P. Baylou

An efficient algorithm for computation of shape moments from run-length codes or chain codes

Abstract Moments are very useful for shape analysis. Zero- to third-order moments have been used for computer vision applications such as shape recognition and orientation. They can serve for composition of the well-known moment invariants used as desirable features as well as for the detection of the location and the principal axis direction of a shape. The shape is often represented by a binary image and its moments can be obtained by use of fast algorithms considering the shape as a discrete point array. In this paper a new algorithm based on the double-integral formulation is presented. The shape is considered as a continuous region and the contribution of boundary points is used for fast computation of shape moments. This method can be used to calculate moments from either the run-length codes or the chain codes of shape.

Multiscale estimation of vector field anisotropy application to texture characterization

This paper deals with the characterization of the anisotropy of textured images. It is well known that either the dominant direction or the texture anisotropy strongly depends on the scale used for the observation. In this paper we propose a new operator for the estimation of the dominant direction, the directional mean vector (DMV), which can be computed at any observation scale. Then, we present a new indicator for the estimation of the DMV field anisotropy. This indicator, called Iso, is computed at a given observation scale. Iso is based on the computation of the DMV field local differences. It is shown that the evolution of Iso versus the observation scale gives a curve which simultaneously characterizes the anisotropy of the texture and the size of the textural patterns. In order to establish this property, we build a specific texture model which allows to assess an analytical expression for Iso. Finally, Iso is applied to the characterization of various images including synthetic textures, Brodatz textures and composite material images.

Flow coherence diffusion. linear and nonlinear case

The paper proposes a novel tensor based diffusion filter, dedicated for filtering images composed of line like structures. We propose a linear version of nonlinear diffusion partial derivative equation, previously presented in [5]. Instead of considering nonlinearity in the image evolution process we are only including it at the computation of the diffusion tensor. The unique tensor construction is based on an adaptive orientation estimation step and yields a significant reduction of the computational complexity. The properties of the filter are analyzed both theoretically and experimentally.

New operators for optimized orientation estimation

This paper focuses on directional textures. It provides a new framework for the design of convolution masks dedicated to orientation estimation. We propose a new technique based on the combination of two complementary operators: a gradient-based operator which is adapted to sloped regions and a valleyness detector which fits the crests and valleys. On each operator, a double optimization procedure is carried out with respect to bias and noise sensitivity reduction. The procedure is generic and applies to any kind of underlying directional texture. Experiments on a synthetic sine wave texture and on natural textures are provided and show the efficiency and the relevance of our approach.

Multiscale estimation of textural features. Application to the characterization of texture anisotropy

This paper deals with the characterization of textures. It focuses on textural properties based on the local differences of attributes, such as homogeneity and orientation. We introduce the scaled scattering indicator (SSI) in order to estimate such textural properties. SSI is computed at various observation scales to take into account micro-textures as well as macro-textures involved in pictures. We establish the theoretical behavior of SSI in the case of a pavement filled with a given textural pattern. We devote this indicator to the multiscale characterization of the anisotropy of pictures. Simulation results on synthetic and real pictures confirm the the theoretical approach we have provided: SSI provides an accurate estimation of textural properties like anisotropy, but also gives an estimation of the size of the textural patterns involved in the picture.

Local multiple orientation estimation: isotropic and recursive oriented network

In this paper, we propose a new operator for texture orientation estimation. We focus on directional textures which can have more than a single orientation at the same point. Our operator consists in a steerable network of parallel lines along which a homogeneity feature is computed in the spatial domain. The analysis of the network response along each direction allows us to set up the presence of single or multiple orientations. In order to reduce the computing cost, we propose a recursive implementation of our operator, thanks to the rotations of the image instead of the rotation of the network. Our operator works on a small support, and thus provides a local estimation of the orientations. Results obtained both with synthetic textures and natural images are accurate and show the selectivity and the isotropic behaviour of our operator.

Level curve tracking algorithm for textural feature extraction

Topographic approaches are often used in the framework of texture characterization. More particularly, level curves proved to be interesting features to describe textures containing elongated patterns. Here, we provide an algorithm for level curve tracking based on a step by step propagation of a level set from a pixel to its neighbors. Textural feature extraction is then considered; orientation and pattern length measurement techniques are proposed. Pattern length retrieval is then exercised on composite material images taken from transmission electron microscopy.

Line orientation operator

This paper proposes new estimators for the local orientation of elongated structures. Classical methods derive local orientation from the argument of gradient estimator. As they were originally designed for edge detection, such operators can lead to high bias in orientation estimation. We introduce the line orientation operator which applies an oriented model made with straight parallel lines on the local neighborhood. We present results either on synthetic and real images. We compare this new operator with other classical orientation operators.

Assessment of Texture Stationarity Using the Asymptotic Behavior of the Empirical Mean and Variance

Given textured images considered as realizations of 2-D stochastic processes, a framework is proposed to evaluate the stationarity of their mean and variance. Existing strategies focus on the asymptotic behavior of the empirical mean and variance (respectively EM and EV), known for some types of nondeterministic processes. In this paper, the theoretical asymptotic behaviors of the EM and EV are studied for large classes of second-order stationary ergodic processes, in the sense of the Wold decomposition scheme, including harmonic and evanescent processes. Minimal rates of convergence for the EM and the EV are derived for these processes; they are used as criteria for assessing the stationarity of textures. The experimental estimation of the rate of convergence is achieved using a nonparametric block sub-sampling method. Our framework is evaluated on synthetic processes with stationary or nonstationary mean and variance and on real textures. It is shown that anomalies in the asymptotic behavior of the empirical estimators allow detecting nonstationarities of the mean and variance of the processes in an objective way.

Orientation difference statistics for texture description

This paper presents a new approach for the description of directional textures based on the study of their orientation and coherence fields. We apply the feature-based interaction maps to the characterization of an orientation field. The features are extracted from orientation spatial difference histograms. The representation of a feature, as a function of the spacing vector used to compute the spatial statistics, yields a 2-D interaction map which can be used to assess the structural layout of texture. Orientation-based interaction maps are exercised on original and distorted Brodatz textures. The results show the relevance and the robustness of the approach for the description of directional textures.