Javier Martinez-Baena

The selection of natural scales in 2D images using adaptive Gabor filtering

This paper analyzes how the natural scales of the shapes in 2D images can be extracted. Spatial information is analyzed by multiple units sensitive to both spatial and spatial-frequency variables. Scale estimates of the relevant shapes are constructed only from strongly responding detectors. The meaningful structures in the response of a detector (computed through 2D Gabor filtering) are, at their natural level of resolution, relatively sharp and have well-defined boundaries. A natural scale is so defined as a level producing local minimum of a function that returns the relative sharpness of the detector response filtered over a range of scales. In a second stage, to improve a first crude estimate of the local scale, the criterion is also rewritten to directly select scales at locations of significant features of each activated detector.

A new image distortion measure based on a data-driven multisensor organization†

This paper describes a visual model that gives a perceptual distortion measure between an input image and that of reference based on a human-image representational model. We study an approach in which once a few active recognizers tuned to significant orientation and spatial-frequency components of the reference spectrum are obtained, any input image to be compared with the reference one is passed through an operator designated to compare its excitation levels given by the active recognizers, to the corresponding excitation levels for the reference image. Hence, the distortion between a pair of complex images is measured as the weighted sum of the distortion in each filter of a bank of strongly responding recognizers, each tuned to a certain 2D spatial-frequency data in the reference picture, with the weighting of each filter modulating its amplitude response.

On first quartile journals which are not of highest impact

Here we study the relationship between journal quartile rankings of ISI impact factor (at the 2010) and journal classification in four impact classes, i.e., highest impact, medium highest impact, medium lowest impact, and lowest impact journals in subject category computer science artificial intelligence. To this aim, we use fuzzy maximum likelihood estimation clustering in order to identify groups of journals sharing similar characteristics in a multivariate indicator space. The seven variables used in this analysis are: (1) Scimago Journal Ranking (SJR); (2) H-Index (H); (3) ISI impact factor (IF); (4) 5-Year Impact Factor (5IF); (5) Immediacy Index (II); (6) Eigenfactor Score (ES); and (7) Article Influence Score (AIS). The fuzzy clustering allows impact classes to overlap, thereby accommodating for uncertainty related to the confusion about the impact class attribution for a journal and vagueness in impact classes definition. This paper demonstrates the complex relationship between quartiles of ISI impact factor and journal impact classes in the multivariate indicator space. And that several indicators should be used for a distinct analysis of structural changes at the score distribution of journals in a subject category. Here we propose it can be performed in a multivariate indicator space using a fuzzy classifier.

A frequency-domain approach for the extraction of motion patterns

A new frequency-domain approach to represent motions is proposed. The new scheme is based on a band-pass filtering with a set of logGabor spatio-temporal filters. It is well known that one of the main problems of these approaches is that a filter response varies with the spatial orientation of the underlying signal. To solve this spatial dependency, the proposed model allows to recombine information of motions that has been separated in several filter responses due to its spatial structure. For this purpose, motion patterns are detected as invariance in statistical structure across a range of spatio-temporal frequency bands. This technique is illustrated on real and simulated data sets, including sequences with occlusion and transparencies.

A multi-channel autofocusing scheme for gray-level shape scale detection

This paper describes the implementation of a multi-channel autofocusing scheme capable of automatically detecting gray-level shape scales. The scale concept in the vision literature stands for the characteristic length over which gray-level variations in the image take place and/or the operator size used for processing the given image. The proposed scheme allows for a data-driven multichannel organization selectively sensitive to spatial frequency and size which is biologically inspired by the behavior of visual cortex and retinal cells. We investigate the suitability of several band-pass filter based autofocusing criteria for the scale selection. In scale-space representation where the gray-level shape is generally comprised of multiple structures at different levels of scale, it is often not possible to obtain an image in which all the structures are described at their best scale levels, because if one structure is well-enhanced, the others appear blurred. At best, some forms of compromise among the structures at different scale levels may be sought. To overcome this problem, we present an efficient multi-channel autofocusing scheme which may be employed to automatically describe each gray-level structure at its most suitable level. The ability to decompose a complex problem-that of where to look as well as how to concentrate on certain features in the input data-into simpler subproblems is a major motivation for using the proposed scheme. In the absence of further information, the information derived through such a formulation may serve as a guide to subsequent processing requiring knowledge about the scales at which a grey-level structure with particular spectrum components (high-, medium- or low-frequency content) occurs.

COMPUTATIONAL VISUAL DISTINCTNESS METRIC

A new computational visual distinctness metric based on principles of the early human visual system is presented. The metric is applied to quantify (1) the visual distinctness of targets in complex natural scenes and (2) the perceptual differences between compressed and uncompressed images. The new metric is shown (1) to predict human observer performance in search and detection tasks on complex natural imagery, (2) to correlate with visual target distinctness estimated by human observers, and (3) to correlate with the quality factor of Joint Photographic Experts Group (JPEG) compressed imagery.

A Spatio-temporal Filtering Approach to Motion Segmentation

In this paper, a new frequency-based approach to motion segmentation is presented. The proposed technique represents the sequence as a spatio-temporal volume, where a moving object corresponds to a three-dimensional object. In order to detect the {}“3D volumes” corresponding to significant motions, a new scheme based on a band-pass filtering with a set of logGabor spatio-temporal filters is used. It is well known that one of the main problems of these approaches is that a filter response varies with the spatial orientation of the underlying signal. To solve this spatial dependency, the proposed model allows to recombine information of motions that has been separated in several filter responses due to its spatial structure. For this purpose, motions are detected as invariance in statistical structure across a range of spatio-temporal frequency bands. This technique is illustrated on real and simulated data sets, including sequences with occlusion and transparencies.

Information visibility using transmission methods

Lossy coding, selective seeing, ignoring visual cues, and perceptual biases are different sources of error into the visual communication. To counteract these tendencies we propose a change of paradigm from transmitting important information first to seeing important information first, for the same quality factor. Here we use the new paradigm to the evaluation of the visual efficiency of image information when it is reconstructed at high and low fidelity using different transmission methods. To this aim, we apply a rational model of computational attention in which a multi-bitrate attention map will provide us with the attention score for each spatial location at high and low quality versions of the image reconstruction. The rational approach of attention does not purport to describe the ways in which the Human Visual System (HVS) actually do behave in making choices among possible locations of interest for allocating attention. Instead we are interested in the aspects of rationality that seem to be present in the decision making of the HVS. From both rate-attention and rate-distortion curves, we conclude which transmission method is the overall winner according to the new paradigm. A dataset of advertisement images is used to compare the visual efficiency of the advertisement when it is transmitted using three different coders without region-dependent quality of encoding. Experimental results show that a potential consumer may see important areas faster using SPIHT (without region-dependent quality of encoding) on a significant number of advertisement images, even though this transmission method should improve its capabilities in terms of important information visibility across bitrates.

Using graphics: motivating students in a C++ programming introductory course

When we study a subject like “introduction to computer programing” with languages like C or C++, some aspects may be considered boring by students. On the one hand, the programs we present often have an ugly aspect due to the fact that we use the command line interface (console) to communicate with user, and on the other hand, these programs tend to solve very simple problems that are usually established with learning proposals in mind. In this paper we propose the use of a C++ library (BiMIP) which allows us to easily create simple graphical user interfaces, avoiding complexity from current broadly used libraries. It has been successfully used in our courses by proposing the development of graphical applications, and more specifically video games, to make the students motivation increase with respect to the applications developed for the console.

Bit-saving path for progressive transmission

Under oscillatory behavior of the net profit of transmission over time, heavy losses may be incurred in the form of foregone opportunities in the future if the transmission system prefers to transmit low-cost bit resources at this time over conserving for the future. This oscillatory behavior over time necessitates devising a stabilizing scheme for its optimal use in the transmission. Here we examine an optimal bit-saving path over time. During an initial period, the transmission system prioritizes exhaustible bit reserves of low transmission cost at the maximum available capacity and allocates gross transmission income partly to transmission and the rest is saved and invested to increase the degree of knowledge; and in the second period, once these low-cost bit reserves are exhausted, it is necessary to switch to a source of transmission solely from returns on current degree of knowledge, which initially includes highly insignificant bit streams. For knowledge-poor transmission systems the optimal bit-saving path differs sharply from that for region-based approaches with higher share of knowledge in the transmissions initial wealth. Also, the bit-saving path is highly dependent on the low-cost bitstreams life. We give a comparison in performance of the state of the art codec in progressive transmission against an algorithm which implements the saving path. It appears that the bit saving may be used with acceptable image fidelity.