Skip to main content

Research Repository

Advanced Search

All Outputs (15)

BRDF estimation for faces from a sparse dataset using a neural network (2013)
Presentation / Conference
Hansen, M. F., Atkinson, G., & Smith, M. (2013, August). BRDF estimation for faces from a sparse dataset using a neural network. Paper presented at Computer Analysis of Images and Patterns, CAIP 2013, York, UK

We present a novel �ve source near-infrared photometric stereo 3D face capture device. The accuracy of the system is demonstrated by a comparison with ground truth from a commercial 3D scanner. We also use the data from the �ve captured images to mo... Read More about BRDF estimation for faces from a sparse dataset using a neural network.

Multi-scale integration of slope data on an irregular mesh (2011)
Presentation / Conference
Saracchini, R., Stolfi, J., Leitão, H., Atkinson, G., & Smith, M. (2011, November). Multi-scale integration of slope data on an irregular mesh. Paper presented at Pacific-Rim Symposium on Image and Video Technology, Gwangju, South Korea, 2011, Gwangju, South Korea

Psychologically inspired dimensionality reduction for 2D and 3D Face Recognition (2011)
Presentation / Conference
Hansen, M. F., Atkinson, G., Smith, M., & Smith, L. (2011, September). Psychologically inspired dimensionality reduction for 2D and 3D Face Recognition. Paper presented at British Machine Vision Conference 2011, Dundee, UK

We present a number of related novel methods for reducing the dimensionality of data for the purposes of 2D and 3D face recognition. Results from psychology show that humans are capable of very good recognition of low resolution images and caricature... Read More about Psychologically inspired dimensionality reduction for 2D and 3D Face Recognition.

The photoface database (2011)
Presentation / Conference
Zafeirou, S., Hansen, M. F., Atkinson, G., Argyriou, V., Petrou, M., Smith, M., & Smith, L. (2011, June). The photoface database. Paper presented at Biometrics Workshop of Computer Vision and Pattern Recognition, Colorado Springs, Colorado, USA

Biologically inspired 3D face recognition from surface normals (2010)
Presentation / Conference
Hansen, M. F., & Atkinson, G. (2010, September). Biologically inspired 3D face recognition from surface normals. Paper presented at Procedia Computer Science, Coimbatore, India

A major consideration in state-of-the-art face recognition systems is the amount of data that is required to represent a face. Even a small (64 × 64) photograph of a face has 2 12 dimensions in which a face may sit. When large (> 1MB) photographs of... Read More about Biologically inspired 3D face recognition from surface normals.

Face recognition based on ridgelet transforms (2010)
Presentation / Conference
Kautkar, S., Koche, R., Keskar, T., Pande, A., Rane, M., & Atkinson, G. (2010, September). Face recognition based on ridgelet transforms. Paper presented at International Conference and Exhibition on Biometrics Technology, Coimbatore, India

Baseline face recognition using photometric stereo data (2010)
Presentation / Conference
Zafeiriou, S., Hansen, M. F., Atkinson, G., Petrou, M., & Smith, M. (2010, September). Baseline face recognition using photometric stereo data. Paper presented at International Conference and Exhibition on Biometrics Technology, Coimbatore, Tamil Nadu, India, 2010, Coimbatore, Tamil Nadu, India

An efficient and practical 3D face scanner using near infrared and visible photometric stereo (2010)
Presentation / Conference
Atkinson, G., Hansen, M. F., Smith, M., & Smith, L. (2010, September). An efficient and practical 3D face scanner using near infrared and visible photometric stereo. Paper presented at International Conference and Exhibition on Biometrics Technology, Coimbatore, India

This paper is concerned with the acquisition of model data for automatic 3D face recognition applications. As 3D methods become progressively more popular in face recognition research, the need for fast and accurate data capture has become crucial. T... Read More about An efficient and practical 3D face scanner using near infrared and visible photometric stereo.

Multi-scale depth from slope with weights (2010)
Presentation / Conference
Saracchini, R., Stolfi, J., Leitão, H., Atkinson, G., & Smith, M. (2010, September). Multi-scale depth from slope with weights. Poster presented at British Machine Vision Conference, Aberystwyth, Wales

We describe a robust method to recover the depth coordinate from a normal or slope map of a scene, obtained e.g. through photometric stereo or interferometry. The key feature of our method is the fast solution of the Poisson-like integration equation... Read More about Multi-scale depth from slope with weights.

Facial reconstruction and alignment using photometric stereo and surface fitting (2009)
Presentation / Conference
Atkinson, G., Farooq, A., Smith, M., & Smith, L. (2009, June). Facial reconstruction and alignment using photometric stereo and surface fitting. Paper presented at Iberian Conference on Pattern Recognition and Image Analysis, Povoa de Varzim, Portugal, 2009, Povoa de Varzim, Portugal

The nose on your face may not be so plain: Using the nose as a biometric (2009)
Presentation / Conference
Moorhouse, A., Evans, N., Atkinson, G., Sun, J., & Smith, M. (2009, June). The nose on your face may not be so plain: Using the nose as a biometric. Paper presented at International Conference on Imaging for Crime Detection and Prevention, Kingston-Upon-Thames, London, UK 2009, Kingston-Upon-Thames, London, UK

Facial geometry estimation using photometric stereo and profile views (2009)
Presentation / Conference
Atkinson, G., Smith, M., Smith, L., & Farooq, A. (2009, June). Facial geometry estimation using photometric stereo and profile views. Paper presented at International Conference on Biometrics, Alghero, Sardinia, Italy, 2009, Alghero, Sardinia, Italy

High-precision polarization measurements and analysis for machine vision applications
Presentation / Conference
Atkinson, G., Thornton, T., Peynado, D., & Ernst, J. High-precision polarization measurements and analysis for machine vision applications. Paper presented at European Workshop on Visual Information Processing

Polarization is a source of information that is steadily attracting attention in the field of computer vision due to its ability to tap into information not readily available in standard colour or greyscale cameras. Unfortunately, most existing data... Read More about High-precision polarization measurements and analysis for machine vision applications.