Face Forensics Announces Unique Disaster Victim Identification Suite
Vancouver, Canada – March 21, 2023 Face Forensics has released a new and unique version of its f2 recognition software specifically designed to help identify the bodies of deceased people from their faces, even if the eyes are closed and the face is significantly damaged, together with other markings such as tattoos.
Developed originally at the request of an international aid agency to identify the bodies of migrants who had drowned in the Mediterranean trying to get to Europe, the Disaster Victim Identification suite combines Face Forensics’ underlying corpse identification and tattoo recognition technologies.
Closed eyes are an issue because face recognition systems place much value on the eye area due to the clear variations, sharp edges, and high contrast of the features there. If both eyeballs are not visible the recognition process will not work.
The design of f2 overcomes this by providing the ability to crop out an undamaged part of a face, place it over a generic facial template and match this against the same area on full faces in a database, making it possible to work with closed eyes and faces that have been damaged.
When a body is found an investigator will take several photos of their face. Each of the shots will be cropped if necessary and copied into the search window where they will be automatically encoded and matched against the encodings of all the faces in the database. The top matches will then be displayed, initially as thumbnail images, for investigators to confirm visually.
The system will automatically connect to and enroll images in existing external databases, as well as import and enroll images provided by relatives. Multiple filters are available to narrow down the possible matches before face matching is applied.
The Disaster Victim Identification Suite is available as application, as a .NET SDK, and as a web service. It can search databases across multiple machines on a VPN, under appropriate controls. f2 Tattoo Recognition is available for evaluation at no charge to government agencies and suppliers to them. Full online assistance is provided. A short video can be seen at
f2 Tattoo Recognition
Face Forensics Announces New Scene/Object Recognition Technology, and Major Upgrade to its Face & Tattoo Recognition Capabilities
VANCOUVER, Canada – April 19, 2022 Face Forensics has extended its image matching capabilities to finding any object in an existing database containing images, regardless of format, size, and even if only partially visible. Using an enhanced version of its crime scene matching technology together with image enhancement, objects as large as buildings and as small as tableware can be matched. Coupled with enhancements to its tattoo and face recognition algorithms, the f2 Image Recognition Suite is an indispensable addition to any agency’s forensic capabilities. The system includes automatic analysis and enrollment of the pattern and other characteristics of images in a database, automatic batch import and enrollment of images in a folder, and automatic detection and enrollment of new images that are added to external databases. Images, and the objects in them, can be of anything solid with distinguishing features, e.g. vehicles, flags, logos, furniture, etc. The software can be
used stand-alone/networked or integrated into existing systems, and there is no limit to the size of the databases to be searched. Large database searches can be split across multiple processors and across a VPN. The f2 Image Recognition Suite and the modules in it are available as a stand-alone/networked application, as a .NET SDK, and as a web service. The suite is available for evaluation at no charge by government agencies and suppliers to them. Full online assistance is available.
About Face Forensics Inc.
The principals of Face Forensics have been directly involved in the development of face recognition technology for over 15 years, and have already developed one of the most successful face recognition systems in North America. This has been installed in numerous police forces and achieved notable successes. The team have also been responsible for the development of one of the largest image processing systems of its type anywhere – the UK’s ChildBase system. The f2 team comprises professionals with many years’ experience in imaging technologies and applications, mathematics, biometrics, information technology, and international business.
Enquiries: Contact: info@faceforensics.com
Face Forensics Announces Major Upgrade to its Advanced Tattoo Recognition Technology
VANCOUVER Canada – October 6, 2020 Face Forensics has significantly enhanced the tattoo encoding and matching performance of its f2 advanced tattoo algorithms, enabling images to be matched against an existing database more accurately and much faster than previously. Developed in response to demand from the law enforcement community, f2 has the ability to identify a tattoo even if it’s partially obscured, for example by clothing. The system includes automatic enrollment of existing tattoos in a database, automatic batch import and enrollment of tattoos in a folder, and automatic detection and encoding of new tattoos that are added to external databases. It can be used stand-alone or integrated into existing biometric-based systems, and there is no practical limit to the size of the databases to be searched. Large database searches can be split across multiple processors. The tattoo matching capability is available as a stand-alone/networked application, as a .NET SDK, and as
a web service. f2 Tattoo Recognition is available for evaluation at no charge by government agencies and suppliers to them.
Face Forensics Inc. Announces Unique Capability to Identify Dead Bodies
VANCOUVER – March 11, 2019 Face Forensics Inc, developers of the AI-based f2 face recognition technology, has announced a significant new module – the ability to identify the faces of dead bodies, i.e. with eyes that are closed, and including where the face is significantly damaged. Closed eyes are an issue because face recognition systems place high value on the area around the eyes due to the clear edges and high contrast of the features there. If the eyeballs are not visible as anchor points the recognition performance can be severely degraded or simply not work at all. Called Corpse-ID, the new module builds on Face Forensics’ unique partial face recognition capability to enable an investigator to estimate the eye center locations optimally. This capability also allows an image of an undamaged part of a face, for example one side or just the eyes, to be matched against the same area on previously enrolled full faces. Corpse-ID adds another unique capability to Face
Forensics’ f2 Image Recognition Suite, which also includes tattoo recognition (also with partials) and scene recognition.
Face Forensics Inc. Announces 300% Face/Tattoo Enroll Speed Increase
VANCOUVER – May 21, 2017 Vancouver-based Face Forensics Inc, developers of the highly-advanced f2 face and tattoo recognition technology, has announced a substantial increase in its image enrollment speed. While f2 always worked in 64-bit on the server side, this new release extends 64-bit to the client side as well. This together with other major enhancements has more than tripled the image enrollment speed. f2’s use of modular hardware architecture plus its full use of multithreading and multiple cores and processors, results in search speeds of faces and tattoos that can be in the many millions of images per second, and delivers scalability from one-to-one matching for access control through to one-to-many matches for the largest databases.
About Face Forensics Inc.
The principals of Face Forensics have been directly involved in the development of face recognition technology for over 15 years, and have already developed one of the most successful face recognition systems in North America. This has been installed in numerous police forces and achieved notable successes. The team have also been responsible for the development of one of the largest image processing systems of its type anywhere – the UK’s ChildBase system. The f2 team comprises professionals with many years’ experience in imaging technologies and applications, mathematics, biometrics, information technology, and international business.
Enquiries: Contact:
info@faceforensics.com
Face Forensics Announces New Advanced Identity Verification Capability
VANCOUVER, Canada – October 4, 2016 Face Forensics’ advanced face recognition technology can be used in both identification and identity verification applications. For its primary purpose is to verify that the person presenting an ID card is the person to whom it was issued, and thus prevent unauthorized individuals from entering the building, and one employee entering on behalf of another. When an individual presents their personal ID card at an entry point, f2 will immediately determine if the presenter’s face matches the face of the owner of the card. As the individual walks through the entrance of a building towards the camera, the employee’s ID card number is read, either through a card reader or by reading a chip on the card, validated, and used to retrieve the individual’s photo from the employee database. In parallel a video camera will automatically take several shots of the individual’s face. Each shot will be encoded, with each encode array compared with ones for
this individual in the database. If the match% for any face exceeds a user-defined acceptance threshold the two faces are deemed to match and the person is accepted to be who they claim to be. At this point the employee will be permitted to enter the building. If there’s no match they won’t be allowed to enter and security will take them to one side for further checking. If they refuse to cooperate f2 can be used in identification mode to compare the camera image with the faces of all the employees in the database in a one-to-many match to determine if the individual is an employee, ex-employee, or an unknown person. The system will also detect buddy-punching, where one employee tries to enter on behalf of another, and identify both of them. In all cases the application can keep a time-stamped record of the images as well as details of the specific location that the match took place, for future investigation if required. Where a face is intentionally partially obscured, e.g. by the
person’s hand, f2’s unique partial face recognition capability can be used to help identify the individual from the features that are visible.
Example of 1:1 Match
Law & Order Magazine Features Face Forensics Tattoo Recognition as Cover Article
VANCOUVER, Canada – July 28, 2016 The cover article in the June 2016 edition of Law & Order magazine was an article on the company’s new and unique tattoo recognition capability written by Face Forensics CEO Iain Drummond. Requested by the magazine, the article focused particularly on its use in a police environment. The article can be seen at:
http://www.hendonpub.com/resources/article_archive/results/details?id=5807 Tattoo recognition is a specific application of Face Forensics’ image recognition technology, which was initially applied to face recognition and our partial face recognition capability, which is also unique. The software can handle heavily-cropped tattoos and includes optional color and text filters to reduce the number of possible matches when dealing with large databases. Tattoo recognition is a particularly challenging task as unlike faces a tattoo can be of virtually anything, so there are no obvious anchor points around which to determine the relative position of other features. Solving this and other associated challenges has resulted in f2 being the only generally-available tattoo recognition system in the world..
Face Forensics Announces World’s First Generally-Available Tattoo Recognition
System
VANCOUVER, Canada – October 24, 2015 Face Forensics has significantly expanded
its f2 face recognition technology by adding the capability to match images of
tattoos against databases containing them. It’s been developed in response to
demand from the law enforcement community, who have asked for the ability to
identify a tattoo or other image, even although it’s been cropped, reformatted,
or is just similar. Although this capability is a new module within the Face
Forensics Recognition Suite it is fully integrated so that it can connect
directly back to the face and name of the owner of any scar, mark, or tattoo.
The system includes automatic enrollment of existing tattoo images, and
automatic detection and encoding of new tattoos that are added to external
databases. Face Forensics accesses these images in read-only mode so data
integrity is assured. The Tattoo module is an independent but integrated module
within the f2 image recognition suite, which includes both full face recognition
and partial face recognition – another unique and powerful capability. It will
work alongside existing biometric systems. The tattoo module is available within
the f2 Image Recognition Suite as a stand-alone/networked application, as a .Net
SDK, and as a web service. The f2 Image Recognition Suite is available for evaluation by interested
organizations and suppliers to them.
Face Forensics Inc. Announces High Speed Partial Face Recognition Capability
VANCOUVER – June 22, 2015 Face Forensics Inc, developers of the highly-advanced
f2 face recognition technology, has announced a significant enhancement to its
unique partial face recognition capability. This capability allows an image of
part of a face, for example one side or just the eyes, to be matched against the
same area on previously enrolled full faces. Databases are searched at extremely
high speed – f2 can be configured to match well in excess of 1m faces/second.
The top matches are displayed as thumbnail images in order of match %, making it
straightforward to determine if the full face is already in the database. Face
Forensics’ unique partial face recognition capability is invaluable for
recognizing faces which are partially-concealed, burnt or injured, as well as
criminals wearing balaclavas, etc.
Face Forensics Partial Face Recognition Technology Featured on Sky News
VANCOUVER – October 8, 2014 In late September London-based Sky News ran a
prime-time feature on the identification of individuals who hide their face by
wearing balaclavas. Central to this feature was the use of Face Forensics’
unique partial face recognition technology. Unlike other face recognition
systems, all of which require a full facial image in order to match a face, f2
can work with just a section of a face.
This is invaluable where the face is partially concealed by, a building, another
person, or by clothing, so that just one eye can be seen. f2 can also work with
a “letterbox” view where only the area around the eyes is visible. The partial
face recognition capability adds a new and invaluable tool to security and law
enforcement agencies around the world.
Face Forensics Inc. Announces Partnership with Otec Solutions Inc.
VANCOUVER – May 16, 2014 Face Forensics Inc, developers of the highly-advanced
f2 face recognition technology, has announced a business partnership with
Toronto-based Otec Solutions Inc.
Under the agreement, Otec will incorporate Face Forensics’ f2 technology into
its Digital Evidence Management Solution (DEMS). When set up, f2 automatically
enrolls all the faces in selected databases by determining over 3000 features in
the central area of the face and transforming the resulting data into a unique
numeric string for each face. This enables facial searches to be conducted
across all databases at extremely high speed – well in excess of 1m
faces/second. The top matches are displayed as thumbnail images in order of
match %, making it straightforward for an officer to visually scan the top
matches to determine if the face is already known. Integrating this capability
with Otec’s Digital Evidence Management enables law enforcement agencies to
securely access and search data, including faces, across a wide range of
applications and devices.
Otec’s Digital Evidence Management Solution streamlines ingestion of crime scene
photography and video with the Camera Wizard. DEMS also provides a robust, fast
search interface for ordering evidence for trial. Orders are processed through a
forensics workflow to deliver orders to police, defense and prosecutors.
Billing for these orders is viable. About Otec Solutions Inc.
Otec Solutions Inc. is a privately held systems integrator with a focus on
providing Digital Evidence Management, Digital Asset Management, Automated
Workflow & secured remote access of those services based on the individual
requirements of its clients. Otec markets, supports and customizes the world’s
leading Digital Asset Management software, Cumulus by Canto. As a Canto
Certified Systems Integrator and Platinum Level Sales Partner, Otec is
well-equipped to adapt it to meet specific needs. Otec holds certifications in
critical IT disciplines to offer a complete and comprehensive design,
installation, training and support of the entire system infrastructure where
required.
Contact:
info@otecsolutions.com
Website:
http://www.otecsolutions.com
Face Forensics Announces Significant Enhancements to its Eye-Detection
Capabilities
Vancouver - April 29, 2014 The performance of Face Forensics’ f2 facial
recognition technology has been significantly enhanced by the upgrading of its
eye detection logic. Eye detection is critical to the performance of face
recognition systems as it performs a vital initial role by finding the key
anchor points around which, in f2’s case, the more than 3000 characteristics of
the face are determined. This improvement means that eye centers can be more
accurately located even when the facial image is not particularly clear. This
development complements Face Forensics’ partial face recognition capabilities,
enabling images of both full and partial faces to be readily identified. F2
search speeds are extremely fast (well in excess of 1m faces/second). It is
available in both 32 and 64 bit, so is well able to handle extremely large
databases.
Forensic Protection Inc. & Face Forensics Agree to Partner on Image Enhancement
and Face Recognition
VANCOUVER - December 19th 2012 – With increasing demand from government agencies
around the world for the ability to recognize wanted individuals from their
face, often from CCTV video streams, there’s a need to be able to enhance the
quality of what are very often low-resolution and poor images. Forensic
Protection Inc. has developed technology which, unlike most providers of this
capability, does this automatically. This is provided as a service – customers
send in the video (or audio) clips they want enhanced, and Forensic Protection
processes and returns them. Where these are of faces, Face Forensics’ advanced
face recognition capabilities can be used to match the enhanced image against a
known image of the suspect, or a database of known offenders, to help identify
them. This includes the unique ability to match part of a face, i.e. one which
is injured, or partially hidden by another person, a building, or even a
balaclava. From Face Forensics’ point of view the partnership offers its
customers the ability to recognize faces where otherwise this would not be
feasible, opening a range of possibilities which previously did not exist. The
Face Forensics f2 system is based on many years’ experience in developing face
recognition technology for law enforcement, both in the US and overseas. It
offers both one-to-one and one-to-many matching, is unaffected by age, race, or
color, and operates at a search speed of over 1m faces/second.
Police Central & Face Forensics Announce Partnership to add Advanced
Face Recognition Capabilities to Police Central’s Jail Management System.
VANCOUVER – May 1, 2012 – Police Central’s comprehensive Jail Management System
is being enhanced with the addition of advanced face recognition technology.
This will facilitate the recognition of unidentified offenders, including those
who refuse to give their name when arrested. It will also identify individuals
with multiple records under different aliases. Atlanta-based PCI’s customer base
includes approximately eighty-five law enforcement agencies in ten states,
including the City of Atlanta Police Department and the City of Atlanta
Department of Corrections. PCI’s web-based Law Enforcement Software suite
already comprises thirty-five modules covering all aspects of law enforcement.
The face recognition capability will complement and add value to these. The Face
Forensics system is based on many years’ experience in developing this type of
technology for law enforcement, both in the US and overseas. It is specifically
designed to be easy to integrate with systems like PCI’s JMS. Recognition
performance is unaffected by age, race, or color, and offers a search speed of
over 1m faces/second. A police department can search the databases of adjacent
police departments under appropriate controls. Face Forensics is the only system
in the world to provide partial face recognition – offering the ability to
recognize injured faces, criminals wearing balaclavas, etc. The Face Forensics
team have also been responsible for the development of one of the largest
pedophilic image recognition systems in the world – the UK Serious Organized
Crime Agency’s ChildBase system.
Face Forensics Announces Full Support for SDK and Web Services Versions
of f2
VANCOUVER - January 18, 2012 - Face Forensics’ facial recognition technology is
now available as a standalone/networked application, an SDK, and as a web
service. Face Forensics is unique in being the only facial recognition system to
include partial face recognition, and is specifically designed to connect to
existing databases. The f2 search speeds are extremely fast (well in excess of
1m faces/second). It is available in both 32 and 64 bit, so is well able to
handle extremely large databases.
Vancouver Riots and Face Forensics.
VANCOUVER – June 21, 2011 – Face Forensics Inc, the developer of the advanced f2
face recognition technology, has provided Global News with insights on how f2
could be used to analyze imagery and video taken from the Vancouver riots. See
the interview here:
Global News interview
Face Forensics Inc. Announces automatic matching of faces across
multiple databases
VANCOUVER – March 24, 2011 – Face Forensics Inc, developers of the
highly-advanced f2 face recognition and unique partial face recognition
technology, has announced the ability to automatically match all faces in
multiple existing databases to identify individuals operating under different
names.
f2 can automatically locate and enroll facial images in SQL Server. It will take each enrolled
face and match it against every other face in the same database or in different
databases. Thus different records of the same individual operating under
different names will be identified. All matches above a user-defined threshold
are written to a separate file for an officer to confirm. By eliminating all but
the most likely matches, f2’s database matching capabilities transform what is
in practice an impossible task into something that is straightforward and fast
for an officer to undertake.
f2 is specifically designed to work easily and quickly with existing databases.
It will detect single or multiple faces in a photo, video, or website, and match
them in real time. It is available as a stand-alone or networked application and
as an SDK, and has the capability to work with extremely large databases. An
evaluation copy can be downloaded from
www.faceforensics.com
Face Forensics Inc. Announces World First: Partial Face Recognition
VANCOUVER – November 11, 2010 – Face Forensics Inc, developers of the
highly-advanced f2 face recognition technology, has announced the unique ability
to match part of a face against a database of faces. This is particularly useful
in a forensics environment where only body parts are left, e.g. after an
explosion or fire, or with surveillance imagery where only part of a face is
available. The image of the facial part is positioned on a generic facial
template. Controls are available to resize the partial face as well as adjust
the key characteristics of the generic template to the partial face. Once
positioned optimally, the partial face is encoded. This encoding is then matched
against the same areas of full faces in the database. Matches above a predefined
threshold are displayed for an investigator to review. f2 is specifically
designed to work easily with existing databases. It will detect single or
multiple faces in a photo, video, or website. It is available both as a
free-standing application and as an SDK, and has the capability to work with
extremely large databases. An evaluation copy can be downloaded from
www.faceforensics.com
360 Biometrics to Market Face Forensics' Face Recognition Technology
VANCOUVER – July 21, 2010 – Face Forensics Inc, the developer of the advanced f2
face recognition technology, has signed an agreement with Silicon Valley based
biometric solution reseller 360 Biometrics to market Face Forensics in its
markets around the world. 360 Biometrics plans to promote both the one-to-one
and one-to-many versions of Face Forensics. These systems are available as both
stand-alone applications and SDKs. 360 Biometrics is also interested in Face
Forensics’ newly announced capability to identify partial faces to be integrated
into 360 Biometrics' security solutions. Designed principally for use by
forensics laboratories, partial face recognition is a unique capability only
available from Face Forensics.
About 360 Biometrics Inc.
360 Biometrics is based in Sunnyvale, California, and provides a complete range
of biometric solutions including software, hardware and consulting. They are
also an established integrator and value-added reseller of multiple biometric
technologies and products. The focus of 360 Biometrics is to assist small
businesses, large enterprises and government bodies with the identity and
security solutions using various biometric technologies such as fingerprint,
face recognition, iris, etc. The customer base of the company ranges from small
businesses to very large commercial enterprises and Government organizations at
both the State and Federal level. 360 Biometrics also serves all markets
worldwide.
About Face Forensics Inc. The principals of the company have
already developed one of the most successful face recognition systems in North
America. This has been installed in numerous police forces and other locations
and achieved major successes. The team have also been responsible for the
development of the largest pedophilic image processing system anywhere – the
UK’s ChildBase system.
The f2 team comprises professionals with many years combined experience in
imaging technologies and applications, mathematics, biometrics, information
technology, and international business.
Enquiries: Contact:
info@faceforensics.com