Call for Participants – Biometric Recognition of the Hand in Uncontrolled Images

post by Gabrielle Hornshaw (2021 cohort)

Hello

My name is Gabrielle and I am a second-year PhD candidate at the Horizon Centre for Doctoral Training (CDT). I am looking for participants to contribute data to a new hand image dataset and earn a £10 Amazon voucher in return (first 50 respondents).

We are aiming to collect a wide variety of images of each participant’s hands, under different lighting conditions and performing different poses and gestures. To do this, we will be asking for 8 short videos (like these: https://youtu.be/Z5OPjIjQwi4) to be self-recorded and uploaded by participants. These recordings should take no more than 5 minutes in total but be done across a period of at least 1 day.

This data will be used to develop techniques for hand matching (deciding whether two hands are the same or not) with the aim to improve investigative processes in cases of abuse with perpetrator-recorded images, where hands can feature more often than faces. Automation of this analysis can improve the efficiency of investigations and reduce some of the human burden of viewing harmful material.

For more information on the project please see the information sheet below. For more detailed recording instructions, and to confirm your participation and submit your videos, please visit this survey:

https://forms.office.com/e/TnRStTT97z

If you do not have a University of Nottingham email address to complete the survey and would still like to participate, please email me directly at gabrielle.hornshaw@nottingham.ac.uk.

Please feel free to contact me with any further questions.

Best regards,
Gabrielle Hornshaw

Information Sheet