Seeing with Humans: Gaze-Assisted Neural Image Captioning

Gaze tracking uses human gaze data for various applications in computer-vision systems, since gaze reflects how humans process visual scenes. Recently, researchers from Max Planck Institute for Informatics, Saarbrucken wanted to know whether gaze data can also be beneficial for scene-centric tasks, such as image captioning. They presented a new perspective on gaze-assisted image captioning using […]

When I’m sixty-four: face aging

Age progression or age synthesis (face aging) is defined as aesthetically rendering a face image with natural aging and rejuvenating effects for a certain face of an individual.

Lie to me: reading hidden emotions

Microexpressions magnified at different levels IEEE researchers have studied micro-expressions: rapid, involuntary facial expressions which reveal emotions that people do not intend to show. This is of extreme importance in forensic science and psychotherapy, and we all remember the TV show Lie to me, which focused on these micro-expressions (MEs). Unlike the pompous TV shows, real-life […]

Face tracking and analysis now on Raspberry Pi!

From v8.2 stable, visage|SDK supports Raspberry Pi as well, adding it to our largest list of supported platforms in the market. Raspberry Pi, a series of single-board computers, was created with a goal of educating computer science and related subjects. Raspberry Pi also uses the ARM processor architecture, used by most modern mobile phones. These low-cost high-performance computers […]

Introducing 3D face placement and face masks

We are proud to present our new 3D-model mesh, which can be used for an array of applications, such as 3d face placement, face painting, face swapping or face masking, either from video or live from your phone or webcam. Read more to see demo! Check out our other possible solutions and custom development: virtual makeup and virtual glasses try-on!

Silence of the lambs: facial landmarks on sheep

Researchers from the University of Cambridge have recently presented a method for facial localization not only on humans, but on sheep as well. Introducing a new feature extraction scheme, they managed to show very competitive performance in comparison to other methods. The new scheme is called the triplet-interpolated feature, and it’s used at each iteration […]

Shadow of a doubt: human action recognition from silhouettes

Three logical horizontal level of human silhouette Silhouette is an eponym derived from the name of a French finance minister Étienne de Silhouette who was, in 1759, forced by France’s credit crisis during the Seven Years’ War, to impose sever economic demands upon the French people, particularly the wealth. Because of this austere economy, his […]

Visage Technologies on Deloitte’s Sweden Technology Fast 50 list second year in a row

Deloitte, one of the “Big Four” accounting organizations and the largest professional services network in the world by revenue and number of professionals ranks the fastest growing technology companies in Sweden each year. The Technology Fast 50 has been dominated by software companies for many years, with media and entertainment in a strong second place. Game development and […]

Nordea Invest: Our co-founder talks face recognition, artificial intelligence and market trends

The investment association Nordea Invest is one of Denmark’s largest investment associations with a strong focus on sustainable savings and a wide range of investment opportunities. Nordea Invest closely follows the financial markets in order to bring relevant and current stories from around the world. Recently, Nordea Invest’s Nina Azoulay featured an interview with our co-founder, Jörgen Ahlberg. […]

Who let the dogs out? Retrieving lost dogs by facial features

Dog dataset examples: pugs are expected to be the hardest to identify, while huskies would be the easiest Researchers from the University of Campinas in Brazil have decided to use computer vision to help people whose pets have gone missing. A moment of distraction is usually enough for unfortunate events like these, and automated visual […]