Computer Vision and Machine Learning (CVML)

Institute for Engineering and Technology Innovation (InETI)

The Computer Vision and Machine Learning (CVML) Research Group emerged as a result of cross-disciplinary interests in research and applications related to Computer Vision, Machine Learning and Medical Image Computing.

The main focus of the group is to research, develop and deploy novel methods for the analysis of visual information for medical and industrial applications. The group have led or been involved in a number of industry, EPSRC, FP7 and HEIF funded projects.

The ongoing emphasis is on developing new vision and machine learning algorithms and their transfer to real-world applications. The particular areas of interest include: Bayesian methodology for data modelling, pattern recognition and tracking; statistical shape analysis; deformation modelling for model-based recognition, segmentation and registration; medical imaging; intelligent energy management; data mining; and applications of deep learning.

The ongoing progress in the mathematical tools, the growing prevalence of very large datasets, ever-increasing computational power and progress in imaging devices established the computer vision and machine learning as mature scientific disciplines with a rapidly growing number of exploitations in wide spectrum of applications, such as machine condition monitoring, medical diagnosis, assistive living or autonomous vehicles to name just a few.

A sample of CVML applications, from left to right: (i) level-set object segmentation with statistical shape prior; (ii) head-pose estimation from depth camera; (iii) eye status detection from video