Ehsan Amid

A kernel-learning approach to semi-supervised clustering with relative distance comparisons

We consider the problem of clustering a given dataset into k clusters subject to an additional set of constraints on relative distance comparisons between the data items. The additional constraints are meant to reflect side-information that is not expressed in the feature vectors, directly. Relative comparisons can express structures at finer level of detail than must-link (ML) and cannot-link (CL) constraints that are commonly used for semi-supervised clustering. Relative comparisons are particularly useful in settings where giving an ML or a CL constraint is difficult because the granularity of the true clustering is unknown. Our main contribution is an efficient algorithm for learning a kernel matrix using the log determinant divergence (a variant of the Bregman divergence) subject to a set of relative distance constraints. Given the learned kernel matrix, a clustering can be obtained by any suitable algorithm, such as kernel k-means. We show empirically that kernels found by our algorithm yield clusterings of higher quality than existing approaches that either use ML/CL constraints or a different means to implement the supervision using relative comparisons.

Unsupervised feature extraction for multimedia event detection and ranking using audio content

In this paper, we propose a new approach to classify and rank multimedia events based purely on audio content using video data from TRECVID-2013 multimedia event detection (MED) challenge. We perform several layers of nonlinear mappings to extract a set of unsupervised features from an initial set of temporal and spectral features to obtain a superior presentation of the atomic audio units. Additionally, we propose a novel weighted divergence measure for kernel based classifiers. The extensive set of experiments confirms that augmentation of the proposed steps results in an improved accuracy for most of the event classes.

A fast method of steel surface defect detection using decision trees applied to LBP based features

Surface defect detection plays a significant role in quality enhancement in steel manufacturing. Support Vector Machines and neural networks are the most popular classifiers in this application. Decision trees are also known as other classifiers for steel defect detection yielding a fast but moderate performance. In this paper, we introduce a more accurate classification method by using decision trees and applying Principal Component Analysis (PCA) and Bootstrap Aggregating (Bagging) on features being extracted by a local binary pattern based operator. This methodology yields an enhanced accuracy and reinstates decision trees as fast and accurate classifiers for two-class classification of steel surface defects. In order to have a complete classification in a real-time automatic surface inspection, a multiclass Support Vector Machine should be cascaded to the decision tree classifier. The proposed classification system is considerably faster than the traditional schemes.

Bayesian Non-parametric Image Segmentation with Markov Random Field Prior

In this paper, a Bayesian framework for non-parametric density estimation with spatial smoothness constraints is presented for image segmentation. Unlike common parametric methods such as mixtures of Gaussians, the proposed method does not make strict assumptions about the shape of the density functions and thus, can handle complex structures. The multiclass kernel density estimation is considered as an unsupervised learning problem. A Dirichlet compound multinomial (DCM) prior is used to model the class label prior probabilities and a Markov random field (MRF) is exploited to impose the spatial smoothness and control the confidence on the Dirichlet hyper-parameters, as well. The proposed model results in a closed form solution using an expectation-maximization (EM) algorithm for maximum a posteriori (MAP) estimation. This provides a huge advantage over other models which utilize more complex and time consuming methods such as Markov chain Monte Carlo (MCMC) or variational approximation methods. Several experiments on natural images are performed to present the performance of the proposed model compared to other parametric approaches.