Jesús V. Albert

Considerations about sample-size sensitivity of a family of edited nearest-neighbor rules

The edited nearest neighbor classification rules constitute a valid alternative to k-NN rules and other nonparametric classifiers. Experimental results with synthetic and real data from various domains and from different researchers and practitioners suggest that some editing algorithms (especially, the optimal ones) are very sensitive to the total number of prototypes considered. This paper investigates the possibility of modifying optimal editing to cope with a broader range of practical situations. Most previously introduced editing algorithms are presented in a unified form and their different properties (acid not just their asymptotic behavior) are intuitively analyzed. The results show the relative limits in the applicability of different editing algorithms.

The role of perceptual contrast non-linearities in image transform quantization

Abstract The conventional quantizer design based on average error minimization over a training set does not guarantee a good subjective behavior on individual images even if perceptual metrics are used. In this work a novel criterion for transform coder design is analyzed in depth. Its aim is to bound the perceptual distortion in each individual quantization according to a non-linear model of early human vision. A common comparison framework is presented to describe the qualitative behavior of the optimal quantizers under the proposed criterion and the conventional rate-distortion based criterion. Several underlying metrics, with and without perceptual non-linearities, are used with both criteria. Analytical results show that the proposed design criterion gives rise to a JPEG-like quantization if a simple linear metric is used. Experimental results show that significant improvements over the perceptually weighted rate-distortion approach are obtained if a more meaningful non-linear metric is used.

An online metric learning approach through margin maximization

This work introduces a method based on learning similarity measures between pairs of objects in any representation space that allows to develop convenient recognition algorithms. The problem is formulated through margin maximization over distance values so that it can discriminate between similar (intra-class) and dissimilar (inter-class) elements without enforcing positive definiteness of the metric matrix as in most competing approaches. A passive-aggressive approach has been adopted to carry out the corresponding optimization procedure. The proposed approach has been empirically compared to state of the art metric learning on several publicly available databases showing its potential both in terms of performance and computation results.

Comparative Evaluation of Batch and Online Distance Metric Learning Approaches Based on Margin Maximization

Distance metric learning aims at obtaining an appropriate metric that conveniently adapts to a particular recognition problem given a set of training pairs. The idea of maximizing a margin that separates similar and dissimilar objects has been used in different ways in several recent works. This paper considers two different learning schemes aiming at the same goal but posing the learning problem either as a batch or as an online formulation. Extensive experiments and the corresponding discussion try to put forward the advantages and drawbacks of each of the approaches considered.

Variable-size block matching algorithm for motion estimation using a perceptual-based splitting criterion

A variable-size block matching technique for motion estimation under the framework of perceptual coding is presented. It is well-known that fixed size block matching can be improved by using a multiresolution approach. It is shown that further improvement is possible both in terms of compactness and robustness of the predicted motion field if a perceptual criterion is used. This scheme is compared against other variable- and fixed-size block matching algorithms both from the point of view of final complexity of motion description and its robustness.

A Random Extension for Discriminative Dimensionality Reduction and Metric Learning

A recently proposed metric learning algorithm which enforces the optimal discrimination of the different classes is extended and empirically assessed using different kinds of publicly available data. The optimization problem is posed in terms of landmark points and then, a stochastic approach is followed in order to bypass some of the problems of the original algorithm. According to the results, both computational burden and generalization ability are improved while absolute performance results remain almost unchanged.

About Combining Metric Learning and Prototype Generation

Distance metric learning has been a major research topic in recent times. Usually, the problem is formulated as finding a Mahalanobis-like metric matrix that satisfies a set of constraints as much as possible. Different ways to introduce these constraints and to effectively formulate and solve the optimization problem have been proposed. In this work, we start with one of these formulations that leads to a convex optimization problem and generalize it in order to increase the efficiency by appropriately selecting the set of constraints. Moreover, the original criterion is expressed in terms of a reduced set of representatives that is learnt together with the metric. This leads to further improvements not only in efficiency but also in the quality of the obtained metrics.

Average-case analysis in an elementary course on algorithms

Average-case algorithm analysis is usually viewed as a tough subject by students in the first courses in Computer Science. Traditionally, these topics are fully developed in advanced courses with a clear mathematical orientation. The work presented here is not an alternative to this, but, it presents the analysis of algorithms (and average-case in particular) adapted to the mathematical background of students in an elementary course on Algorithms or Programming by using some specially selected examples.

Accurate Detection and Characterization of Corner Points Using Circular Statistics and Fuzzy Clustering

Accurate detection and characterization of corner points in grey level images is considered as a pattern recognition problem. The method considers circular statistic tests to detect 2D features. A fuzzy clustering algorithm is applied to the edge orientations near the prospective corners to detect and classify them. The method is based on formulating hypotheses about the distribution of these orientations around an edge, corner or other 2-D feature. The method may provide accurate estimates of the direction of the edges that converge in a corner, along with their confidence intervals. Experimental results show the method to be robust enough against noise and contrast changes. Fuzzy membership improves the results of the algorithm and both versions (crisp and fuzzy) give better results than other previously proposed corner detectors.

Adaptive Motion Estimation and Video Vector Quantization Based on Spatiotemporal Non-linearities of Human Perception

The two main tasks of a video coding system are motion estimation and vector quantization of the signal. In this work a new splitting criterion to control the adaptive decomposition for the non-uniform optical flow estimation is exposed. Also, a novel bit allocation procedure is proposed for the quantization of the DCT transform of the video signal. These new approaches are founded on a perception model that reproduce the relative importance given by the human visual system to any location in the spatial frequency, temporal frequency and amplitude domain of the DCT transform. The experiments show that the proposed procedures behave better than their equivalent (fixed-block-size motion estimation and fixed-step-size quantization of the spatial DCT) used by MPEG-2.