A unified framework for thermal face recognition

The reduction of the cost of infrared (IR) cameras in recent years has made IR imaging a highly viable modality for face recognition in practice. A particularly attractive advantage of IR-based over conventional, visible spectrumbased face recognition stems from its invariance to visible illumination. In this paper we argue that the main limitation of previous work on face recognition using IR lies in its ad hoc approach to treating different nuisance factors which affect appearance, prohibiting a unified approach that is capable of handling concurrent changes in multiple (or indeed all) major extrinsic sources of variability, which is needed in practice. We describe the first approach that attempts to achieve this – the framework we propose achieves outstanding recognition performance in the presence of variable (i) pose, (ii) facial expression, (iii) physiological state, (iv) partial occlusion due to eye-wear, and (v) quasi-occlusion due to facial hair growth.

A new design concept for knitted external vein-graft support mesh

Autologous vein-graft failure significantly limits the long-term efficacy of coronary artery bypass procedures. The major cause behind this complication is biomechanical mismatch between the vein and coronary artery. The implanted vein experiences a sudden increase (10-12 fold) in luminal pressures. The resulting vein over-distension or 'ballooning' initiates wall thickening phenomenon and ultimate occlusion. Therefore, a primary goal in improving the longevity of a coronary bypass procedure is to inhibit vein over-distension using mechanical constriction. The idea of using an external vein-graft support mesh has demonstrated sustained benefits and wide acceptance in experimental studies. Nitinol based knitted structures have offered more promising mechanical features than other mesh designs owing to their unique loosely looped construction. However, the conventional plain knit construction still exhibits limitations (radial compliance, deployment ease, flexibility, and bending stresses) which limit this design from proving its real clinical advantage. The new knitted mesh design presented in this study is based on the concept of composite knitting utilising high modulus (nitinol and polyester) and low modulus (polyurethane) material components. The experimental comparison of the new design with a plain knit design demonstrated significant improvement in biomechanical (compliance, flexibility, extensibility, viscoelasticity) and procedural (deployment limit) parameters. The results are indicative of the promising role of new mesh in restoring the lost compliance and pulsatility of vein-graft at high arterial pressures. This way it can assist in controlled vein-graft remodelling and stepwise restoration of vein mechanical homoeostasis. Also, improvement in deployment limit parameter offers more flexibility for a surgeon to use a wide range of vein diameters, which may otherwise be rendered unusable for a plain knit mesh.

Efficient and accurate set-based registration of time-separated aerial images

This paper addresses the task of time-separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change under illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several major novelties (i) unlike previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how image space local, pair-wise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed; (iv) lastly, we introduce a new and, to the best of our knowledge, the only data corpus suitable for the evaluation of set-based aerial image registration algorithms. Using this data set, we demonstrate (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task and (ii) that the increase in the number of available images in a set consistently reduces the average registration error, with a major difference already for a single additional image.

Groupwise registration of aerial images

This paper addresses the task of time separated aerial image registration. The ability to solve this problem accurately and reliably is important for a variety of subsequent image understanding applications. The principal challenge lies in the extent and nature of transient appearance variation that a land area can undergo, such as that caused by the change in illumination conditions, seasonal variations, or the occlusion by non-persistent objects (people, cars). Our work introduces several novelties: (i) unlike all previous work on aerial image registration, we approach the problem using a set-based paradigm; (ii) we show how local, pairwise constraints can be used to enforce a globally good registration using a constraints graph structure; (iii) we show how a simple holistic representation derived from raw aerial images can be used as a basic building block of the constraints graph in a manner which achieves both high registration accuracy and speed. We demonstrate: (i) that the proposed method outperforms the state-of-the-art for pair-wise registration already, achieving greater accuracy and reliability, while at the same time reducing the computational cost of the task; and (ii) that the increase in the number of available images in a set consistently reduces the average registration error.