Centre for Vision, Speech and Signal Processing (CVSSP)

Research Fellow wins top biometrics industry award

Dr Zhenhua Feng has won the European Association for Biometrics Industry Award 2017 for his development of an algorithm which enables facial landmark detection in ‘uncontstrained’ situations.

Dr Zhenhua Feng (second left) with the other EAB award winners and judges.

The prestigious Award – which includes a cash prize of €2,000 – is one of only two awarded annually by the European Association for Biometrics (EAB) to recognise individuals who have made a significant contribution to the field of biometrics research in Europe.

Dr Feng, a Research Fellow in Surrey’s Centre for Vision, Speech and Signal Processing (CVSSP), received the award at the fourth EAB Research Projects Conference (EAB-RPC) in Darmstadt, Germany, on 20 September. Along with other finalists from across Europe, he presented his paper in front of the awards jury (a panel of internationally recognised biometrics experts), EAB members and a public audience.

Dr Feng’s research focuses on developing robust facial landmark detection techniques for use in unconstrained or uncontrolled situations – where a person’s appearance is compromised by their pose, expression, lighting, poor image resolution or an obstruction such as sunglasses. The robust ‘facial landmark detection algorithm’ he has developed is an important breakthrough in the creation of a fully-automatic face recognition system as it can accurately estimate a set of key points for a given face image, allowing for large-scale variations in pose.

Face recognition is already widely used in our daily lives, in areas such as CCTV surveillance and public security systems at airports and stations, and in mobile technology such as the newly released iPhone X. The work of Dr Feng – and colleagues within CVSSP – is therefore attracting a lot of interest from industry as manufacturers work towards systems which work well in daily life. This area of research is funded by the £6m FACER2VM project which aims to make face recognition ubiquitous by 2020.

Dr Feng explained: “While existing techniques perform very well in recognising faces – even better than humans – in constrained situations, enabling systems to recognise unconstrained faces accurately is a very challenging task.

“I’m excited to have won the European Biometric Industry Award 2017, and grateful for the opportunity provided by the University, CVSSP and also the EPSRC programme grant for FACER2VM. 

Professor Josef Kittler commented: “The EAB Industry Award 2017 received by Zhenhua is not only international recognition of scientific excellence of his work in face biometrics but also of its potential impact and industrial relevance.”

Dr Feng’s paper, ‘Dynamic Attention-controlled Cascaded Shape Regression for Robust Facial Landmark Detection in the Wild’, won the EAB industry award at the IEEE Conference on Computer Vision and Pattern Recognition in July 2017.

Discover our programmes in Electrical and Electronic Engineering, including our MSc in Computer Vision, Robotics and Machine Learning.

 

Related news and features