Raul Queiroz Feitosa

A new covariance estimate for Bayesian classifiers in biometric recognition

In many biometric pattern-recognition problems, the number of training examples per class is limited, and consequently the sample group covariance matrices often used in parametric and nonparametric Bayesian classifiers are poorly estimated or singular. Thus, a considerable amount of effort has been devoted to the design of other covariance estimators, for use in limited-sample and high-dimensional classification problems. In this paper, a new covariance estimate, called the maximum entropy covariance selection (MECS) method, is proposed. It is based on combining covariance matrices under the principle of maximum uncertainty. In order to evaluate the MECS effectiveness in biometric problems, experiments on face, facial expression, and fingerprint classification were carried out and compared with popular covariance estimates, including the regularized discriminant analysis and leave-one-out covariance for the parametric classifier, and the Van Ness and Toeplitz covariance estimates for the nonparametric classifier. The results show that, in image recognition applications whenever the sample group covariance matrices are poorly estimated or ill posed, the MECS method is faster and usually more accurate than the aforementioned approaches in both parametric and nonparametric Bayesian classifiers.

Conditional Random Fields for Multitemporal and Multiscale Classification of Optical Satellite Imagery

In this paper, we present a method for the multitemporal and contextual classification of georeferenced optical remote sensing images acquired at different epochs and having different geometrical resolutions. The method is based on Conditional Random Fields (CRFs) for contextual classification. The CRF model is expanded by temporal interaction terms that link neighboring epochs via transition probabilities between different classes. In order to be able to deal with data of different resolution, the class structure at different epochs may vary with the resolution. The goal of the multitemporal classification is an improved classification performance at all individual epochs, but also the detection of land-cover changes, possibly using lower resolution data. This paper also contains a comparison of the performance of different models for the interaction potentials. Results are given for two different test sites in Germany, where Ikonos, RapidEye, and Landsat images are available. Our results show that the multitemporal classification does indeed increase the overall accuracy of all epochs compared to a monotemporal classification and to a state-of-the-art multitemporal classification method, and that it is feasible to detect changes in lower resolution images.

Design of radial basis function network as classifier in face recognition using eigenfaces

In this paper we investigate alternative designs of a radial basis function network acting as classifier in a face recognition system. The inputs to the RBF network are the projections of a face image over the principal components. A database of 250 facial images of 25 persons is used for training and evaluation. Two RBF designs are studied: the forward selection and the Gaussian mixture model. Both designs are also compared to the conventional Euclidean and Mahalanobis classifiers. A set of experiments evaluates the recognition rate of each method as a function of the number of principal components used to characterize the image samples. The results of the experiments indicate that the Gaussian mixture model RBF achieves the best performance while allowing less neurons in the hidden layer. The Gaussian mixture model approach shows also to be less sensitive to the choice of the training set.

Assessment of Binary Coding Techniques for Texture Characterization in Remote Sensing Imagery

This letter investigates the use of rotation invariant descriptors based on Local Binary Patterns (LBP) and Local Phase Quantization (LPQ) for texture characterization in the context of land-cover and land-use classification of Remote Sensing (RS) optical image data. Very high resolution images from the IKONOS-2 and Quickbird-2 orbital sensor systems covering different urban study areas were subjected to classification through an object-based approach. The experiments showed that the discrimination capacity of LBP and LPQ descriptors substantially increased when combined with contrast information. This work also proposes a novel texture descriptors assembled through the concatenation of the histograms of either LBP or LPQ descriptors and of the local variance estimates. Experimental analysis demonstrated that the proposed descriptors, though more compact, preserved the discrimination capacity of bi-dimensional histograms representing the joint distribution of textural descriptors and contrast information. Finally, the paper compares the discrimination capacity of the LBP- and LPQ-based textural descriptors with that of features derived from the Gray Level Co-occurrence Matrices (GLCM). The related experiments revealed a noteworthy superiority of LBP and LPQ descriptors over the GLCM features in the context of RS image data classification.

A Region-Growing Segmentation Algorithm for GPUs

This letter proposes a parallel version for graphics processing units (GPU) of a region-growing image segmentation algorithm widely used by the geographic object-based image analysis (GEOBIA) community. Initially, all image pixels are considered as seeds or primitive segments. Fine-grained parallel threads assigned to individual pixels merge adjacent segments iteratively always ensuring to minimize the overall heterogeneity increase. Besides spectral features the merging criterion considers morphological features that can be efficiently computed in the underlying GPU architecture. Two alternatives using different merging criteria are proposed and tested. An experimental analysis upon five different test images has shown that the parallel algorithm may run up to 19 times faster than its sequential counterpart.

Urban Area Extent Extraction in Spaceborne HR and VHR Data Using Multi-Resolution Features

Detection of urban area extents by means of remotely sensed data is a difficult task, especially because of the multiple, diverse definitions of what an “urban area” is. The models of urban areas listed in technical literature are based on the combination of spectral information with spatial patterns, possibly at different spatial resolutions. Starting from the same data set, “urban area” extraction may thus lead to multiple outputs. If this is done in a well-structured framework, however, this may be considered as an advantage rather than an issue. This paper proposes a novel framework for urban area extent extraction from multispectral Earth Observation (EO) data. The key is to compute and combine spectral and multi-scale spatial features. By selecting the most adequate features, and combining them with proper logical rules, the approach allows matching multiple urban area models. Experimental results for different locations in Brazil and Kenya using High-Resolution (HR) data prove the usefulness and flexibility of the framework.

A knowledge-based, transferable approach for block-based urban land-use classification

In this work we propose a knowledge-based approach for land-use classification of city blocks through the automatic interpretation of very-high-resolution remote-sensing imagery. Our approach is founded on geographic object-based image analysis (GEOBIA) concepts and is concerned with transferability across distinct knowledge representation formalisms. This paper therefore investigates the viability of translating a high-level description of the interpretation problem into the particular knowledge representation structures and interpretation strategies of two different software platforms, namely the proprietary Definiens Developer system and the open-source InterIMAGE system. Initially, textual descriptions of the land-use classes of interest were created by photo interpreters. Then, generic class descriptions were defined as a system-independent knowledge model, which was subsequently translated into interpretation projects in the different systems. Altogether 49 blocks located on two different test-sites in the city of São Paulo (Brazil) were considered in the experiments. Although the classification results from the Definiens Developer system were slightly better than those obtained with the InterIMAGE system, we concluded that both systems have been shown to be equally qualified to implement the target application properly through adaptation of the generic knowledge model.

A New Cloud Computing Architecture for the Classification of Remote Sensing Data

This paper proposes a new distributed architecture for supervised classification of large volumes of earth observation data on a cloud computing environment. The architecture supports distributed execution, network communication, and fault tolerance in a transparent way to the user. The architecture is composed of three abstraction layers, which support the definition and implementation of applications by researchers from different scientific investigation fields. The implementation of architecture is also discussed. A software prototype (available online), which runs machine learning routines implemented on the cloud using the Waikato Environment for Knowledge Analysis (WEKA), a popular free software licensed under the GNU General Public License, is used for validation. Performance issues are addressed through an experimental analysis in which two supervised classifiers available in WEKA were used: random forest and support vector machines. This paper further describes how to include other classification methods in the available software prototype

An object-based image analysis approach based on independent segmentations

Geographic Object-Based Image Analysis (GEOBIA) makes it possible to exploit a number of new features in the remote sensing image classification process. Such possibility is brought by the introduction of a segmentation step in the analysis process. The new features refer to aggregated spectral pixel values, textural, morphological and topological features computed for the different image segments. The usual segmentation approach in GEOBIA works relies on a hierarchy of segmentations, each level related to a number of object classes that have similar sizes, i.e., are detectable in a similar scale. We, therefore, propose an approach founded on the assumption that if segmentations are not specialized for each object class, then many of the new segment features cannot be properly exploited in the classification process. The proposed approach relies on a specific rule to solve eventual spatial conflicts among different segmentations. Preliminary experimental results show that the proposed approach performed better that the usual one.

Towards distributed region growing image segmentation based on MapReduce

Image segmentation is a critical step in image analysis, and usually involves a high computational cost, especially when dealing with large volumes of data. Given the significant increase in the spatial, spectral and temporal resolutions of remote sensing imagery in the last years, current sequential and parallel solutions fail to deliver the expected performance and scalability. This work proposes a scalable and efficient segmentation method, capable of handling efficiently very large high resolution images. The proposed solution is based on the MapReduce model, which offers a highly scalable and reliable framework for storing and processing massive data in cloud computing environments. The solution was implemented and validated using the Hadoop platform. Experimental results attest the viability of performing region growing segmentation in the MapReduce framework.