Antonio Robles-Kelly - Profile on Academia.edu (original) (raw)

Papers by Antonio Robles-Kelly

Technical Committee and Area Chairs

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2007

This paper offers two new directions to shape-from-shading, namely the use of the heat equation t... more This paper offers two new directions to shape-from-shading, namely the use of the heat equation to smooth the field of surface normals and the recovery of surface height using a low-dimensional embedding. Turning our attention to the first of these contributions, we pose the problem of surface normal recovery as that of solving the steady state heat equation subject to the hard constraint that Lambert's law is satisfied. We perform our analysis on a plane perpendicular to the light source direction, where the z component of the surface normal is equal to the normalized image brightness. The x - y or azimuthal component of the surface normal is found by computing the gradient of a scalar field that evolves with time subject to the heat equation. We solve the heat equation for the scalar potential and, hence, recover the azimuthal component of the surface normal from the average image brightness, making use of a simple finite difference method. The second contribution is to pose t...

IEEE transactions on pattern analysis and machine intelligence, 2005

This paper is concerned with computing graph edit distance. One of the criticisms that can be lev... more This paper is concerned with computing graph edit distance. One of the criticisms that can be leveled at existing methods for computing graph edit distance is that they lack some of the formality and rigor of the computation of string edit distance. Hence, our aim is to convert graphs to string sequences so that string matching techniques can be used. To do this, we use a graph spectral seriation method to convert the adjacency matrix into a string or sequence order. We show how the serial ordering can be established using the leading eigenvector of the graph adjacency matrix. We pose the problem of graph-matching as a maximum a posteriori probability (MAP) alignment of the seriation sequences for pairs of graphs. This treatment leads to an expression in which the edit cost is the negative logarithm of the a posteriori sequence alignment probability. We compute the edit distance by finding the sequence of string edit operations which minimizes the cost of the path traversing the edi...

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, 2004

In this paper, we explore how graph-spectral methods can be used to develop a new shape-from-shad... more In this paper, we explore how graph-spectral methods can be used to develop a new shape-from-shading algorithm. We characterize the field of surface normals using a weight matrix whose elements are computed from the sectional curvature between different image locations and penalize large changes in surface normal direction. Modeling the blocks of the weight matrix as distinct surface patches, we use a graph seriation method to find a surface integration path that maximizes the sum of curvature-dependent weights and that can be used for the purposes of height reconstruction. To smooth the reconstructed surface, we fit quadrics to the height data for each patch. The smoothed surface normal directions are updated ensuring compliance with Lambert's law. The processes of height recovery and surface normal adjustment are interleaved and iterated until a stable surface is obtained. We provide results on synthetic and real-world imagery.

Hyperspectral Imaging Pipeline

This paper presents a novel approach for recovering the shape of non-Lambertian, multicolored obj... more This paper presents a novel approach for recovering the shape of non-Lambertian, multicolored objects using two input images. We show that a ring light source with complementary colored lights has the potential to be effectively utilized for this purpose. Under this lighting, the brightness of an object surface varies with respect to different reflections. Therefore, analyzing how brightness is modulated by illumination color gives us distinct cues to recover shape. Moreover, the use of complementary colored illumination enables the color photometric stereo to be applicable to multicolored surfaces. Here, we propose a color correction method based on the addition principle of complementary colors to remove the effect of illumination from the observed color. This allows the inclusion of surfaces with any number of chromaticities. Therefore, our method offers significant advantages over previous methods, which often assume constant object albedo and Lambertian reflectance. To the best of our knowledge, this is the first attempt to employ complementary colors on a ring light source to compute shape while considering both non-Lambertian reflection and spatially varying albedo. To show the efficacy of our method, we present results on synthetic and real world images and compare against photometric stereo methods elsewhere in the literature.

Underexposed Image Correction Via Approximation of the Scene Radiance Function

In this paper we propose a simple yet powerful method for learning representations in supervised ... more In this paper we propose a simple yet powerful method for learning representations in supervised learning scenarios where an input datapoint is described by a set of feature vectors and its associated output may be given by soft labels indicating, for example, class probabilities. We represent an input datapoint as a K-dimensional vector, where each component is a mixture of probabilities over its corresponding set of feature vectors. Each probability indicates how likely a feature vector is to belong to one-out-of-K unknown prototype patterns. We propose a probabilistic model that parameterizes these prototype patterns in terms of hidden variables and therefore it can be trained with conventional approaches based on likelihood maximization. More importantly, both the model parameters and the prototype patterns can be learned from data in a discriminative way. We show that our model can be seen as a probabilistic generalization of learning vector quantization (LVQ). We apply our method to the problems of shape classification, hyperspectral imaging classification and people's work class categorization, showing the superior performance of our method compared to the standard prototype-based classification approach and other competitive benchmarks.

A relaxed factorial Markov random field for colour and depth estimation from a single foggy image

Automatic exposure control for multispectral cameras

A Comparative Evaluation of Spectral Reflectance Representations for Spectrum Reconstruction, Interpolation and Classification

ABSTRACT Due to the high dimensionality of spectral data, spectrum representation techniques have... more ABSTRACT Due to the high dimensionality of spectral data, spectrum representation techniques have often concentrated on modelling the spectra as a linear combination of a small basis set. Here, we focus on the evaluation of a B-Spline representation, a Gaussian mixture model, PCA and wavelets when applied to represent real-world spectrometer and spectral image data. These representations are important since they open up the possibility of reducing densely sampled spectra to a compact form for spectrum reconstruction, interpolation and classification. In particular, we shall perform an evaluation of these representations for the above tasks on two datasets consisting of reflectance spectra and hyperspectral images.

A spiking neural network for illuminant-invariant colour discrimination

ABSTRACT In this paper, we propose a biologically inspired spiking neural network approach to obt... more ABSTRACT In this paper, we propose a biologically inspired spiking neural network approach to obtaining an opponent pair which is invariant to illumination variations and can be employed for colour discrimination. The model is motivated by the neural mechanisms involved in processing the visual stimulus starting from the cone photo receptors to the centre-surround receptive fields present in the retinal ganglion cells and the striate cortex. For our spiking neural network, we have employed the excitatory and inhibitory lateral synaptic connections, the Spike-Timing Dependent Plasticity (STDP) and long term potentiation and depression (LTP/LTD). Here, we employ a feed-forward leaky integrate-and-fire spiking neural network trained using a dataset of Munsell spectra. We have performed tests on perceptually similar colours under large illuminant power variations and done experiments on colour-based object recognition. We have also compared our results to those yielded by a number of alternatives.

School of Engineering, Australian National University, Canberra ACT 0200, Australia

Research School of Engineering, Australian National University, Canberra ACT 0200, Australia

In this paper, we develop a method for reconstructing the polarisation components from unpolarise... more In this paper, we develop a method for reconstructing the polarisation components from unpolarised imagery. Our approach rests on a model of polarisation which accounts for reflection from rough surfaces illuminated at moderate and large angles of incidence. Departing from the microfacet structure of rough surfaces, we relate the maximal and minimal polarimetric intensities to the diffuse and specular components of an unpolarised image via the Fresnel reflection theory. This allows us to reconstruct the polarimetric components from a single unpolarised image. Thus, the model presented here provides a link between the microfacet structure and polarisation of light upon reflection from rough surfaces. We evaluate the accuracy of the reconstructed polarisation components and illustrate the utility of the method for the simulation of a polarising filter on real-world images.

In this study, the authors explore the opportunities, application areas and challenges involving ... more In this study, the authors explore the opportunities, application areas and challenges involving the use of imaging spectroscopy as a means for scene understanding. This is important, since scene analysis in the scope of imaging spectroscopy involves the ability to robustly encode material properties, object composition and concentrations of primordial components in the scene. The combination of spatial and compositional information opens-up a vast number of application possibilities. For instance, spectroscopic scene analysis can enable advanced capabilities for surveillance by permitting objects to be tracked based on material properties. In computational photography, images may be enhanced taking into account each specific material type in the scene. For food security, health and precision agriculture it can be the basis for the development of diagnostic and surveying tools which can detect pests before symptoms are apparent to the naked eye. This combination of a broad domain of application with the use of key technologies makes the use of imaging spectroscopy a worthwhile opportunity for researchers in the areas of computer vision and pattern recognition.

An optimisation approach to the recovery of reflection parameters from a single hyperspectral image

ABSTRACT In this paper, we present a method to recover the parameters governing the reflection of... more ABSTRACT In this paper, we present a method to recover the parameters governing the reflection of light from a surface making use of a single hyperspectral image. To do this, we view the image radiance as a combination of specular and diffuse reflection components and present a cost functional which can be used for purposes of iterative least squares optimisation. This optimisation process is quite general in nature and can be applied to a number of reflectance models widely used in the computer vision and graphics communities. We elaborate on the use of these models in our optimisation process and provide a variant of the Beckmann–Kirchhoff model which incorporates the Fresnel reflection term. We show results on synthetic images and illustrate how the recovered photometric parameters can be employed for skin recognition in real world imagery, where our estimated albedo yields a classification rate of 95.09 ± 4.26% as compared to an alternative, whose classification rate is of 90.94 ± 6.12%. We also show quantitative results on the estimation of the index of refraction, where our method delivers an average per-pixel angular error of 0.15°. This is a considerable improvement with respect to an alternative, which yields an error of 9.9°.

Recovery of spectral sensitivity functions from a colour chart image under unknown spectrally smooth illumination

Factor Graphs for Image Processing

DETERMINING COLOUR VALUES IN HYPERSPECTRAL OR MULTISPECTRAL IMAGES