Oscar Dalmau

Image segmentation by convex quadratic programming

A quadratic programming formulation for multiclass image segmentation is investigated. It is proved that, in the convex case, the non-negativity constraint on the recent reported quadratic Markov measure field model can be neglected and the solution preserves the probability measure property. This allows one to design efficient optimization algorithms. Additionally, it is proposed a (free parameter) inter-pixel affinity measure which is more related with classes memberships than with color or gray gradient based standard methods. Moreover, it is introduced a formulation for computing the pixel likelihoods by taking into account local context and texture properties.

Variational Viewpoint of the Quadratic Markov Measure Field Models: Theory and Algorithms

We present a framework for image segmentation based on quadratic programming, i.e., by minimization of a quadratic regularized energy linearly constrained. In particular, we present a new variational derivation of the quadratic Markov measure field (QMMF) models, which can be understood as a procedure for regularizing model preferences (memberships or likelihoods). We also present efficient optimization algorithms. In the QMMFs, the uncertainty in the computed regularized probability measure field is controlled by penalizing Ginis coefficient, and hence, it affects the convexity of the quadratic programming problem. The convex case is reduced to the solution of a positive definite linear system, and for that case, an efficient Gauss-Seidel (GS) scheme is presented. On the other hand, we present an efficient projected GS with subspace minimization for optimizing the nonconvex case. We demonstrate the proposal capabilities by experiments and numerical comparisons with interactive two-class segmentation, as well as the simultaneous estimation of segmentation and (parametric and nonparametric) generative models. We present extensions to the original formulation for including color and texture clues, as well as imprecise user scribbles in an interactive framework.

MFCA: matched filters with cellular automata for retinal vessel detection

Blood vessel extraction is an important step for abnormality detection and for obtaining good retinopathy diabetic diagnosis in digital retinal images. The use of filter bank has shown to be a powerful technique for detecting blood vessels. In particular, the Matched Filter is appropriate and efficient for this task and in combination with other methods the blood vessel detection can be improved. We propose a combination of the Matched Filter with a segmentation strategy by using a Cellular Automata. The strategy presented here is very efficient and experimentally yields competitive results compared with others methods of the state of the art.

A General Bayesian Markov Random Field Model for Probabilistic Image Segmentation

We propose a general Bayesian model for image segmentation with spatial coherence through a Markov Random Field prior. We also study variants of the model and their relationship. In this work we use the Matusita Distance, although our formulation admits other metric-divergences. Our main contributions in this work are the following. We propose a general MRF-based model for image segmentation. We study a model based on the Matusita Distance, whose solution is found directly in the discrete space with the advantage of working in a continuous space. We show experimentally that this model is competitive with other models of the state of the art. We propose a novel way to deal with non-linearities (irrational) related with the Matusita Distance. Finally, we propose an optimization method that allows us to obtain a hard image segmentation almost in real time and also prove its convergence.

Segmentation of carbon nanotube images through an artificial neural network

Segmentation of carbon nanotube images is an important task for nanotechnology. The segmentation stage determines the accuracy of the measurement process of nanotube when assessing the quality of nanomaterials. In this work, we propose two segmentation algorithms for carbon nanotube images. Each algorithm includes three stages: preprocessing, segmentation and postprocessing. The first one is applied on images from scanning electron microscopy and employs a matched filter bank in the preprocessing step followed by a neural network in the segmenting phase. The second algorithm uses the Perona–Malik filter for enhancing the nanotube information. The segmentation phase is composed of the relaxed Otsu’s threshold and an artificial neural network. This algorithm is applied on images from transmission electron microscopy. The postprocessing stage, for both algorithms, is based on mathematical morphology. The performance of the proposed algorithms is numerically evaluated by using real image databases, manually segmented by an expert. The algorithm for segmentation of scanning electron microscopy achieved 92.74% of overall accuracy, while the algorithm for segmentation of transmission electron microscopy obtained an accuracy of 73.99% if the whole image is considered. A performance improvement is accomplished if only the region of interest is segmented, arriving to 84.19% of overall accuracy.

GP-MPU Method for Implicit Surface Reconstruction

This work addresses the problem of surface reconstruction from unorganized points and normals that are acquired from laser scanning of 3D objects. We propose a novel technique for implicit surface reconstruction that effectively combines the trend setting method known as Multi-level Partition of the Unity (MPU) with the Gaussian Process Regression. The reconstructed implicit surface is obtained by subdividing the domain into a set of smaller sub-domains using the MPU algorithm, in each sub-domain a Gaussian Process Regression is carried out that provides accurate local approximations which are blended to obtain a global representation corresponding to the reconstructed implicit surface. The proposed algorithm is able to deal efficiently with point clouds presenting several features such as complex topology and geometry, missing regions and very low sampling rate. Moreover, we conduct some experiments with several acquired data and perform some comparisons with state of the art techniques showing competitive results.

Spatial Sampling for Image Segmentation

We present a novel framework for image segmentation based on the maximum likelihood estimator. A common hypothesis for explaining the differences among image regions is that they are generated by sampling different likelihood functions called models. In this work, we construct on last hypothesis and, additionally, we assume that such samples come from independent and identically distributed random variables. Thus, the probability (likelihood) that a particular model generates the observed value (at a given pixel) is estimated by computing the likelihood of the sample composed with the surrounding pixels. This simple approach allows us to propose efficient segmentation methods able to deal with textured images. Our approach is naturally extended for combining different features. Experiments in interactive image segmentation, automatic stereo analysis and denoising of brain water diffusion multi-tensor fields demonstrate the capabilities of our approach.

Alpha Markov Measure Field model for probabilistic image segmentation

We apply the theory of metric-divergences between probability distributions and a variational approach in order to obtain a new model for probabilistic image segmentation. We study a specific model based on a very general measure between discrete probability distributions. We show experimentally that this model is competitive with some other models of the state of the art. In this work we use a particular case of the the measure of kind(@a@b@c@d) between two discrete probability distributions.

Bayesian Scheme for Interactive Colourization, Recolourization and Image/Video Editing

We propose a general image and video editing method based on a Bayesian segmentation framework. In the first stage, classes are established from scribbles made by a user on the image. These scribbles can be considered as a multi‐map (multi‐label map) that defines the boundary conditions of a probability measure field to be computed for each pixel. In the second stage, the global minima of a positive definite quadratic cost function with linear constraints, is calculated to find the probability measure field. The components of such a probability measure field express the degree of each pixel belonging to spatially smooth classes. Finally, the computed probabilities (memberships) are used for defining the weights of a linear combination of user provided colours or effects associated to each class. The proposed method allows the application of different operators, selected interactively by the user, over part or the whole image without needing to recompute the memberships. We present applications to colourization, recolourization, editing and photomontage tasks.

A Multi-Disciplinary Approach to Remote Sensing through Low-Cost UAVs

The use of Unmanned Aerial Vehicles (UAVs) based on remote sensing has generated low cost monitoring, since the data can be acquired quickly and easily. This paper reports the experience related to agave crop analysis with a low cost UAV. The data were processed by traditional photogrammetric flow and data extraction techniques were applied to extract new layers and separate the agave plants from weeds and other elements of the environment. Our proposal combines elements of photogrammetry, computer vision, data mining, geomatics and computer science. This fusion leads to very interesting results in agave control. This paper aims to demonstrate the potential of UAV monitoring in agave crops and the importance of information processing with reliable data flow.