A method for 3D iris reconstruction from multiple 2D near-infrared images

Bastias, Diego; Perez, Claudio A.; Benalcazar, Daniel P.; Bowyer, Kevin W.

doi:10.1109/btas.2017.8272735

Cited by 12 publications

(22 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, a combination of lateral and frontal illumination showed slightly superior iris-recognition performance than that of frontal NIR illumination [14]. Our work builds upon these previous studies to create a robust and reliable method of 3D iris scanning that is not only useful for biometrics, but also is promising as a less expensive screening tool for Acute Angle Glaucoma, a disease currently diagnosed with an OCT [13]- [15].…”

Section: Demonstrated Thatmentioning

confidence: 67%

“…Previous work in this area includes the following. Bastias et al [13] reconstructed a 3D model of the iris from several NIR images in order to capture the depth information of the iris surface. A raspberry-pi V2 camera was used to capture NIR iris images along a circular arch [13].…”

Section: Demonstrated Thatmentioning

confidence: 99%

“…Bastias et al [13] reconstructed a 3D model of the iris from several NIR images in order to capture the depth information of the iris surface. A raspberry-pi V2 camera was used to capture NIR iris images along a circular arch [13]. Then, a photogrammetry algorithm was used to reconstruct a 3D model, thus creating a new method for human iris analysis [13].…”

Section: Demonstrated Thatmentioning

confidence: 99%

“…A raspberry-pi V2 camera was used to capture NIR iris images along a circular arch [13]. Then, a photogrammetry algorithm was used to reconstruct a 3D model, thus creating a new method for human iris analysis [13]. Issues with that method include the noisy nature of the camera, the resolution, and the plane correction needed to integrate all the images [13].…”

Section: Demonstrated Thatmentioning

confidence: 99%

“…Then, a photogrammetry algorithm was used to reconstruct a 3D model, thus creating a new method for human iris analysis [13]. Issues with that method include the noisy nature of the camera, the resolution, and the plane correction needed to integrate all the images [13]. In recent work, Benalcazar et al [14] used lateral visible-light (VL) illumination to capture highly textured images of the iris at a resolution of 16Mpx.…”

Section: Demonstrated Thatmentioning

confidence: 99%

See 4 more Smart Citations

A 3D Iris Scanner From Multiple 2D Visible Light Images

et al. 2019

Self Cite

View full text Add to dashboard Cite

The development of new methods for biometrics using the 3-D surface of the iris could be useful in various applications, such as reliable identity verification of people, when only segments of the iris are available, the study of how the iris code changes with pupil dilation, and studying acute angle glaucoma and its relation to the 3-D iris structure. The goal of this paper was to build a 3-D model of the iris surface from several 2-D iris images, adding depth information to the iris model. We developed a 3-D iris scanner, which reconstructs a 3-D mesh model of the iris surface from several 2-D visible light images. First, a smartphone camera captures visible light iris images from different angles in a controlled illumination environment. Then, a structure-from-motion algorithm reconstructs a point-cloud 3-D model. Finally, the best-fitting 3-D mesh model is obtained using the screened Poisson surface reconstruction technique. Our results include the reconstruction of the 3-D iris models of ten subjects. These models contain an average of 11,000 3-D points. The spatial resolution of our device was measured as 11 µm by scanning a 3-D pattern of known dimensions. The 3-D model of the iris is compared with the results from an optical coherence tomography (OCT) performed on one iris. Our results show that our new 3-D iris scanning method produces a model with potential applications in biometrics and ophthalmology. INDEX TERMS 3D iris reconstruction, 3D iris scanner, biometrics, iris recognition, structure from motion.

show abstract

Section: Demonstrated Thatmentioning

confidence: 67%

Section: Demonstrated Thatmentioning

confidence: 99%

Section: Demonstrated Thatmentioning

confidence: 99%

Section: Demonstrated Thatmentioning

confidence: 99%

Section: Demonstrated Thatmentioning

confidence: 99%

See 3 more Smart Citations

A 3D Iris Scanner From Multiple 2D Visible Light Images

et al. 2019

Self Cite

View full text Add to dashboard Cite

show abstract

3D iris model and reader for iris identification

Cohen

Sowmithran

2020

Concurrency and Computation

View full text Add to dashboard Cite

In the presence of eyelids and eyelashes movement, pupil dilation, poor lighting, blur due to movement during iris image acquisition, and factors that collectively cause distortion in the iris image, 2D image-based iris identification techniques become limited and might lead to iris misclassification due to the dependency on the image appearance (texture) on the possibly distorted image. To alleviate this problem, we introduce a new 3D iris model and reader based upon which iris identification is performed. Using a set of at least two 2D images taken from different views, a small set of reliable and corresponding salient fiducial points (corner points taken from crypts, corona, and serpentine rings of iris pattern) in the two images are extracted, from which a set of 3D iris salient points are obtained using triangulation. Corresponding salient points in the 2D images are found using the Random Sampling Consensus (RANSAC) algorithm, which is robust in identifying the inlier points that correspond to each other in different views of the iris. From this small and reliable salient point set, a denser (high-resolution) set of extra salient feature points is constructed at minimum cost using a loop subdivision method that yields corresponding extra salient points in the two images from which a high-resolution 3D iris model is obtained. The points associated with the 3D high-resolution model are tessellated to form a high-resolution triangular mesh with the appearance of a triangular patch in the image imported onto the iris personalized 3D model rendering it a 3D iris surface with appearance. This 3D model construction method allows for a 3D classification of a test iris to one of many possible irises stored in the database. The classification is based on a geometric 3D point cloud error. For cross-validation, the geometric-based classification can be augmented by considering a mean squared error (MSE) based on the appearance of corresponding points on the test and base models to further disambiguate between irises with close geometric error values.

show abstract

Iris Identification in 3D

Cohen

Sowmithran

2019

Image Analysis

View full text Add to dashboard Cite

A method for 3D iris reconstruction from multiple 2D near-infrared images

Cited by 12 publications

References 13 publications

A 3D Iris Scanner From Multiple 2D Visible Light Images

A 3D Iris Scanner From Multiple 2D Visible Light Images

3D iris model and reader for iris identification

Iris Identification in 3D

Contact Info

Product

Resources

About