US Super Recognizers Wanted For New Game Show

“You Bet Your Life” with Jay Leno, is a new comedy game show coming to Fox TV this fall.   The producers have recently become interested in reaching out to people with specifically interesting jobs to invite to apply to be contestants on the show. One of the jobs they mentioned was finding someone who is a super recognizer

Chosen contestants will compete to win cash and prizes by answering trivia questions. Filming will take place in Los Angeles between July and October, but contestants will only be needed for approximately 24-48 hours.

If you are a US Super Recognizer and wish to be involved, contact the Association or Mike Neville at mike.neville@superrecognisersinternational.com

Improvements to Glasgow Face Matching Test

In the attached article, Dr David White, from the University of New South Wales, describes how he has improved this much used test.

Abstract from the paper:

We present an expanded version of a widely used measure of unfamiliar face matching ability, the Glasgow Face Matching Test (GFMT). The GFMT2 is created using the same source database as the original test but makes five key improvements. First, the test items include variation in head angle, pose, expression and subject-to-camera distance, making the new test more difficult and more representative of challenges in everyday face identification tasks. Second, short and long versions of the test each contain two forms that are calibrated to be of equal difficulty, allowing repeat tests to be performed to examine effects of training interventions. Third, the short-form tests contain no repeating face identities, thereby removing any confounding effects of familiarity that may have been present in the original test. Fourth, separate short versions are created to target exceptionally high performing or exceptionally low performing individuals using established psychometric principles. Fifth, all tests are implemented in an executable program, allowing them to be administered automatically. All tests are available free for scientific use via www.gfmt2.org.

GFMT2: A psychometric measure of face matching ability (springer.com)

Police Use of Facial Recognition Deemed Unlawful in Canada

The Canadian federal police force broke the law when it used controversial facial recognition software, the country's Office of the Privacy Commissioner's (OPC) found in a report released on Thursday. This related to the Royal Canadian Mounted Police and their use of Clearview AI. See the full report on the link below. This once again emphasises the need for HUMAN super recognisers to be selected and used by law enforcement agencies across the world.

Canada police broke law with facial recognition software, regulator finds (msn.com)

Super Recogniser Brings Killer to Justice

A Super Recogniser from the English city of Bradford helped to bring a child killer and rapist to justice in Pakistan.

Read the Simone Malik’s assistance to the police at this link:

'Super recogniser': Bradford artist - who has an above-average ability to remember faces - uses her special skill to fight crime | Bradford Telegraph and Argus (thetelegraphandargus.co.uk)

Partnership with Artificial Intelligence Company - IREX

The Surveillance Camera Commissioner’s Code of Practice in UK demands that there must be “human intervention” if computerised facial recognition software or artificial intelligence are used to identify suspects for crime. The Association have long held the view that human Super Recognisers are the RIGHT people to perform that role and check identifications from machines.

IREX are a global company offering video analytics to Smart Cities and they are committed to ensuring ethical use of their systems. IREX will now offer Super Recognisers International selection and training to those purchasing their products. Daniel Eborall, their Global Business Development Director stated,

“We see a huge potential in a strategic collaboration with Super Recognisers International that could lead to further ethical standards in facial recognition practices for end users. IREX is determined to be an industry leader for ethical standards and best practices for AI surveillance and believe our partnership will help end-users learn and adhere to those standards.”

This is a major step forward for Super Recognisers and the use of artificial intelligence to fight crime. See the IREX website for more on this company:

IREX Smart Cities | Public Safety | Video Analytics | AI

Thames Valley Police - Super Recogniser Expansion

Thames Valley Police are at the forefront of the selection and use of Super Recognisers in the UK. The force covers the counties of Berkshire, Buckinghamshire and Oxfordshire. The force intends to run four courses over the next two years to enhance their use of Super Recognisers to target all types of crime. The Association praises their commitment to innovation.

On-line Course May 2021 - A Great Success!

The Super Recogniser on-line course held between 25th and 27th May proved to be a great success with students from across the world.  The nations represented included the UK, US, Canada, Brazil, France, Germany, Hungary and Lithuania.  The feedback noted the excellent presentations by Prof. Josh Davis, Peter Jupp (behavioural detection), Dale Nufer (evidential description of faces), Kelly Hearsey (Chief Operating Officer) and Pat O’Riordan (police super recogniser).  The fast-moving final exercise was also enjoyed by the course – a high pressure matching operation with a realistic scenario based on an actual police investigation.

Abison, an eye (very apt for a Super Recogniser!)  from England noted, “It’s great to be part of the super recognisers. It is very apparent that Mike and the University of Greenwich have done a thorough and amazing job to build up the organisation. The work that they are doing is critical to security of the nation and I look forward to playing my part.”

Paola from Germany said, "I want to thank Mike Neville for his great engagement during the course. Each of the lecturers was very approachable. All of the contents were captivating and, due to many images and videos shown, very lively. The subject "Super-Recognisers" was illuminated from all sides. I had an intense time and feel very enriched."

The next on-line courses will be held between 7th to 9th September and 30th November to 2nd December.   More details on the Courses page.

Interactive Use of Images Improve Super Recogniser Performance

This article shows that the ability to view images from different angles improves identification. This is especially applicable to Super Recognisers.

Police Professional | Interactive images could cut errors in facial recognition, study suggests

This was taken from this academic article:

Smith, H. M. J., Andrews, S., Baguley, T., Colloff, M. F., Davis, J. P., White, D., Rockey, J. C., & Flowe, H. D. (2021). Performance of typical and superior face recognisers on a novel interactive face matching procedure. British Journal of Psychology, DOI: 10.1111/bjop.12499 (https://bpspsychub.onlinelibrary.wiley.com/doi/full/10.1111/bjop.12499)

The conclusion from the academic paper:

In this paper, we tested typical and superior recognizers using a novel interactive face matching procedure. In contrast to standard (i.e., static frontal) one-to-one face matching tasks, the procedure provides fluid orientation information, and the opportunity to interact with the comparison facial image by manoeuvring it into different orientations. This easy-to-implement procedure has a range of applied benefits: It optimizes the performance of both typical and superior recognizers, and has the potential to highlight both similarities and differences between facial images. The results support the hypothesis that typical and superior face recognizers process faces in qualitatively similar ways: Reliance on pictorial encoding when viewing static images helps to explain the benefit of the interactive procedure.

Project Flin Flon - For Licentiates

This is an opportunity to practice your skills on a real project.

Super Recognisers International were contacted earlier this year by a member of Flin Flon’s Heritage Project with a proposal for a collaborative project.

Please note: This is a voluntary project open only to Licentiate Members of the Association of Super Recognisers who have completed the SRI Training Course and qualified as a Super Recogniser or Face Matcher.

What is Flin Flon? Flin Flon is a small mining town in Canada on the Manitoba/Saskatchewan border. The town, founded in 1927, was once a thriving place with one of the richest mines in Canada, employing 15,000 people. The mine is slowly winding down and is expected to close in 2022. Our contact, Doug Evans, grew up in the town from the age of 5 weeks old when the accommodation comprised of only log cabins and tents. He is a member of the Flin Flon Heritage Project and curates much of its photographic collection. For more information on the town of Flin Flon please see:

https://en.wikipedia.org/wiki/Flin_Flon

Flin Flon Heritage Project website:

http://flinflonheritageproject.com

The Collaborative Project - Background Information Flin Flon had an huge archive of old photos that was informal and without organisation. Flin Flon town volunteers went through the collection, documenting the photos. Sadly a flood destroyed their index, though the photos were saved. There is a large number of images of important people who established the town, many with no names attached and their identity unconfirmed. The Heritage group decided to make a digital archive for the web. People began sending in shoeboxes of old photos. The collection now contains approximately 50,000 photos. A club was formed for those who worked in the mine around 1927, the “27 Club”. Most photos we have were taken around 15-20 years after the initial activity in the mine and the project would like to centre on these characters. We have been given images from around 1926 onwards, when the mine was being developed. Some of these images depict a time when the only access to the mine was by canoe or steamboat!

How to get involved We have two sets of images. Set 1 depicts members of the founding members of Flin Flon, the “1927 Club”. Names are written either on the image or the reverse of the photo. These give us our KNOWN images. Set 2 is a selection of photographs depicting UNNAMED people from the early years of the mine. Your task is to study both sets of images and if possible, identify some of the unknown (unnamed) persons. There is no right or wrong, your submission is subjective and purely your own opinion. I will collate the results and submit them to the Flin Flon Heritage Project once all findings are received. How to present your report I would like you to present your report in any way you feel works well and are comfortable with. Your findings should be presented clearly and professionally. I will be looking for accuracy and attention to detail. The reader should be able to understand your report quickly and easily. An instinctive reaction is not enough for an identification, you must present your reasoning behind the identification. Your work will give me an insight into how you approach a task. I will not give guidance as to the exact way you present your report, I would like to see your own interpretation without my influence! If you would like to be involved in this project, please email me at:

kelly.hearsey@superrecognisersinternational.com

and I will send you all you need to get started. This is a fabulous opportunity to practice your skills and demonstrate your ability. I hope you will find this an enjoyable project to be involved in and look forward to hearing from you. Closing date to submit your findings is 20th June 2021.

New UK Surveillance Camera Commissioner - Quizzed by Association CEO

The new SCC, Fraser Sampson, appeared on a webinar for the CCTV User Group. Our CEO, Mike Neville, was able to ask questions regarding measuring the police use of CCTV. This, no doubt, would increase the use of images to solve crime and would result in more Super Recognisers being utilised.

Watch our Snapshot Webinar: New Surveillance Camera Commissioner talks CCTV, regulation and funding (cctvusergroup.com)