LCMine: An efficient algorithm for mining discriminative regularities and its application in supervised classification

In this paper, we introduce an efficient algorithm for mining discriminative regularities on databases with mixed and incomplete data. Unlike previous methods, our algorithm does not apply an a priori discretization on numerical features; it extracts regularities from a set of diverse decision trees, induced with a special procedure. Experimental results show that a classifier based on the regularities obtained by our algorithm attains higher classification accuracy, using fewer discriminative regularities than those obtained by previous pattern-based classifiers. Additionally, we show that our classifier is competitive with traditional and state-of-the-art classifiers.     

A graph-theoretical clustering method based on two rounds of minimum spanning trees

Many clustering approaches have been proposed in the literature, but most of them are vulnerable to the different cluster sizes, shapes and densities. In this paper, we present a graph-theoretical clustering method which is robust to the difference. Based on the graph composed of two rounds of minimum spanning trees (MST), the proposed method (2-MSTClus) classifies cluster problems into two groups, i.e. separated cluster problems and touching cluster problems, and identifies the two groups of cluster problems automatically. It contains two clustering algorithms which deal with separated clusters and touching clusters in two phases, respectively. In the first phase, two round minimum spanning trees are employed to construct a graph and detect separated clusters which cover distance separated and density separated clusters. In the second phase, touching clusters, which are subgroups produced in the first phase, can be partitioned by comparing cuts, respectively, on the two round minimum spanning trees. The proposed method is robust to the varied cluster sizes, shapes and densities, and can discover the number of clusters. Experimental results on synthetic and real datasets demonstrate the performance of the proposed method.     

Semantic fusion of laser and vision in pedestrian detection

Fusion of laser and vision in object detection has been accomplished by two main approaches: (1) independent integration of sensor-driven features or sensor-driven classifiers, or (2) a region of interest (ROI) is found by laser segmentation and an image classifier is used to name the projected ROI. Here, we propose a novel fusion approach based on semantic information, and embodied on many levels. Sensor fusion is based on spatial relationship of parts-based classifiers, being performed via a Markov logic network. The proposed system deals with partial segments, it is able to recover depth information even if the laser fails, and the integration is modeled through contextual information—characteristics not found on previous approaches. Experiments in pedestrian detection demonstrate the effectiveness of our method over data sets gathered in urban scenarios.     

A level set method based on the Bayesian risk for medical image segmentation

This paper proposes an alternative criterion derived from the Bayesian risk classification error for image segmentation. The proposed model introduces a region-based force determined through the difference of the posterior image densities for the different classes, a term based on the prior probability derived from Kullback-Leibler information number, and a regularity term adopted to avoid the generation of excessively irregular and small segmented regions. Compared with other level set methods, the proposed approach relies on the optimum decision of pixel classification and the estimates of prior probabilities; thus the approach has more reliability in theory and practice. Experiments show that the proposed approach is able to extract the complicated shapes of targets and robust for various types of medical images. Moreover, the algorithm can be easily extendable for multiphase segmentation.     

Hierarchical vibrations for part-based recognition of complex objects

We propose a technique for the recognition and segmentation of complex shapes in 2D images using a hierarchy of finite element vibration modes in an evolutionary shape search. The different levels of the shape hierarchy can influence each other, which can be exploited in top-down part-based image analysis. Our method overcomes drawbacks of existing structural approaches, which cannot uniformly encode shape variation and co-variation, or rely on training. We present results demonstrating that by utilizing a quality-of-fit function the model explicitly recognizes missing parts of a complex shape, thus allowing for categorization between shape classes.     

On minimum class locality preserving variance support vector machine

In this paper, a so-called minimum class locality preserving variance support machine (MCLPV_SVM) algorithm is presented by introducing the basic idea of the locality preserving projections (LPP), which can be seen as a modified class of support machine (SVM) and/or minimum class variance support machine (MCVSVM). MCLPV_SVM, in contrast to SVM and MCVSVM, takes the intrinsic manifold structure of the data space into full consideration and inherits the characteristics of SVM and MCVSVM. We discuss in the paper the linear case, the small sample size case and the nonlinear case of the MCLPV_SVM. Similar to MCVSVM, the MCLPV_SVM optimization problem in the small sample size case is solved by using dimensionality reduction through principal component analysis (PCA) and one in the nonlinear case is transformed into an equivalent linear MCLPV_SVM problem under kernel PCA (KPCA). Experimental results on real datasets indicate the effectiveness of the MCLPV_SVM by comparing it with SVM and MCVSVM.     

Semi-automatic dynamic auxiliary-tag-aided image annotation

Image annotation is the foundation for many real-world applications. In the age of Web 2.0, image search and browsing are largely based on the tags of images. In this paper, we formulate image annotation as a multi-label learning problem, and develop a semi-automatic image annotation system. The presented system chooses proper words from a vocabulary as tags for a given image, and refines the tags with the help of the user's feedback. The refinement amounts to a novel multi-label learning framework, named Semi-Automatic Dynamic Auxiliary-Tag-Aided (SADATA), in which the classification result for one certain tag (target tag) can be boosted by the classification results of a subset of the other tags (auxiliary tags). The auxiliary tags, which have strong correlations with the target tag, are determined in terms of the normalized mutual information. We only select those tags whose correlations exceed a threshold as the auxiliary tags, so the auxiliary set is sparse. How much an auxiliary tag can contribute is dependent on the image, so we also build a probabilistic model conditioned on the auxiliary tag and the input image to adjust the weight of the auxiliary tag dynamically. For an given image, the user feedback on the tags corrects the outputs of the auxiliary classifiers and SADATA will recommend more proper tags next round. SADATA is evaluated on a large collection of Corel images. The experimental results validate the effectiveness of our dynamic auxiliary-tag-aided method. Furthermore, the performance also benefits from user feedbacks such that the annotation procedure can be significantly speeded up.     

An improved method for voice pathology detection by means of a HMM-based feature space transformation

This paper presents new a feature transformation technique applied to improve the screening accuracy for the automatic detection of pathological voices. The statistical transformation is based on Hidden Markov Models, obtaining a transformation and classification stage simultaneously and adjusting the parameters of the model with a criterion that minimizes the classification error. The original feature vectors are built up using classic short-term noise parameters and mel-frequency cepstral coefficients. With respect to conventional approaches found in the literature of automatic detection of pathological voices, the proposed feature space transformation technique demonstrates a significant improvement of the performance with no addition of new features to the original input space. In view of the results, it is expected that this technique could provide good results in other areas such as speaker verification and/or identification.     

Action categorization with modified hidden conditional random field

In this paper, we present a method for action categorization with a modified hidden conditional random field (HCRF). Specifically, effective silhouette-based action features are extracted using motion moments and spectrum of chain code. We formulate a modified HCRF (mHCRF) to have a guaranteed global optimum in the modelling of the temporal action dependencies after the HMM pathing stage. Experimental results on action categorization using this model are compared favorably against several existing model-based methods including GMM, SVM, Logistic Regression, HMM, CRF and HCRF.     

Continuous force field analysis for generalized gradient vector flow field

We propose a modification of the generalized gradient vector flow field techniques based on a continuous force field analysis. At every iteration the generalized gradient vector flow method obtains a new, improved vector field. However, the numerical procedure always employs the original image to calculate the gradients used in the source term. The basic idea developed in this paper is to use the resulting vector field to obtain an improved edge map and use it to calculate a new gradient based source term. The improved edge map is evaluated by new continuous force field analysis techniques inspired by a preceding discrete version. The approach leads to a better convergence and better segmentation accuracy as compared to several conventional gradient vector flow type methods.