Showing papers on "Feature (computer vision) published in 2009"

An HOG-LBP human detector with partial occlusion handling

Abstract: By combining Histograms of Oriented Gradients (HOG) and Local Binary Pattern (LBP) as the feature set, we propose a novel human detection approach capable of handling partial occlusion. Two kinds of detectors, i.e., global detector for whole scanning windows and part detectors for local regions, are learned from the training data using linear SVM. For each ambiguous scanning window, we construct an occlusion likelihood map by using the response of each block of the HOG feature to the global detector. The occlusion likelihood map is then segmented by Mean-shift approach. The segmented portion of the window with a majority of negative response is inferred as an occluded region. If partial occlusion is indicated with high likelihood in a certain scanning window, part detectors are applied on the unoccluded regions to achieve the final classification on the current scanning window. With the help of the augmented HOG-LBP feature and the global-part occlusion handling method, we achieve a detection rate of 91.3% with FPPW= 10−6, 94.7% with FPPW= 10−5, and 97.9% with FPPW= 10−4 on the INRIA dataset, which, to our best knowledge, is the best human detection performance on the INRIA dataset. The global-part occlusion handling method is further validated using synthesized occlusion data constructed from the INRIA and Pascal dataset.

SBA: A software package for generic sparse bundle adjustment

Abstract: Bundle adjustment constitutes a large, nonlinear least-squares problem that is often solved as the last step of feature-based structure and motion estimation computer vision algorithms to obtain optimal estimates. Due to the very large number of parameters involved, a general purpose least-squares algorithm incurs high computational and memory storage costs when applied to bundle adjustment. Fortunately, the lack of interaction among certain subgroups of parameters results in the corresponding Jacobian being sparse, a fact that can be exploited to achieve considerable computational savings. This article presents sba, a publicly available C/C++ software package for realizing generic bundle adjustment with high efficiency and flexibility regarding parameterization.

On feature combination for multiclass object classification

Abstract: A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. While this is a necessity in order to generalize beyond a given set of training images, it is also a very difficult problem due to the high variability of visual appearance within each class. In the last years substantial performance gains on challenging benchmark datasets have been reported in the literature. This progress can be attributed to two developments: the design of highly discriminative and robust image features and the combination of multiple complementary features based on different aspects such as shape, color or texture. In this paper we study several models that aim at learning the correct weighting of different features from training data. These include multiple kernel learning as well as simple baseline methods. Furthermore we derive ensemble methods inspired by Boosting which are easily extendable to several multiclass setting. All methods are thoroughly evaluated on object classification datasets using a multitude of feature descriptors. The key results are that even very simple baseline methods, that are orders of magnitude faster than learning techniques are highly competitive with multiple kernel learning. Furthermore the Boosting type methods are found to produce consistently better results in all experiments. We provide insight of when combination methods can be expected to work and how the benefit of complementary features can be exploited most efficiently.

A comparison of random forest and its Gini importance with standard chemometric methods for the feature selection and classification of spectral data

Abstract: Regularized regression methods such as principal component or partial least squares regression perform well in learning tasks on high dimensional spectral data, but cannot explicitly eliminate irrelevant features. The random forest classifier with its associated Gini feature importance, on the other hand, allows for an explicit feature elimination, but may not be optimally adapted to spectral data due to the topology of its constituent classification trees which are based on orthogonal splits in feature space. We propose to combine the best of both approaches, and evaluated the joint use of a feature selection based on a recursive feature elimination using the Gini importance of random forests' together with regularized classification methods on spectral data sets from medical diagnostics, chemotaxonomy, biomedical analytics, food science, and synthetically modified spectral data. Here, a feature selection using the Gini feature importance with a regularized classification by discriminant partial least squares regression performed as well as or better than a filtering according to different univariate statistical tests, or using regression coefficients in a backward feature elimination. It outperformed the direct application of the random forest classifier, or the direct application of the regularized classifiers on the full set of features. The Gini importance of the random forest provided superior means for measuring feature relevance on spectral data, but – on an optimal subset of features – the regularized classifiers might be preferable over the random forest classifier, in spite of their limitation to model linear dependencies only. A feature selection based on Gini importance, however, may precede a regularized linear classification to identify this optimal subset of features, and to earn a double benefit of both dimensionality reduction and the elimination of noise from the classification task.

Activity recognition using the velocity histories of tracked keypoints

Abstract: We present an activity recognition feature inspired by human psychophysical performance. This feature is based on the velocity history of tracked keypoints. We present a generative mixture model for video sequences using this feature, and show that it performs comparably to local spatio-temporal features on the KTH activity recognition dataset. In addition, we contribute a new activity recognition dataset, focusing on activities of daily living, with high resolution video sequences of complex actions. We demonstrate the superiority of our velocity history feature on high resolution video sequences of complicated activities. Further, we show how the velocity history feature can be extended, both with a more sophisticated latent velocity model, and by combining the velocity history feature with other useful information, like appearance, position, and high level semantic information. Our approach performs comparably to established and state of the art methods on the KTH dataset, and significantly outperforms all other methods on our challenging new dataset.

Multi-task feature learning via efficient l 2, 1 -norm minimization

Abstract: The problem of joint feature selection across a group of related tasks has applications in many areas including biomedical informatics and computer vision. We consider the l2, 1-norm regularized regression model for joint feature selection from multiple tasks, which can be derived in the probabilistic framework by assuming a suitable prior from the exponential family. One appealing feature of the l2, 1-norm regularization is that it encourages multiple predictors to share similar sparsity patterns. However, the resulting optimization problem is challenging to solve due to the non-smoothness of the l2, 1-norm regularization. In this paper, we propose to accelerate the computation by reformulating it as two equivalent smooth convex optimization problems which are then solved via the Nesterov's method---an optimal first-order black-box method for smooth convex optimization. A key building block in solving the reformulations is the Euclidean projection. We show that the Euclidean projection for the first reformulation can be analytically computed, while the Euclidean projection for the second one can be computed in linear time. Empirical evaluations on several data sets verify the efficiency of the proposed algorithms.

Robust biomarker identification for cancer diagnosis using ensemble feature selection methods

Abstract: Motivation: Biomarker discovery is an important topic in biomedical applications of computational biology, including applications such as gene and SNP selection from high dimensional data. Surprisingly, the stability with respect to sampling variation or robustness of such selection processes has received attention only recently. However, robustness of biomarkers is an important issue, as it may greatly influence subsequent biological validations. In addition, a more robust set of markers may strengthen the confidence of an expert in the results of a selection method. Results: Our first contribution is a general framework for the analysis of the robustness of a biomarker selection algorithm. Secondly, we conducted a large-scale analysis of the recently introduced concept of ensemble feature selection, where multiple feature selections are combined in order to increase the robustness of the final set of selected features. We focus on selection methods that are embedded in the estimation of support vector machines (SVMs). SVMs are powerful classification models that have shown state-ofthe-art performance on several diagnosis and prognosis tasks on biological data. Their feature selection extensions also offered good results for gene selection tasks. We show that the robustness of SVMs for biomarker discovery can be substantially increased by using ensemble feature selection techniques, while at the same time improving upon classification performances. The proposed methodology is evaluated on four microarray data sets showing increases of up to almost 30% in robustness of the selected biomarkers, along with an improvement of about 15% in classification performance. The stability improvement with ensemble methods is particularly noticeable for small signature sizes (a few tens of genes), which is most relevant for the design of a diagnosis or prognosis model from a gene signature.

Bundling features for large scale partial-duplicate web image search

Abstract: In state-of-the-art image retrieval systems, an image is represented by a bag of visual words obtained by quantizing high-dimensional local image descriptors, and scalable schemes inspired by text retrieval are then applied for large scale image indexing and retrieval. Bag-of-words representations, however: 1) reduce the discriminative power of image features due to feature quantization; and 2) ignore geometric relationships among visual words. Exploiting such geometric constraints, by estimating a 2D affine transformation between a query image and each candidate image, has been shown to greatly improve retrieval precision but at high computational cost. In this paper we present a novel scheme where image features are bundled into local groups. Each group of bundled features becomes much more discriminative than a single feature, and within each group simple and robust geometric constraints can be efficiently enforced. Experiments in Web image search, with a database of more than one million images, show that our scheme achieves a 49% improvement in average precision over the baseline bag-of-words approach. Retrieval performance is comparable to existing full geometric verification approaches while being much less computationally expensive. When combined with full geometric verification we achieve a 77% precision improvement over the baseline bag-of-words approach, and a 24% improvement over full geometric verification alone.

Disease state prediction from resting state functional connectivity

Abstract: The application of multivoxel pattern analysis methods has attracted increasing attention, particularly for brain state prediction and real-time functional MRI applications. Support vector classification is the most popular of these techniques, owing to reports that it has better prediction accuracy and is less sensitive to noise. Support vector classification was applied to learn functional connectivity patterns that distinguish patients with depression from healthy volunteers. In addition, two feature selection algorithms were implemented (one filter method, one wrapper method) that incorporate reliability information into the feature selection process. These reliability feature selections methods were compared to two previously proposed feature selection methods. A support vector classifier was trained that reliably distinguishes healthy volunteers from clinically depressed patients. The reliability feature selection methods outperformed previously utilized methods. The proposed framework for applying support vector classification to functional connectivity data is applicable to other disease states beyond major depression.

Knowledge based reconstruction of building models from terrestrial laser scanning data

Abstract: This paper presents an automatic method for reconstruction of building facade models from terrestrial laser scanning data. Important facade elements such as walls and roofs are distinguished as features. Knowledge about the features’ sizes, positions, orientations, and topology is then introduced to recognize these features in a segmented laser point cloud. An outline polygon of each feature is generated by least squares fitting, convex hull fitting or concave polygon fitting, according to the size of the feature. Knowledge is used again to hypothesise the occluded parts from the directly extracted feature polygons. Finally, a polyhedron building model is combined from extracted feature polygons and hypothesised parts. The reconstruction method is tested with two data sets containing various building shapes.

Text feature selection using ant colony optimization

Abstract: Feature selection and feature extraction are the most important steps in classification systems. Feature selection is commonly used to reduce dimensionality of datasets with tens or hundreds of thousands of features which would be impossible to process further. One of the problems in which feature selection is essential is text categorization. A major problem of text categorization is the high dimensionality of the feature space; therefore, feature selection is the most important step in text categorization. At present there are many methods to deal with text feature selection. To improve the performance of text categorization, we present a novel feature selection algorithm that is based on ant colony optimization. Ant colony optimization algorithm is inspired by observation on real ants in their search for the shortest paths to food sources. Proposed algorithm is easily implemented and because of use of a simple classifier in that, its computational complexity is very low. The performance of proposed algorithm is compared to the performance of genetic algorithm, information gain and CHI on the task of feature selection in Reuters-21578 dataset. Simulation results on Reuters-21578 dataset show the superiority of the proposed algorithm.

Reasoning about edits to feature models

Abstract: Features express the variabilities and commonalities among programs in a software product line (SPL). A feature model defines the valid combinations of features, where each combination corresponds to a program in an SPL. SPLs and their feature models evolve over time. We classify the evolution of a feature model via modifications as refactorings, specializations, generalizations, or arbitrary edits. We present an algorithm to reason about feature model edits to help designers determine how the program membership of an SPL has changed. Our algorithm takes two feature models as input (before and after edit versions), where the set of features in both models are not necessarily the same, and it automatically computes the change classification. Our algorithm is able to give examples of added or deleted products and efficiently classifies edits to even large models that have thousands of features.

Long-lasting modulation of feature integration by transcranial magnetic stimulation

Abstract: The human brain analyzes a visual object first by basic feature detectors. On the objects way to a conscious percept, these features are integrated in subsequent stages of the visual hierarchy. The time course of this feature integration is largely unknown. To shed light on the temporal dynamics of feature integration, we applied transcranial magnetic stimulation (TMS) to a feature fusion paradigm. In feature fusion, two stimuli which differ in one feature are presented in rapid succession such that they are not perceived individually but as one single stimulus only. The fused percept is an integration of the features of both stimuli. Here, we show that TMS can modulate this integration for a surprisingly long period of time, even though the individual stimuli themselves are not consciously perceived. Hence, our results reveal a long-lasting integration process of unconscious feature traces.

Efficient representation of local geometry for large scale object retrieval

Abstract: State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local geometry is stored for each feature detected in each image and requires storage larger than the inverted file and term frequency and inverted document frequency weights together. We propose a novel method for learning discretized local geometry representation based on minimization of average reprojection error in the space of ellipses. The representation requires only 24 bits per feature without drop in performance. Additionally, we show that if the gravity vector assumption is used consistently from the feature description to spatial verification, it improves retrieval performance and decreases the memory footprint. The proposed method outperforms state of the art retrieval algorithms in a standard image retrieval benchmark.

Airborne lidar feature selection for urban classification using random forests

Abstract: Various multi-echo and Full-waveform (FW) lidar features can be processed. In this paper, multiple classifers are applied to lidar feature selection for urban scene classification. Random forests are used since they provide an accurate classification and run efficiently on large datasets. Moreover, they return measures of variable importance for each class. The feature selection is obtained by backward elimination of features depending on their importance. This is crucial to analyze the relevance of each lidar feature for the classification of urban scenes. The Random Forests classification using selected variables provide an overall accuracy of 94.35%.

Landmark classification in large-scale image collections

Abstract: With the rise of photo-sharing websites such as Facebook and Flickr has come dramatic growth in the number of photographs online. Recent research in object recognition has used such sites as a source of image data, but the test images have been selected and labeled by hand, yielding relatively small validation sets. In this paper we study image classification on a much larger dataset of 30 million images, including nearly 2 million of which have been labeled into one of 500 categories. The dataset and categories are formed automatically from geotagged photos from Flickr, by looking for peaks in the spatial geotag distribution corresponding to frequently-photographed landmarks. We learn models for these landmarks with a multiclass support vector machine, using vector-quantized interest point descriptors as features. We also explore the non-visual information available on modern photo-sharing sites, showing that using textual tags and temporal constraints leads to significant improvements in classification rate. We find that in some cases image features alone yield comparable classification accuracy to using text tags as well as to the performance of human observers.

CHoG: Compressed histogram of gradients A low bit-rate feature descriptor

Abstract: Establishing visual correspondences is an essential component of many computer vision problems, and is often done with robust, local feature-descriptors. Transmission and storage of these descriptors are of critical importance in the context of mobile distributed camera networks and large indexing problems. We propose a framework for computing low bit-rate feature descriptors with a 20× reduction in bit rate. The framework is low complexity and has significant speed-up in the matching stage. We represent gradient histograms as tree structures which can be efficiently compressed. We show how to efficiently compute distances between descriptors in their compressed representation eliminating the need for decoding. We perform a comprehensive performance comparison with SIFT, SURF, and other low bit-rate descriptors and show that our proposed CHoG descriptor outperforms existing schemes.

Trajectons: Action recognition through the motion analysis of tracked features

Abstract: The defining feature of video compared to still images is motion, and as such the selection of good motion features for action recognition is crucial, especially for bag of words techniques that rely heavily on their features. Existing motion techniques either assume that a difficult problem like background/foreground segmentation has already been solved (contour/silhouette based techniques) or are computationally expensive and prone to noise (optical flow). We present a technique for motion based on quantized trajectory snippets of tracked features. These quantized snippets, or trajectons, rely only on simple feature tracking and are computationally efficient. We demonstrate that within a bag of words framework trajectons can match state of the art results, slightly outperforming histogram of optical flow features on the Hollywood Actions dataset. Additionally, we present qualitative results in a video search task on a custom dataset of challenging YouTube videos.

Better matching with fewer features: The selection of useful features in large database recognition problems

Abstract: There has been recent progress on the problem of recognizing specific objects in very large datasets. The most common approach has been based on the bag-of-words (BOW) method, in which local image features are clustered into visual words. This can provide significant savings in memory compared to storing and matching each feature independently. In this paper we take an additional step to reducing memory requirements by selecting only a small subset of the training features to use for recognition. This is based on the observation that many local features are unreliable or represent irrelevant clutter. We are able to select “useful” features, which are both robust and distinctive, by an unsupervised preprocessing step that identifies correctly matching features among the training images. We demonstrate that this selection approach allows an average of 4% of the original features per image to provide matching performance that is as accurate as the full set. In addition, we employ a graph to represent the matching relationships between images. Doing so enables us to effectively augment the feature set for each image through merging of useful features of neighboring images. We demonstrate adjacent and 2-adjacent augmentation, both of which give a substantial boost in performance.

SAT-based analysis of feature models is easy

Abstract: Feature models are a popular variability modeling notation used in product line engineering. Automated analyses of feature models, such as consistency checking and interactive or offline product selection, often rely on translating models to propositional logic and using satisfiability (SAT) solvers.Efficiency of individual satisfiability-based analyses has been reported previously. We generalize and quantify these studies with a series of independent experiments. We show that previously reported efficiency is not incidental. Unlike with the general SAT instances, which fall into easy and hard classes, the instances induced by feature modeling are easy throughout the spectrum of realistic models. In particular, the phenomenon of phase transition is not observed for realistic feature models.Our main practical conclusion is a general encouragement for researchers to continued development of SAT-based methods to further exploit this efficiency in future.