International Journal of Pattern Recognition and Artificial Intelligence

In this paper we argue that phenomenology needs to be supported by explicit mechanisms if one is to have computational models of consciousness. Computational work in this area is reviewed and a set of axioms that help to decompose being conscious into manageable concepts is evoked. This leads to a kernel architecture and a digital implementation which is shown to work in examples of visual illusions that are revealing of how the brain supports phenomenology. This model is used to address the unstable phenomenology related to observation of the ambiguous Necker cube.

Much of the allocation of human resources to tasks is studied under the rubric of "attention". However this is a very low-dimensional characterization of a system that has many degrees of freedom. To make progess in understanding human brain resource allocations, we will need to understand its basic functions at an abstract level. One way of accomplishing such an integration is to create a model of a human that has a useful amount of complexity. Essentially, one is faced with proposing an embodied "operating system" model that can be tested against human performance. Recently, technological advances have been made that allow progress in this direction. Graphic models that simulate extensive human capabilities can be used as platforms to develop synthetic models of visuo-motor behavior. Currently, such models can capture only a small portion of a full behavioral repertoire, but for the behaviors that they do model, they can describe complete visuo-motor subsystems at a level of detail that can be tested against human performance in realistic environments. This paper outlines one such model and shows both that it can produce interesting new hypotheses as to the role of vision and also that it can greatly enhance our understanding of a more multifacted characterization attention in visuo-motor tasks.

Some symbolic AI models, for example, BDI (belief, desire, intention) models are conceived as explicit and operational models of the intentional pursuit and belief dynamics. The main concern of these models is to provide a clear understanding of the functional roles of different kinds of epistemic and motivational states (beliefs, acceptances, expectations, intentions, goals, desires, etc. …), of the relational properties among them. Mental configurations of appraisal (involving different kinds of motivational and epistemic states) which correspond to particular cognitive emotions such as disappointment, fear, relief, shame, etc. … have been analyzed by several authors close to the BDI theoretical tradition. The main objective of this work is a formal analysis of Surprise in a BDI-like cognitive architecture. A clarification of the functional role of Surprise in a BDI-like cognitive architecture with respect to resource bounded belief revision is given.

In this paper we address the issue of how form and motion can be integrated in order to provide suitable information to attentively track multiple moving objects. Such integration is designed in a Bayesian framework, and a Belief Propagation technique is exploited to perform coherent form/motion labeling of regions of the observed scene. Experiments on both synthetic and real data are presented and discussed.

Image descriptions aimed at the realization of content-based image retrieval (CBIR) should include the vagueness of both data representations and user queries. Here we show how multiscale textural gradient can be used as an efficient visual cue for image description. This feature has been already efficiently used in problems of image segmentation and texture separation. Our main idea is based on the assumption that, for image description, shape and textures should be considered together within a unified model. We report an efficient image description algorithm where the multiscale analysis is modeled by a differential morphological filter. Experiments with large image databases and comparisons with classical methods are reported.

Accurate measurement of poses and expressions can increase the efficiency of recognition systems by avoiding the recognition of spurious faces. This paper presents a novel and robust pose-expression invariant face recognition method in order to improve the existing face recognition techniques. First, we apply the TSL color model for detecting facial region and estimate the vector X-Y-Z of face using connected components analysis. Second, the input face is mapped by a deformable 3D facial model. Third, the mapped face is transformed to the frontal face which appropriates for face recognition by the estimated pose vector and action unit of expression. Finally, the damaged regions which occur during the process of normalization are reconstructed using PCA. Several empirical tests are used to validate the application of face detection model and the method for estimating facial poses and expression. In addition, the tests suggest that recognition rate is greatly boosted through the normalization of the poses and expression.

A common problem encountered in structural pattern recognition is the difficulty of constructing classification models or rules from a set of examples, due to the complexity of the structures needed to represent the patterns. In this paper, we present an extension of a method for structural learning. The goal of the method is to find descriptions which are general (in other words, are successfully applicable to recognize objects different from the ones in the training set), preserving at the same time their discrimination ability. This method has been applied to predictive toxicology evaluation, that is the inference of the cancerogenic characteristics of chemical compounds.

We present a method to assign to either the foreground or the background the regions into which a gray-level image is partitioned by watershed transformation. Our method is inspired by visual perception in the sense that the border separating any foreground component from the background is detected in correspondence with the locally maximal gray-level changes through the image. The method is implemented as consisting of three steps. The first two steps perform a basic assignment of the regions, while the remaining step examines again some regions tentatively assigned to the background during the second step and possibly changes their status. A feature of the method is that a hierarchical ranking of the regions assigned to the foreground is also accomplished.

Psychophysical researches on the human visual system have shown that the points of high curvature on the contour of an object play an important role in the recognition process. Inspired by these studies we propose: (i) a novel algorithm to select points of high curvature on the contour of an object which can be used to construct a recognizable polygonal approximation, (ii) a test which evaluates the effect of deletion of contour segments containing such points on the performance of contour based object recognition algorithms. We use complete contour representations of objects as a reference (training) set. Incomplete contour representations of the same objects are used as a test set. The performance of an algorithm is reported using the recognition rate as a function of the percentage of contour retained. We consider two types of contour incompleteness obtained by deletion of contour segments of high or low curvature. We illustrate the test procedure using two shape recognition algorithms that deploy a shape context and a distance multiset as local shape descriptors. Both algorithms qualitatively mimic human visual perception in that the deletion of segments of high curvature has a stronger performance degradation effect than the deletion of other parts of the contour. This effect is more pronounced in the performance of the shape context method.

This paper proposes the prediction based occluded multitarget tracking method using spatio-temporal attention mechanism. To cope with occlusion between targets, the proposed method provides an efficient method for more complex analysis by combining object association with partial probability model in spatially attentive window and occlusion activity detection in predicted temporal location. While multiple objects are moving or occluding between them in areas of visual field, a simultaneous tracking of multiple objects tends to fail. This is due to the fact that incompletely estimated feature vectors such as location, color, velocity, and acceleration of a target can provide only ambiguous and missing information. Thus, the spatially and temporally considered mechanism is proposed to track each target before, during, and after occlusion. Robustness of the proposed method is demonstrated with representative simulations.

This paper presents a robust and direct algorithm for the least-square fitting of ellipses to scattered data. The proposed algorithm makes use of well-known techniques that improve the robustness of the direct least-square fitting with a modest increase of the computational burden. Furthermore, by trivial modifications of the constrained minimization problem the algorithm may be converted to perform the specific fitting of other types of conics such as hyperbola. The method is simple and accurate and can be implemented with fixed time of computation. These characteristics coupled to its robustness and specificity makes the algorithm well-suited for applications requiring real-time machine vision.

This paper describes how a facial albedo map can be recovered from a single image using a statistical model that captures variations in surface normal direction. We fit the model to intensity data using constraints on the surface normal direction provided by Lambert's law and then use the differences between observed and reconstructed image brightness to estimate the albedo. We show that this process is stable under varying illumination. We then show how eigenfaces trained on albedo maps may provide a better representation for illumination insensitive recognition than those trained on raw image intensity.