Michal Haindl

Bidirectional Texture Function Modeling: A State of the Art Survey

An ever-growing number of real-world computer vision applications require classification, segmentation, retrieval, or realistic rendering of genuine materials. However, the appearance of real materials dramatically changes with illumination and viewing variations. Thus, the only reliable representation of material visual properties requires capturing of its reflectance in as wide range of light and camera position combinations as possible. This is a principle of the recent most advanced texture representation, the bidirectional texture function (BTF). Multispectral BTF is a seven-dimensional function that depends on view and illumination directions as well as on planar texture coordinates. BTF is typically obtained by measurement of thousands of images covering many combinations of illumination and viewing angles. However, the large size of such measurements has prohibited their practical exploitation in any sensible application until recently. During the last few years, the first BTF measurement, compression, modeling, and rendering methods have emerged. In this paper, we categorize, critically survey, and psychophysically compare such approaches, which were published in this newly arising and important computer vision and graphics area.

Hierarchical Multiple Markov Chain Model for Unsupervised Texture Segmentation

In this paper, we present a novel multiscale texture model and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled, in turn, by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The ldquofragmentationrdquo step allows one to find the elementary textures of the model, while the ldquoreconstructionrdquo step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural and remote sensing images.

Texture segmentation benchmark

The Prague texture segmentation data-generator and benchmark is a Web based (http://mosaic.utia.cas.cz) service designed to mutually compare and rank different texture segmenters, and to support new segmentation and classification methods development. The benchmark verifies their performance characteristics on monospectral, multispectral, bidirectional texture function (BTF) data and enables to test their noise robustness, scale, and rotation or illumination invariance. It can easily be used for other applications such as feature selection, image compression, and query by pictorial example, etc. The benchmark functionalities are demonstrated on five previously published image segmentation algorithms evaluation.

Conditional mutual information based feature selection for classification task

We propose a sequential forward feature selection method to find a subset of features that are most relevant to the classification task. Our approach uses novel estimation of the conditional mutual information between candidate feature and classes, given a subset of already selected features which is utilized as a classifier independent criterion for evaluation of feature subsets. The proposed mMIFS-U algorithm is applied to text classification problem and compared with MIFS method and MIFS-U method proposed by Battiti and Kwak and Choi, respectively. Our feature selection algorithm outperforms MIFS method and MIFS-U in experiments on high dimensional Reuters textual data.

Computer-Aided Evaluation of Screening Mammograms Based on Local Texture Models

We propose a new approach to diagnostic evaluation of screening mammograms based on local statistical texture models. The local evaluation tool has the form of a multivariate probability density of gray levels in a suitably chosen search window. First, the density function in the form of Gaussian mixture is estimated from data obtained by scanning of the mammogram with the search window. Then we evaluate the estimated mixture at each position and display the corresponding log-likelihood value as a gray level at the window center. The resulting log-likelihood image closely correlates with the structural details of the original mammogram and emphasizes unusual places. We assume that, in parallel use, the log-likelihood image may provide additional information to facilitate the identification of malignant lesions as untypical locations of high novelty.

Feature selection based on mutual correlation

Feature selection is a critical procedure in many pattern recognition applications. There are two distinct mechanisms for feature selection namely the wrapper methods and the filter methods. The filter methods are generally considered inferior to wrapper methods, however wrapper methods are computationally more demanding than filter methods. A novel filter feature selection method based on mutual correlation is proposed. We assess the classification performance of the proposed filter method by using the selected features to the Bayes classifier. Alternative filter feature selection methods that optimize either the Bhattacharrrya distance or the divergence are also tested. Furthermore, wrapper feature selection techniques employing several search strategies such as the sequential forward search, the oscillating search, and the sequential floating forward search are also included in the comparative study. A trade off between the classification accuracy and the feature set dimensionality is demonstrated on both two benchmark datasets from UCI repository and two emotional speech data collections.

Extreme Compression and Modeling of Bidirectional Texture Function

The recent advanced representation for realistic real-world materials in virtual reality applications is the bidirectional texture function (BTF), which describes rough texture appearance for varying illumination and viewing conditions. Such a function can be represented by thousands of measurements (images) per material sample. The resulting BTF size excludes its direct rendering in graphical applications and some compression of these huge BTF data spaces is obviously inevitable. In this paper, we present a novel, fast probabilistic model-based algorithm for realistic BTF modeling allowing an extreme compression with the possibility of a fast hardware implementation. Its ultimate aim is to create a visual impression of the same material without a pixelwise correspondence to the original measurements. The analytical step of the algorithm starts with a BTF space segmentation and a range map estimation by photometric stereo of the BTF surface, followed by the spectral and spatial factorization of selected subspace color texture images. Single mono-spectral band-limited factors are independently modeled by their dedicated spatial probabilistic model. During rendering, the subspace images of arbitrary size are synthesized and both color (possibly multispectral) and range information is combined in a bump-mapping filter according to the view and illumination directions. The presented model offers a huge BTF compression ratio unattainable by any alternative sampling-based BTF synthesis method. Simultaneously, this model can be used to reconstruct missing parts of the BTF measurement space.

Model-Based Texture Segmentation

An efficient and robust type of unsupervised multispectral texture segmentation method is presented. Single decorrelated monospectral texture factors are assumed to be represented by a set of local Gaussian Markov random field (GMRF) models evaluated for each pixel centered image window and for each spectral band. The segmentation algorithm based on the underlying Gaussian mixture (GM) model operates in the decorrelated GMRF parametric space. The algorithm starts with an oversegmented initial estimation which is adaptively modified until the optimal number of homogeneous texture segments is reached.

A Multiresolution Causal Colour Texture Model

An efficient recursive algorithm for realistic colour texture synthesis is proposed. The algorithm starts with spectral factorization of an input colour texture image using the Karhunen-Loeve decorrelation. Single orthogonal monospectral components are further decomposed into a multi-resolution grid and each resolution data are independently modeled by their dedicated simultaneous causal autoregressive random field model (CAR). We estimate an optimal contextual neighbourhood and parameters for each CAR submodel. Finally single synthesized monos-pectral texture pyramids are collapsed into the fine resolution images and using the inverse Karhunen-Loeve transformation we obtain the required colour texture. The benefit of the multigrid approach is the replacement of a large neighbourhood CAR model with a set of several simpler CAR models which are easy to synthesize and wider application area of these multigrid models capable of reproducing realistic textures for enhancing realism in texture application areas.

Unsupervised detection of non-iris occlusions

Accurate iris defect detection.Unconstrained mobile devices high resolution color iris images.Multispectral Markovian spatial texture model.Ranked first from the 97+1 recent Noisy Iris Challenge Evaluation contest alternative methods.Promising performance on the very challenging, high resolution, and highly variable Mobile Iris Challenge Evaluation data. Display Omitted This paper presents a fast precise unsupervised iris defects detection method based on the underlying multispectral spatial probabilistic iris textural model and adaptive thresholding applied to demanding high resolution mobile device measurements. The accurate detection of iris eyelids and reflections is the prerequisite for the accurate iris recognition, both in near-infrared or visible spectrum measurements. The model adaptively learns its parameters on the iris texture part and subsequently checks for iris reflections using the recursive prediction analysis. The method is developed for color eye images from unconstrained mobile devices but it was also successfully tested on the UBIRIS v2 eye database. Our method ranked first from the 97+1 recent Noisy Iris Challenge Evaluation contest alternative methods on this large color iris database using the exact contest data and methodology.