):  
Erhan Güler

We consider rotational hypersurface in the four dimensional Euclidean space. We calculate the mean curvature and the Gaussian curvature, and some relations of the rotational hypersurface. Moreover, we define the third Laplace-Beltrami operator and apply it to the rotational hypersurface.


Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 52
Author(s):  
Tianyi Zhang ◽  
Abdallah El Ali ◽  
Chen Wang ◽  
Alan Hanjalic ◽  
Pablo Cesar

Recognizing user emotions while they watch short-form videos anytime and anywhere is essential for facilitating video content customization and personalization. However, most works either classify a single emotion per video stimuli, or are restricted to static, desktop environments. To address this, we propose a correlation-based emotion recognition algorithm (CorrNet) to recognize the valence and arousal (V-A) of each instance (fine-grained segment of signals) using only wearable, physiological signals (e.g., electrodermal activity, heart rate). CorrNet takes advantage of features both inside each instance (intra-modality features) and between different instances for the same video stimuli (correlation-based features). We first test our approach on an indoor-desktop affect dataset (CASE), and thereafter on an outdoor-mobile affect dataset (MERCA) which we collected using a smart wristband and wearable eyetracker. Results show that for subject-independent binary classification (high-low), CorrNet yields promising recognition accuracies: 76.37% and 74.03% for V-A on CASE, and 70.29% and 68.15% for V-A on MERCA. Our findings show: (1) instance segment lengths between 1–4 s result in highest recognition accuracies (2) accuracies between laboratory-grade and wearable sensors are comparable, even under low sampling rates (≤64 Hz) (3) large amounts of neutral V-A labels, an artifact of continuous affect annotation, result in varied recognition performance.


Sign in / Sign up

Export Citation Format

Share Document