Khemraj Emrith

Measuring perceived differences in surface texture due to changes in higher order statistics

We investigate the ability of humans to perceive changes in the appearance of images of surface texture caused by the variation of their higher order statistics. We incrementally randomize their phase spectra while holding their first and second order statistics constant in order to ensure that the change in the appearance is due solely to changes in third and other higher order statistics. Stimuli comprise both natural and synthetically generated naturalistic images, with the latter being used to prevent observers from making pixel-wise comparisons. A difference scaling method is used to derive the perceptual scales for each observer, which show a sigmoidal relationship with the degree of randomization. Observers were maximally sensitive to changes within the 20%-60% randomization range. In order to account for this behavior we propose a biologically plausible model that computes the variance of local measurements of phase congruency.

Visual search for a target against a 1/fβ continuous textured background

We present synthetic surface textures as a novel class of stimuli for use in visual search experiments. Surface textures have certain advantages over both the arrays of abstract discrete items commonly used in search studies and photographs of natural scenes. In this study we investigate how changing the properties of the surface and target influence the difficulty of a search task. We present a comparison with Itti and Kochs saliency model and find that it fails to model human behaviour on these surfaces. In particular it does not respond to changes in orientation in the same manner as human observers.

Real-time recovery of moving 3D faces for emerging applications

Existing face imaging systems are not suitable to meet the face representation and recognition demands for emerging applications in areas such as interactive gaming, enhanced learning environments and directed advertising. This is mainly due to the poor capture and characterisation of facial data that compromises their spatial and temporal precision. For emerging applications it is not only necessary to have a high level of precision for the representation of facial data, but also to characterise dynamic faces as naturally as possible and in a timely manner. This study proposes a new framework for capturing and recovering dynamic facial information in real-time at significantly high order of spatial and temporal accuracy to capture and model subtle facial changes for enhanced realism in 3D face visualisation and higher precision for face recognition applications. We also present a novel, fast, and robust correspondence mapping approach for 3D registration of moving 3D faces.

2.5D Facial Expression Recognition using Photometric Stereo and the Area Weighted Histogram of Shape Index

In this work we argue that the high frequency spatial variations in the topological information of the face are important for Facial Expression Recognition. Stereo and laser scanner based datasets currently used are inherently regularized, resulting in the loss of high frequency information. We test our hypothesis on the dense gradient field from Photometric Stereo which preserves this high frequency information. To overcome the geometric artefacts introduced through the integration of the gradient field we take a local approach and, assuming piecewise smoothness, we directly extract the second order differential geometry. We introduce the Area Weighted Histogram of Shape Index which is invariant to both scale and orientation and extend this to a localized histogram approach. Rather than using heuristically chosen areas of the face we use a data driven approach based on the Fisher Discriminant Ratio to identify the most discriminatory regions of the face. Using a non-linear Support Vector Machine we are able to recognize the six prototypic expressions of the face. We carry out analysis on the Binghamton BU4DFE database as well as a small Photometric Stereo dataset and show that the high frequency information preserved by Photometric Stereo may be highly useful for automatic Facial Expression Recognition.

PTU-024 Photometric stereo reconstruction for surface analysis of mucosal tissue

Introduction The American Society of Gastroenterology endoscopy led Preservation and Incorporation of Valuable endoscopic Innovations initiative has identified real time polyp detection diagnosis as one of the next major technology-driven changes in endoscopy.1We have recently described a novel photometric stereo (PS) imaging sensor for endoscopy imaging in a porcine model.2Following image acquisition, reconstruction of the surface data is necessary to calculate the shape index (SI) to identify regions that are locally spherical, suggestive of polyps to aid polyp detection. Method Using a porcine gut model, photometric images were captured using a six-light source PS setup as previously described.2Surface analysis of the obtained surface data was performed: Derivatives of the height fields arranged on a square lattice were calculated using finite differences, and used to characterise the differential geometry using the principal curvatures.3Surface measures analysis: for each point on the surface, the shape index (SI) was computed and used to measure the local shape: SI = 1/2 – 1/π tan−1 ((K1+K2)/(K1-K2)) ResultsAbstract PTU-024 Figure 1 Porcine colonic data captured using the photometric stereo system. Left to right: Colour image, Normal map, Reconstructed height map, SI image top view, SI image side view Conclusion Using a novel PS image acquisition 3D reconstruction was obtained on colonic mucosa. We observe that the recovered 3D surface retains the surface geometry in the captured areas and important structural information at a fine level of detail, even in the presence of numerous specular reflections. This is highly significant for automated processing and analysis of surface abnormalities. Disclosure of interest None Declared. References Rex, et alet al. Gastrointest Endosc 2011;73:419–22 Poullis, et alet al. Gut 2014;63(Suppl 1):A46 do Carmo M. Differential geometry of curves and surfaces. Prentice Hall, 1976, ISBN:0132125897

Testing the Validity of Lamberts Law for Micro-scale Photometric Stereo Applied to Paper Substrates

This paper presents an empirical study to investigate the use of photometric stereo (PS) for micro-scale 3D measurement of paper samples. PS estimates per-pixel surface orientation from images of a surface captured from the same viewpoint but under different illumination directions. Specifically, we investigate the surface properties of paper to test whether they are sufficiently well approximated by a Lambertian reflectance model to allow veridical surface reconstruction under PS and explore the range of conditions for which this model is valid. We present an empirical setup that is used to conduct a series of experiments in order to analyse the applicability of PS at the micro-scale. In addition, we determine the best 4, 6, and 8 light source tilt (illumination) angles with respect to multi-source micro-scale PS. Furthermore, an intensity based image registration method is used to test the accuracy of the recovery of surface normals. The results demonstrate that at the micro-scale: (a) Lambert model represents well the data sets with low root mean square (RMS) error between the original and reconstructed image, (b) increasing the light sources from 4 to 8 reduces RMS error, and (c) PS can be used to extract veridical surface normals.

PTU-022 A Novel Photometric Stereo Imaging Sensor For Endoscopy Imaging: Proof Of Concept Studies On A Porcine Model

Introduction The American Society of Gastroenterology Endoscopy led Preservation and Incorporation of Valuable Endoscopic Innovations initiative has identified real time polyp diagnosis as one of the next major technology-driven changes in endoscopy.1 A number of imaging techniques are presently being investigated in this area. The complex and demanding nature of the imaging environment, including issues relating to operation in a confined space, the presence of surface fluids and the highly reflective nature of the mucosa, renders 3D surfaccapture and analysis for the purpose of diagnosis an extremely challenging task. A novel Photometric Stereo (PS) imaging sensor has never been previously assessed for mucosal imaging. PS imaging requires the capture of the mucosal regions while illuminated using light from differing known directions and offers the potential for the recovery of high resolution 3D shape and topographic texture data. The captured PS images are then used to recover and analyse the 3D surface geometry. Methods Using a porcine gut model, photometric images were captured using a six-light source PS setup. PS assumes diffuse reflectance from the illuminated surfaces. We use a least squares approximation approach to estimate the surface in the presence of the specular highlights. Several areas of the porcine gastrointestinal tract were scanned. For each area investigated six photometric images were captured. This data was then used to recover the depth information. Results 3D reconstruction was obtained on all mucosal areas of the gastrointestinal tract that were studied (Figure 1). We observe that the recovered 3D surface retains the surface geometry in the captured areas and important structural information at a fine level of detail, even in the presence of numerous specular reflections. This is highly significant for automated processing and analysis of surface abnormalities. Abstract PTU-022 Figure 1 Conclusion Using a novel sensor technology it was possible to obtain mucosal views and 3D surface reconstruction on all areas of the gastrointestinal tract using a porcine model. 3D geometric representations of the mucosal views were obtained, raising the possibility of automated computer analysis of endoscopic images. This novel technique needs to be explored further in human studies. Reference Rex et al. Gastrointest Endosc 2011;73:419–22 Disclosure of Interest None Declared.