Edison Vein ID System

Edison Vein ID System

Low-Cost Intel-Edison-Powered User Authentication System that uses an Individual’s Unique Finger-vein Pattern (Presented at Intel ISEF '17)

Artificial Intelligence, Internet of Things

  • 0 Collaborators

  • 56 Followers

    Follow

Description

While biometrics have become a vital part of user authentication in technological platforms, they suffer from issues like fabrication, high costs, and vulnerability to physical damage that make them difficult to implement in low-cost scenarios. To meet this need, this project authenticates identities through inexpensive peripheral vein biometrics with the Edison Vein ID (EVID) system.

EVID consists of a low-cost NIR camera and low-power NIR LED array. The array emits ~850 nanometer light, which is absorbed by the finger veins’ deoxygenated blood and detected by the camera. Through the Intel Edison Compute Model, a computer vision algorithm captures a raw image, performs contrast-limited adaptive histogram equalization to increase the veins’ contrast, and reduces image noise through a Bilateral Gaussian Filter that preserves the veins’ edges. Finally, a binary threshold segments the image and extracts the unique vein structure, which is then registered as a biometric template.

A MATLAB normalized cross correlation algorithm computes a matching score [0-1] to compare an input image against a template for authentication. This process was repeated with all registered templates to test EVID’s ability to use input images to identify individuals. A 0.573 match score threshold for the verification and identification processes was determined based on False Acceptance Rates and False Rejection Rates according to Biometric Evaluation Standards.

EVID captured, processed, and stored peripheral vein images from 30+ samples, using these templates to authenticate and identify individuals from over 170 images. Future work includes using multi-modular biometrics to create the most secure identity verification system.

Gallery

Links

Intel ISEF 2nd Place in System Software Category

Medium atc

Anthony C. created project gRPC framework to support application to utilize the Cache Allocation Technology of Intel's RDT

Medium 2e327c44 2c22 4c02 aac1 0aa671714087

gRPC framework to support application to utilize the Cache Allocation Technology of Intel's RDT

Network Functions Virtualization ( NFV ) and Service Function Chaining ( SFC ) have moved from idea to POC to implementation stage . The challenge still remains to get bare metal performance from virtual machines . Resource Director Technology (RDT) from Intel is designed to bring in QoS to the virtual machine resources. gRPC from Google is a framework which could be used to design priority based services . This project integrates these technologies and creates a framework for more reliable and efficient services via gRPC enhanced with RDT.

Default user avatar 57012e2942

Ravi K. updated status

Default user avatar 57012e2942

Ravi K

Hi, I am very eager to learn AI technologies, I am master student at Governors State University,Chicago.

Medium headshot

Timothy P. created project MR. Configurator Tool

Medium a59775a0 6147 4390 92a9 8a2021fafea0

MR. Configurator Tool

This tool was designed to speed up calibration of your MR setup. This article explains how to use the tool and help you get the most out of your MR experiences. For VR users and streamers, making MR videos is a great way to show a different perspective to people who aren’t wearing a head-mounted display (HMD), while for VR developers, MR videos are a great way to create trailers and show a more comprehensive view of the VR experience.

Default user avatar 57012e2942

Basavaraj H. created project Apparent/Real Image Estimation using Deep Learning

Medium 1a3bd4ff 09be 4a4b 804b a9fc3e72fb38

Apparent/Real Image Estimation using Deep Learning

IMDB-WIKI age dataset processing and data loading into PyTorch model Fine tune VGG16 pre-trained on ImageNet using IMDB-WIKI database to estimate real age Train the fine-tuned model using LAP database to estimate apparent age Real age estimation is evaluated using MAE Used Ensemble 8 VGG16 nets to estimate the apparent age

Default user avatar 57012e2942

Makiko K. created project Smarter Wireless Power Transfer Technology

Medium e73a28d9 543a 4a6f afd2 ed3fdb0b5682

Smarter Wireless Power Transfer Technology

Wireless Power Transfer Technology enables people charging devices without a physical connection to the battery source. There are two main methods: Magnetic Inductance and Magnetic Resonance.

Magnetic Inductance charges devices within proximity. Magnetic Resonance, in turn, can charge further.

This project is an early proposal to evaluate how the different possible variables can impact the efficiency of the system, i.e., how fast can the device be charged subject to the distance, for example, material, object collision, room temperature, etc impact on the efficiency of the device.

Subject to these variables, the AI component of this project seeks to create a "smart wireless power charger", which reading through sensors the various conditions of the environment suggest the optimal distance for energy charging and placement without compromising the comfort of the user.

Default user avatar 57012e2942

Aashiq J. updated status

See More

No users to show at the moment.

Bigger 8 jk prc
Innovator
  • Projects 2
  • Followers 1

Gokula Krishnan Santhanam

Masters student @ ETH Zurich, Deep Learning Researcher working on both fundamentals and applications of Deep Learning technologies.

Limmatquai 122, 8001 Zürich, Switzerland

Bigger 0 0ge4aoo5gqsww1aiyxvgfv983wbdwxhsuknsuho 1mihwpdsjkv0zni6inwtojtdyon0zne6k oswmlcewjbjlo5f odwmparwjvuo9ltmuxwjsbrddr6srdsd
  • Projects 0
  • Followers 1

Mate Kisantal

Machine Learning oriented Aerospace Control Engineering student, with some experience in self-driving car control design.

Rotterdam, Netherlands

Default user avatar 57012e2942
  • Projects 0
  • Followers 1

perry obara

I'm always ready to learn.

Nairobi, Kenya

Bigger afro cartoon characters
  • Projects 0
  • Followers 1

Victor Kinoti

python programmer, telecommunications eng.

Nairobi, Kenya

Bigger 13096300 1739689082982412 1116910342765371095 n
  • Projects 1
  • Followers 0

Shuo Liu

I am studying electronic engineering at University of British Columbia (Okanagan Campus ), Canada.

Kelowna, BC, Canada

Bigger 0 pi8ofmmb66zvnu8utmyzoq2qcvlpfha79vgg0r a56d1f2d7rvggaj0tznw9num79vg4osycqi51nag298al4voaai5pnap2r8apsmglkjqsnqs5rx3jfiirni
  • Projects 0
  • Followers 0

Arslan Ahmed

261 Richmond Rd, Ottawa, ON K1Z 6X1, Canada

Bigger 0 xurcfxds fmqyz0 wg6rmuwwipl2jja80a6a0sdihiwujzy aofnahwacyqiym08ho6vhyhaaqverhhiofez40esqqvorhshsfezsxnd1yxirxpws sqwzuo0y
  • Projects 0
  • Followers 0

Akhilesh Rao

2360 SE Morrison St, Portland, OR 97214, USA

See More