Toward an Efficient Iris Recognition System on Embedded Devices

doi:10.1109/ACCESS.2023.3337033

Toward an Efficient Iris Recognition System on Embedded Devices

2023-01-01

2

OA

AI

Enrique López Droguett

C

Christoph Busch

DOI：10.1109/ACCESS.2023.3337033

Original

Original request for help

Save

Abstract

En 中文

Iris Recognition (IR) is one of the market's most reliable and accurate biometric systems. Today, it is challenging to build NearInfraRed (NIR) capturing devices under the premise of hardware price reduction. Commercial NIR sensors are protected from modification. The process of building a new device is not trivial because it is required to start from scratch with the process of capturing images with quality, calibrating operational distances, and building lightweight software such as eyes/iris detectors and segmentation sub-systems. In light of such challenges, this work aims to develop and implement iris recognition software in an embedding system and calibrate NIR in a contactless binocular setup. We evaluate and contrast speed versus performance obtained with two embedded computers and infrared cameras. Further, a lightweight segmenter sub-system called Unet_xxs is proposed, which can be used for iris semantic segmentation under restricted memory resources. The evaluations reveal that Unet_xxs reduces the number of parameters by 77% and duplicates the speed of state-of-the-art segmentation models with an EER drop smaller than 1% in Iris Recognition with 8.06 frame per second (fps) and Intersection Over Union (IOU) of 0.8382.

Keywords:

Embedding systems

iris sensor

NIR camera

hardware

Toward an Efficient Iris Recognition System on Embedded Devices

Abstract

Journal

Organization