Limits...
An Effective 3D Ear Acquisition System.

Liu Y, Lu G, Zhang D - PLoS ONE (2015)

Bottom Line: It can be easily captured from a distance without a fully cooperative subject.Also, the ear has a relatively stable structure that does not change much with the age and facial expressions.In this paper, we present a novel method of 3D ear acquisition system by using triangulation imaging principle, and the experiment results show that this design is efficient and can be used for ear recognition.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China.

ABSTRACT
The human ear is a new feature in biometrics that has several merits over the more common face, fingerprint and iris biometrics. It can be easily captured from a distance without a fully cooperative subject. Also, the ear has a relatively stable structure that does not change much with the age and facial expressions. In this paper, we present a novel method of 3D ear acquisition system by using triangulation imaging principle, and the experiment results show that this design is efficient and can be used for ear recognition.

No MeSH data available.


Contour maps of different ear samples (the top row is contour maps drawn from one ear, the bottom row is contour maps drawn from another ear).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4464888&req=5

pone.0129439.g010: Contour maps of different ear samples (the top row is contour maps drawn from one ear, the bottom row is contour maps drawn from another ear).

Mentions: In addition, we extract the contour maps of 3D ears' samples to illustrate their geometrical shapes. As shown in Fig 10, the six samples were collected at different sessions from two different ears. The top three contour maps are extracted from one ear, the bottom three contour maps are extracted from another ear. From the contour maps, it can be seen intuitively that the geometrical shapes of 3D ear samples from the same object are stable; on the other hand, for different ears they are distinguishable. Therefore, we can safely assume that the 3D ears' samples captured by our acquisition system would be suitable for 3D ear recognition. In order to corroborating the assumption, a 3D ear database was established by using the developed 3D ear acquisition system. The database contains 2000 samples from 500 volunteers, including 341 males and 159 females. We collected the 3D ears on two separate occasions, at an interval of around one month. On each occasion, the subject was asked to provide two samples. Then the modified ICP alignment is used for samples matching, and the statistical results are illustrated in the form of genuine and impostor distribution curves, as well as the receiver operating characteristic (ROC) curve.


An Effective 3D Ear Acquisition System.

Liu Y, Lu G, Zhang D - PLoS ONE (2015)

Contour maps of different ear samples (the top row is contour maps drawn from one ear, the bottom row is contour maps drawn from another ear).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4464888&req=5

pone.0129439.g010: Contour maps of different ear samples (the top row is contour maps drawn from one ear, the bottom row is contour maps drawn from another ear).
Mentions: In addition, we extract the contour maps of 3D ears' samples to illustrate their geometrical shapes. As shown in Fig 10, the six samples were collected at different sessions from two different ears. The top three contour maps are extracted from one ear, the bottom three contour maps are extracted from another ear. From the contour maps, it can be seen intuitively that the geometrical shapes of 3D ear samples from the same object are stable; on the other hand, for different ears they are distinguishable. Therefore, we can safely assume that the 3D ears' samples captured by our acquisition system would be suitable for 3D ear recognition. In order to corroborating the assumption, a 3D ear database was established by using the developed 3D ear acquisition system. The database contains 2000 samples from 500 volunteers, including 341 males and 159 females. We collected the 3D ears on two separate occasions, at an interval of around one month. On each occasion, the subject was asked to provide two samples. Then the modified ICP alignment is used for samples matching, and the statistical results are illustrated in the form of genuine and impostor distribution curves, as well as the receiver operating characteristic (ROC) curve.

Bottom Line: It can be easily captured from a distance without a fully cooperative subject.Also, the ear has a relatively stable structure that does not change much with the age and facial expressions.In this paper, we present a novel method of 3D ear acquisition system by using triangulation imaging principle, and the experiment results show that this design is efficient and can be used for ear recognition.

View Article: PubMed Central - PubMed

Affiliation: Department of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, China.

ABSTRACT
The human ear is a new feature in biometrics that has several merits over the more common face, fingerprint and iris biometrics. It can be easily captured from a distance without a fully cooperative subject. Also, the ear has a relatively stable structure that does not change much with the age and facial expressions. In this paper, we present a novel method of 3D ear acquisition system by using triangulation imaging principle, and the experiment results show that this design is efficient and can be used for ear recognition.

No MeSH data available.