International Journal of Pattern Recognition and Artificial Intelligence

In this paper, we discuss how image segmentation can be handled by using Bayesian learning and inference. In particular variational techniques relying on free energy minimization will be introduced. It will be shown how to embed a spatial diffusion process on segmentation labels within the Variational Bayes learning procedure so as to enforce spatial constraints among labels.

This paper proposes to use case-based-reasoning for grey-level image segmentation. Different approaches to image segmentation have been proposed in the literature. The selection of the segmentation approach and the assignment of the values to the parameters involved in the selected algorithm depend on image domain and on the specific application. Case-based-reasoning seems a promising way to make the above selection automatic. In this paper, we describe the results of a preliminary study done in this respect. In particular, we refer to the automatic selection of the values of the parameters for a new watershed image segmentation algorithm.

In some Computer Vision applications there is the need for grouping, in one or more clusters, only a part of the whole dataset. This happens, for example, when samples of interest for the application at hand are present together with several noisy samples.

In this paper we present a graph-based algorithm for cluster detection that is particularly suited for detecting clusters of any size and shape, without the need of specifying either the actual number of clusters or the other parameters.

The algorithm has been tested on data coming from two different computer vision applications. A comparison with other four state-of-the-art graph-based algorithms was also provided, demonstrating the effectiveness of the proposed approach.

We present a biologically plausible computational model for solving the visual feature binding problem, based on recent results regarding the time course and processing sequence in the primate visual system. The feature binding problem appears due to the distributed nature of visual processing in the primate brain, and the gradual loss of spatial information along the processing hierarchy. This paper puts forward the proposal that by using multiple passes of the visual processing hierarchy, both bottom-up and top-down, and using task information to tune the processing prior to each pass, we can explain the different recognition behaviors that primate vision exhibits. To accomplish this, four different kinds of binding processes are introduced and are tied directly to specific recognition tasks and their time course. The model relies on the reentrant connections so ubiquitous in the primate brain to recover spatial information, and thus allow features represented in different parts of the brain to be integrated in a unitary conscious percept. We show how different tasks and stimuli have different binding requirements, and present a unified framework within the Selective Tuning model of visual attention.

We present a system for object recognition that is largely inspired by physiologically identified processing streams in the visual cortex, specifically in the ventral stream. It consists of neural units organized in a hierarchy of layers with encoding features of increasing complexity. A key feature of the system is that the neural units learn their preferred patterns from visual input alone. Through this "soft wiring" of neural units the system becomes tuned for target object classes through passive visual experience and no labels are required in this stage. Object labels are only introduced in the last step to train a classifier on the system's output. While this tuning process is purely feed-forward we also present a neural mechanism for back projection of the learned image patterns down the hierarchical layers, and demonstrate how this feedback can be used to stabilize the system in the presence of noise. We test the neural system with natural images from publicly available data-sets of natural scenes and handwritten digits.

Cognitive development refers to the ability of a system to gradually acquire knowledge through experiences during its existence. As a consequence, the learning strategy should be represented as an integrated, online process that aims to build a model of the "world" and a continuous update of this model. Considering as reference the Modal Model of Memory introduced by Atkinson and Schiffrin, we propose an online learning algorithm for cognitive systems design. The incremental part of the algorithm is responsible of updating existing information or creating new data categories and the decremental part, to efficiently evaluate the system's performance facing partial or total loss of data. The proposed algorithm has been applied to the face recognition problem. More generally, the current approach can be extended to large-scale classification problems, to limit the memory requirements for optimal data representation and storage.

The aim of this paper is to propose an artificial intelligence based approach to moving object detection and tracking. Specifically, we adopt an approach to moving object detection based on self organization through artificial neural networks. Such approach allows to handle scenes containing moving backgrounds and gradual illumination variations, and achieves robust detection for different types of videos taken with stationary cameras. Moreover, for object tracking we propose a suitable conjunction between Kalman filtering, properly instanced for the problem at hand, and a matching model belonging to the class of Multiple Hypothesis Testing. To assess the validity of our approach, we experimented both proposed moving object detection and object tracking over different color video sequences that represent typical situations critical for video surveillance systems.

In this paper, we present an algorithm for the hierarchical recognition of an environment using independent components of optical flow fields for the visual navigation of a mobile robot. For the computation of optical flow, the pyramid transform of an image sequence is used for the analysis of global and local motion. Our algorithm detects the planar region and obstacles in the image from optical flow fields at each layer in the pyramid. Therefore, our algorithm allows us to achieve both global perception and local perception for robot vision. We show experimental results for both test image sequences and real image sequences captured by a mobile robot. Furthermore, we show some aspects of this work from the viewpoint of information theory.

There are many factors affecting the depth estimation for 3D shape recovery using passive optical methods. In this paper, we consider the effects of noise, source illumination and texture reflectance for shape from focus technique. We present a focus measure which shows consistent performance for varying noise levels, source illumination levels and different texture reflectance. The focus measure is based on an optical transfer function implemented in the Fourier domain and its results are compared with four other focus measures. The additive Gaussian noise is considered for noise analysis. Three illumination levels are considered for source illumination and three different textures are studied for reflectance analysis.

The promise of Brain-Computer Interfaces (BCI) technology is to augment human capabilities by enabling interaction with computers through a conscious and spontaneous modulation of the brainwaves after a short training period. Indeed, by analyzing brain electrical activity online, several groups have designed brain-actuated devices that provide alternative channels for communication, entertainment and control. Thus, a person can write messages using a virtual keyboard on a computer screen and also browse the internet. Alternatively, subjects can operate simple computer games, or brain games, and interact with educational software. Work with humans has shown that it is possible for them to move a cursor and even to drive a wheelchair. This paper briefly reviews the field of BCI, with a focus on noninvasive systems based on electroencephalogram (EEG) signals. It also describes three brain-actuated devices we have developed: a virtual keyboard, a brain game, and a wheelchair. Finally, it shortly discusses current research directions we are pursuing in order to improve the performance and robustness of our BCI system, especially for real-time control of brain-actuated robots.

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient's epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify subgroups of partial epilepsy by Multilayer Perceptron Neural Networks (MLPNNs). This is the first study to classify the partial epilepsy groups using the neural network according to EEG signals. 418 patients with epilepsy diagnoses according to International League against Epilepsy (ILAE, 1981) were included in this study. The epilepsy outpatients at the Neurology Department Clinic of Cukurova University Medical School between the years of 2002–2005 were examined and included in the study. The MLPNNs were trained by the parameters obtained from the EEG signals and clinical findings of the patients. Test results show that the MLPNN model is able to classify partial epilepsy with an accuracy of 91.5%. Moreover, new MLPNNs were constructed for determining significant variables on classification. The loss of consciousness in the course of seizure time variable caused the largest decrease in the classification accuracy when it was left out. In conclusion, we think that the classification performance of MLPNN model for partial epilepsy is satisfactory and this model may be used in clinical studies as a decision support tool to determine the partial epilepsy classification of the patients.

The main goal of our current research is the design of a robotic architecture that has the capability of adapting the robot's behavior to the rate of change of a dynamic environment. We present a model which takes free inspiration from some features of biological clocks. In particular, we associate the concept of Innate Releasing Mechanisms (IRM) to the concept of periodic behavior activation in order to link the variability of the behavior to the circumstances in which it is activated. We propose an architecture in which the frequency of access to the sensory system is modified in accordance to the environmental changes. To this purpose we use the Schema Theory paradigm. Some first experimental results are reported and discussed.

In this paper a neurosymbolic hybrid system for robot self-localization is proposed. This crucial issue in autonomous robotic research field has been tackled with slightly different approaches depending mainly on robot sensors and actuation devices, its available computational resources, and the environment in which it acts. The system we present has been designed for robot endowed with poor sensors (a 16-element sonar array, a camera just performing very light computation, odometric sensors) which acts in an office-like environment. In the proposed landmark based approach, we have considered as "natural" environmental features the corners formed by wall intersections, and corners formed by doors that are present in the scene. The whole problem, from landmark recognition to position estimation, is carried out by a unified neurosymbolic system.

In this paper we address the challenging problem of sensorimotor integration, with reference to eye-hand coordination of an artificial agent engaged in a natural drawing task. Under the assumption that eye-hand coupling influences observed movements, a motor continuity hypothesis is exploited to account for how gaze shifts are constrained by hand movements. A Bayesian model of such coupling is presented in the form of a novel Dynamic Bayesian Network, namely an Input–Output Coupled Hidden Markov Model. Simulation results are compared to those obtained by eye-tracked human subjects involved in drawing experiments.

This paper presents the implementation of ARQ-PROP II, a limited-depth propositional neural reasoner based on the Resolution Principle. The SATyrus platform was used in the synthesis of Energy functions from a set of pseudo-Boolean constraints specifying ARQ-PROP II architectures for different inferencing depths. Global minima of the Energy functions produced by SATyrus are associated to SATisfiability of a formula and, in the case of ARQ-PROP II, are associated to Resolution-based refutations. This allows for simplified abduction, prediction and planning to be unified with deduction in a goal-driven style, i.e. there is no need for presetting a reasoning style upon a target set of clauses. Experimental results on deduction with ARQ-PROP II using different propositional depth settings are presented together with a correction of Gadi Pinkas' mapping of SATisfiability into Energy minima.

Among forms of creative language, verbal humor has received some attention in the computational milieu. Some aspects of irony and wordplay could be experimented in automated systems. For instance, we developed a system that makes fun of existing acronyms, based mainly on lexical reasoning. The dimension of emotion in words is also starting to be understood among computational linguists. The challenge of electronic advertisements offers in particular a great opportunity for getting now deeper into creative language expression and emotion. An advertising message induces in the recipient a positive or negative attitude toward the advertised object. A prototype we have developed for advertising professionals has two steps: (i) the creative variation of familiar expressions, taking into account the effective content of the produced text, (ii) the automatic animation (semantically consistent with the affective text content) of the resulting expression, using kinetic typography techniques. In this way the ironic-affective effect is perceptually emphasized.

In this paper we present a theoretical framework for the formalization of design methodologies of artifacts, in which we distinguish three levels: the design strategies level, the artifacts representation level, and the level of graphics systems for 3D rendering. This work proposes both a formal apparatus for the definition of design strategies, considered as processes operating on representations of artefacts, and provides a methodological contribution to the building of knowledge-based aid design systems. The key idea of the paper is that, independently of the design type, it is essential to separate the level of design strategy from that of artifact representation and to connect them through appropriate translation rules. The strategy level is a "meta"-level with respect to the representation level. Therefore when we formalize a strategy, we must represent it through a language of greater order than the one used in formalizing the artifact representation. In this paper we present a formalization of some typical design strategies classes for every-day artifact in which an artifact is represented as a class of a formal ontology. Though the methodological and formal apparatus presented has been defined for the generative design operating method, we think that the concepts here exposed apply also to other architectural design approaches.

This study investigates pausing strategies, focusing the attention on empty speech pauses. A cross-modal analysis (video and audio) of spontaneous narratives produced by male and female children and adults showed that a remarkable amount of empty speech pauses was used to signal new concepts in the speech flow and to segment discourse units such as clauses and paragraphs. Based on these results, an adaptive mathematical model for pause distribution was suggested, that exploits, as pause features, the absence of signal and/or the changes of energy over different acoustic dimensions strongly related to the auditory perception. These considerations inspired the formulation and the implementation of two pause detection procedures that proved to be more effective than the Likelihood Ratio Test (LRT) and Long-Term Spectral Divergence (LTSD) algorithms recently proposed in literature and applied for Voice Activity Detection (VAD).