Long range iris acquisition system for stationary and mobile subjects

Venugopalan, Shreyas; Prasad, Unni; Harun, Khalid; Neblett, Kyle; Toomey, Douglas W.; Heyman, Joseph L.; Savvides, Marios

doi:10.1109/ijcb.2011.6117484

Cited by 18 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since longer focal lens covers a smaller view angle, methods such as pan-tilt-zoom (PTZ) and multiple cameras are proposed to expand the FoV in iris imaging [23]. Venugopalan [22] uses an off-the-shelf PTZ camera with the 360 • pan and 180 • tilt capabilities to capture unconstrained iris image between 0.5 m and 1.6 m. Even the pantilt movement with an adjustable speed up to 450 • /second, the heavy and bulky optical form factors will jeopardize the performance of response time and angular resolution when it comes to distant object. Another intuitive solution to expand the view angle of iris image capture is by increasing the number of cameras as demonstrated in the well-known IOM system from Sarnoff in 2006 [14].…”

Section: Related Workmentioning

confidence: 99%

“…Following this idea, recent advances have been able to extend the depth range on the order of 100's of centimeter. Telescope imaging was introduced to achieve larger standoff distance on the order of 1's of meter in range distance iris recognition [22]. Bulky optical and focus control components, however, implies critical application issues.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

All-in-Focus Iris Camera With a Great Capture Volume

Zhang¹,

Shen²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

Imaging volume of an iris recognition system has been restricting the throughput and cooperation convenience in biometric applications. Numerous improvement trials are still impractical to supersede the dominant fixed-focus lens in stand-off iris recognition due to incremental performance increase and complicated optical design. In this study, we develop a novel all-in-focus iris imaging system using a focus-tunable lens and a 2D steering mirror to greatly extend capture volume by spatiotemporal multiplexing method. Our iris imaging depth of field extension system requires no mechanical motion and is capable to adjust the focal plane at extremely high speed. In addition, the motorized reflection mirror adaptively steers the light beam to extend the horizontal and vertical field of views in an active manner. The proposed all-in-focus iris camera increases the depth of field up to 3.9 m which is a factor of 37.5 compared with conventional long focal lens. We also experimentally demonstrate the capability of this 3D light beam steering imaging system in real-time multi-person iris refocusing using dynamic focal stacks and the potential of continuous iris recognition for moving participants.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

All-in-Focus Iris Camera With a Great Capture Volume

Zhang¹,

Shen²,

Wang³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The IAAD system has a long working distance, but it has a lower speed compared to other systems. Venugopalan's system has a number of 'burst' images [20]. Till now, these systems can not be applied in practice.…”

Section: "Stand Off" Iris Imagingmentioning

confidence: 99%

An Embedded Iris Image Acquisition Research

Chen

Qin

2017

IJEECS

View full text Add to dashboard Cite

In view of the limitation of traditional identification, it is easy to lose and copy keys, cards or ID cards, and it is easy to forget the password. Here, an embedded application system was designed based on the iris identification technology, the functions of gathering, inputing, and registering the iris information and identification can be realized. The system architecture was designed by using the embedded microprocessor of advanced RISC machines (ARM), which is used as the core. The iris sensor was used to gather the iris information, and the development of software was accomplished with the embedded OS Windows CE. The system can be used on the company entrance guard system, customs security of airport and criminal identification.

show abstract

“…At the same time, they require the users to be very close to the camera to extract high-resolution information. Consequently, the majority of the works in the literature that propose to use long-range (LR) iris images are focused on improving the acquisitions system using specific technologies [5,13,37,49].…”

Section: Introductionmentioning

confidence: 99%

Verification system based on long-range iris and Graph Siamese Neural Networks

Zola

Fernandez-Carrasco

Bruse

et al. 2022

2022 the 3rd European Symposium on Software Engineering

View full text Add to dashboard Cite

Biometric systems represent valid solutions in tasks like user authentication and verification. However, especially when physical biometrics are used, as is the case of iris recognition, they require specific hardware such as retina scanners, sensors, or HD cameras to achieve relevant results. In this sense, the majority of the prior studies propose to improve the acquisitions of long-range (LR) iris images using specific technologies, without trying to analyze their potential during the processing and classification phase. For this reason, in this work, we propose a novel approach that uses LR distance images taken from traditional cameras for implementing an iris verification system. More specifically, we present a novel methodology for converting LR iris images into graphs based on 1) converting the image in greyscale, 2) discretizing it and 3) performing a binarization, then, 4) graph nodes are defined by detecting the connected components in the binarized image, as well as their 5) features and 6) their edges. Once these graphs are extracted, they are used as input in Graph Siamese Neural Networks (GSNN) to predict whether two graphs belong to the same person. In this study, three experiments are carried out. In the first one, we evaluate how the number of nodes in the generated graphs affects the verification system. In the second one, specific filters are used to enhance the spectral information of the LR images, changing their graph definition. Finally, in the third one, we evaluate how the number of users impacts the verification system performance.Results show that a small number of nodes or using too many nodes worsens the model performance, whereas it is possible to improve the F1-score of the GSNN using spectral enhanced images (up to 77%). Furthermore, increasing the number of users shows a small deterioration in the GSNNs performance. These results demonstrate the suitability of this approach, encouraging the community to explore the usage of traditional LR distance images and graph application in biometric systems. CCS Concepts: • Theory of computation → Graph algorithms analysis; • Security and privacy → Biometrics; • Computing methodologies → Spectral methods; Image processing.

show abstract

Long range iris acquisition system for stationary and mobile subjects

Cited by 18 publications

References 8 publications

All-in-Focus Iris Camera With a Great Capture Volume

All-in-Focus Iris Camera With a Great Capture Volume

An Embedded Iris Image Acquisition Research

Verification system based on long-range iris and Graph Siamese Neural Networks

Contact Info

Product

Resources

About