Con esta herramienta te facilitamos un acceso a todas las ofertas y demandas de tecnología europeas y a búsquedas de socios para participar en propuestas europeas de I+D publicadas en la red Enterprise Europe Network, pudiendo filtrar los resultados para facilitar las búsquedas más acordes con tus necesidades.

¿Quieres recibir estos listados de oportunidades de colaboración en tu correo de forma periódica y personalizada? Date de alta en nuestro Boletín

Los términos de búsqueda han de ser en inglés.

Universidad británica que ha desarrollado un método de desclasificación de imágenes faciales para proteger la privacidad en contenidos multimedia busca socios con el fin de establecer acuerdos de licencia o cooperación técnica

Resumen

Tipo:
Oferta Tecnológica
Referencia:
TOUK20170106001
Publicado:
12/01/2017
Caducidad:
12/01/2018
Resumen:
Una universidad británica ha desarrollado una solución de privacidad online para desclasificar imágenes faciales. Esta solución permite cambiar el rostro original por una imagen facial existente elegida por el usuario o por un rostro sintetizado automáticamente, y tiene aplicaciones potenciales en un gran número de sectores. El prototipo en tiempo real está disponible para demostración. La universidad busca socios para licenciar la tecnología en sus aplicaciones mediante acuerdos de licencia o para desarrollar la tecnología a través de acuerdos de cooperación técnica.

Details

Tittle:
A UK university seeks partners for licensing agreements or technical cooperation agreements for a new de-identification method for facial images suitable for privacy protection in multimedia conten
Summary:
A UK university has developed an online privacy solution for de-identification of facial images that allows the swapping of the original face with either an existing face image of the user´s choice or an automatically synthesized face with potential to be applied across a number of potential markets. The university seeks partners to license the technology in their own applications for a license agreement or technical development partners of the solution for a technical cooperation agreement.
Description:
With the advance of camera technology and face biometrics, many organisations and governments are exploiting the potential of data sharing to enhance their operations or business models. However, this has inevitably ignited concerns about the privacy of individuals identifiable in recordings. De-identification in multimedia content can be defined as the process of concealing the identities of individuals captured in a given data set (images, video, audio, text) for the purpose of protecting their privacy.

The intensive adaptation of surveillance has inevitably raised concerns about the privacy of individuals identifiable in recordings. This growing concern, along with the associated ethical and social responsibilities has made de-identification the focus of attention in many organisations. The European COST framework is hosting action IC1206 "De-identification for privacy protection in multimedia content"(2013-2017). The US National Institute of Standards and Technology has published its first guidelines on "De-identification of personal information" as well. This is in addition to the UK Data Protection Act , the EU General Data Protection Regulation and the US Consumer Privacy Bill of Rights which all demand the deployment of appropriate technical and organisational methods to protect private information.

Masking, blurring and pixilation are the ad hoc face de-identification methods that were widely used in the past. However, these methods fail to serve their purpose as they are either reversible or unable to thwart existing face recognition software. Moreover, they are highly destructive and hence destroy data utility.

The solution developed by this UK university have developed a novel solution to this problem that opens many opportunities in the field of online personal privacy protection using the k-same family process, where sets of images are partitioned into clusters identified in size by the value term "k".

The solution has the potential to be developed in a number of potential areas including:

Privacy protected public data sharing and dissemination. An example may be a TV interview under witness protection where the original face is replaced with a synthesised face.
Privacy protection built into photo sharing/social media applications where people with access permission can see original images/videos while people without access permission see de-identified faces with original expressions and movements.
In the film and game industry where there is the potential to transfer facial expressions between the faces of different characters or between different versions e.g. between a photo version and a cartoon version of the same face.
In the beauty industry - to demonstrate the impact on a client´s face of cosmetic surgery, aging, weight loss, make up etc with dynamic video showing the expressions of the client rather than a still image
Face swapping for fun - replacing an existing face with another face of a celebrity, a cartoon character or animal - complete with expressions.

This UK university seeks partners interested in licensing the technology for applications such as those mentioned for a license agreement or partners willing to work with the university to further develop this solution for a technical cooperation agreement.
Advantages and Innovations:
The scientists at this well-known UK university have developed a unique face de-identification system that, unlike other technologies, offers the ability to produce a distinguishable face for each individual while retaining the same diversity as the original face set within a corresponding de-identified face set.

This means faces that look similar before de-identification will remain similar afterwards and faces that look different will remain different.

This method also reduces the re-identification risk of the de-identified (synthesized) faces to nearly zero. This has been tested using some of the most advanced face recognition systems including local binary patterns, histogram of oriented gradients and local phase quantization.

Additional the system has incorporated model based facial expression transfer to restore the facial movements and expressions in the original images or videos thus producing a more natural experience.

The system offers the ability for online video/photo sharing features to offer access permissions where those with permission will see the original face and those without will see a de-identified version.

The system also offers the ability to complete the de-identification process by blending a de-identified face region with its original background, where the new shape of the de-identified face region is retained without distorting other objects in the image and the skin tone within the face region is adjusted to achieve seamless blending with other parts of the human body e.g. ears and, neck.
Stage of Development:
Available for demonstration
IPs:
Copyright
CommeR Statunts Regarding IPR Status:
Software covered by copyright

Partner sought

Type and Role of Partner Sought:
The university seeks partners interested in licensing the technology for use in their own applications as part of a license agreement. They are also interested in working with partners on further technical development of this solution through a technical cooperation agreement.

Client

Type and Size of Client:
University
Already Engaged in Trans-National Cooperation:
Si
Languages Spoken:
English

Keywords

Technology Keywords:
01003009 Data Protection, Storage, Cryptography, Security
01003012 Imaging, Image Processing, Pattern Recognition