Bio-inspired computational object classification model for object recognition

Human beings can effortlessly perceive stimuli through their sensory systems to learn, understand, recognize and act on our environment or context. Over the years, efforts have been made to enable cybernetic entities to be close to performing human perception tasks; and in general, to bring artificial intelligence closer to human intelligence.Neuroscience and other cognitive sciences provide evidence and explanations of the functioning of certain aspects of visual perception in the human brain. Visual perception is a complex process, and its has been divided into several parts. Object classification is one of those parts; it is necessary for carrying out the declarative interpretation of the environment. This article deals with the object classification problem.In this article, we propose a computational model of visual classification of objects based on neuroscience, it consists of two modular systems: a visual processing system, in charge of the extraction of characteristics; and a perception sub-system, which performs the classification of objects based on the features extracted by the visual processing system.With the results obtained, a set of aspects are analyzed using similarity and dissimilarity matrices. Also based on the neuroscientific evidence and the results obtained from this research, some aspects are suggested for consideration to improve the work in the future and bring us closer to performing the task of visual classification as humans do.     

Rapid object category adaptation during unlabelled classification

Recent reports from electrophysiological and psychophysical experiments provide evidence that repeated exposure to an ordered sequence of morphed stimuli may over time adapt a prelearned object category such that the category may generalise the entire sequence as belonging to the same object. Here, a new protocol that includes a single exposure to a morphing sequence is presented. Subjects exposed to the new protocol replaced a prelearned face with an entirely different face within just 3 days, significantly faster than in previous reports.     

Probabilistic causality reexamined

According to Nancy Cartwright, a causal law holds just when a certain probabilistic condition obtains in all test situations which in turn satisfy a set of background conditions. These background conditions are shown to be inconsistent and, on separate account, logically incoherent. I offer a corrective reformulation which also incorporates a strategy for problems like Hesslow's thrombosis case. I also show that Cartwright's recent argument for modifying the condition to appeal to singular causes fails.Proposed modifications of the theory's probabilistic condition to handle effects with extreme probabilities (0 or 1) are found unsatisfactory. I propose a unified solution which also handles extreme causes. Undefined conditional probabilities give rise to three good, but non-equivalent, ways of formulating the theory. Various formulations appear in the literature. I give arguments to eliminate all but one candidate. Finally, I argue for a crucial new condition clause, and show how to extend the results beyond a simple probabilistic framework.     

Group cohesiveness reexamined

The paradigm through which group cohesiveness is conceptualized and researched is examined. It is found that cohesiveness is typically seen as a positive state necessary for effective therapy. This notion is critiqued at a meta-theoretical level using a dynamic model of process reminiscent of Sartrian and Riegelian dialectics. Cohesiveness, seen in this way, becomes a complex process initially necessary and subsequently defensive in groups. Recommendations for theory, practice and research are made which are based on a concept of cohesiveness as a changing, dialectical process.The author wishes to thank Ronald Janoff and Bernard Katz, both of New York University, for support and criticism essential to the development of this article.     

Direct and indirect effects of action on object classification

We report three experiments in which name verification responses to either objects (Experiments 1 and 2) or hand movements (Experiment 3) were compared with action decisions, where participants verified whether an object is typically used in the way described by a verbal label. In Experiments 1 and 2, we report that action decisions show more consistent and larger effects of the congruency of either a handgrip or a type of movement than do name verification responses, although there was some effect of the congruency of the handgrip on name verification. In Experiment 3, we demonstrate that the congruency of the object being moved affects both action and name verification responses to hand movements. We discuss the]data relative to accounts of how actions and names are accessed by visually presented objects and in relation to work on the information called upon in classification tasks.     

Perception of correlation reexamined

Almost all studies of adult notions of correlation between dichotomous variables show that people do not incorporate two conditional probabilities as they should according to normative definitions. However, these studies disagree considerably about what correlational notions people do have. This paper identifies three factors that contribute to the variability in research results. The first two factors were mentioned in the literature, and the evidence concerning them is summarized: (1) the way data are presented and (2) the instructions subjects receive. A third factor is suggested and studied; the type of variables between which correlation is judged may affect subjects’ notion of correlation, Specifically, asymmetric, present/absent variables (e.g., symptom: present, absent) may strengthen the incorrect notion of correlation as the tendency of two events to coexist (e.g., presence of symptom and presence of disease) disregarding the complementary events. In three experiments, subjects were asked to choose among five interpretations of the sentence “A strong [or no] relationship exists between [two variables],” The above prediction was confirmed.     

Multidimensional shape similarity in the development of visual object classification

The current work examined age differences in the classification of novel object images that vary in continuous dimensions of structural shape. The structural dimensions employed are two that share a privileged status in the visual analysis and representation of objects: the shape of discrete prominent parts and the attachment positions of those parts. Experiment 1 involved a triad classification task in which participants at each of three different ages (5 years, 8 years, and adult) classified object images from two distinct stimulus sets. Across both sets, the youngest children demonstrated a systematic bias toward the shape of discrete parts during their judgments. With increasing age, participants increasingly came to select both the shape and the position of parts when classifying the images. The findings from Experiment 2 indicate that the local shape bias observed in young children's classifications is not merely a consequence of a discrimination advantage for that dimension. Results are discussed in relation to corresponding age-related changes in other functional contexts of visual processing.     

Spatial configurations: Erikson reexamined

In a 1951 study, Erik Erikson reported differences in preadolescents' play constructions. He claimed that his findings reflected differences between males and females in their experience and perception of space. The present study replicated but also expanded the original design. In order to control for possible sex bias of materials, a constructed scene using only blocks was added to Erikson's original design. The results failed to replicate Erikson's findings. In fact, in the construction of scenes from blocks, more females than males built erected structures; this was true across all ages. These findings are in direct contrast to Erikson's results, and they lead to the conclusion that the materials provided, not innate anatomical sex differences, account for the resulting spatial configurations.The research reported here was part of the first author's dissertation. The authors gratefully acknowledge the cooperation of Holy Innocents Episcopal School and Georgia State University.     

The allure of connectionism reexamined

There is currently a debate over whether cognitive architecture is classical or connectionist in nature. One finds the following three comparisons between classical architecture and connectionist architecture made in the pro-connectionist literature in this debate: (1) connectionist architecture is neurally plausible and classical architecture is not; (2) connectionist architecture is far better suited to model pattern recognition capacities than is classical architecture; and (3) connectionist architecture is far better suited to model the acquisition of pattern recognition capacities by learning than is classical architecture. If true, (1)–(3) would yield a compelling case against the view that cognitive architecture is classical, and would offer some reason to think that cognitive architecture may be connectionist. We first present the case for (1)–(3) in the very words of connectionist enthusiasts. We then argue that the currently available evidence fails to support any of (1)–(3).     

Domains and knowledge effects: strategies in object and social classification

This research examined differences in classification strategies in object and social domains. Wattenmaker (1995) found that additive classification rules were more compatible with the social than the object domain. The present experiments examined the generality of these results by using fundamentally different types of social and object categories. A sorting paradigm was used to evaluate the frequency with which subjects used additive strategies. In Experiment 1, the social domain was represented by social events that possess very different properties than core social concepts such as traits or occupations. Even with these types of social materials, however, many more additive strategies and family resemblance sorts occurred with social than object materials. In Experiment 2, the object domain was represented by abstract object categories that were designed to possess properties of core social concepts such as traits. Again, however, more additive strategies and family resemblance sorts occurred with social than object materials. The results indicate that differences in the compatibility between additive strategies and object and social domains are not limited to subsets of categories in these domains but rather extend to many types of object and social categories.     

Vicario's illusion of sloping steps reexamined

If a few parallel horizontal rows of dots are set diagonally, like steps, across the visual field, the inner rows appear not to be horizontal but sloping up to one side; the effect holds as long as the vertical distances between the rows do not exceed a given visual angle. This illusion, described by Vicario in 1978, was never explained. An experiment is reported in which the illusion was still visible at row separations well in excess of the spatial limits originally considered, provided the stimulus elements were enlarged. The maximum illusion was obtained for length ratios (interrow distance to size of dots) identical to those which have been shown to produce the largest effects in a number of illusions of area and length. This suggests that Vicario's illusion is similar to other illusions of extent, and that it can be explained by a neural extent-coding model.     

Subordinate-level categorization relies on high spatial frequencies to a greater degree than basic-level categorization

In two experiments, category verification of images of common objects at subordinate, basic, and superordinate levels was performed after low-pass spatial filtering, high-pass spatial filtering, 50% phase randomization, or no image manipulation. Both experiments demonstrated the same pattern of results: Low-pass filtering selectively impaired subordinate-level category verification, while having little to no effect on basic-level category verification. Subordinate categorization consequently relies to a greater degree on high spatial frequencies of images. This vulnerability of subordinate-level processing was specific to a lack of high spatial frequency information, as opposed to other visual information, since neither high-pass filtering nor the addition of phase noise produced a comparable reduction in performance. These results are consistent with the notion that object recognition at basic levels relies on the general shapes of objects, whereas recognition at subordinate levels relies on finer visual details.     

Absorption and hypnotizability: context effects reexamined

Two independent studies failed to find evidence consistent with Council, Kirsch, and Hafner (1986), who argued that the repeatedly observed correlations between Tellegen's (1981) Absorption Scale (TAS) and hypnosis measures were artifacts of testing context, and de Groot, Gwynn, and Spanos (1988), who claimed evidence for a Gender x Context moderator effect. In the present studies, Ss completed the TAS and other personality questionnaires on 2 occasions: during an independent survey and later immediately prior to an assessment of hypnotizability. In Experiment 1 (N = 475), the effect of context on the relation between questionnaire scores and hypnotizability was weak and variable; in Experiment 2 (N = 434), these weak effects were reversed. The results reaffirm the construct validity of absorption as both a major dimension of personality and as a predictor of hypnotic responsiveness.     

Endogenous attention and illusory line motion reexamined

P. Downing and A. Treisman's (1997) failure to replicate an effect of endogenous attention on the direction of illusory line motion (ILM) was reexamined. Four experiments with slightly modified stimulus presentation methods based on gradient theories of ILM found that endogenous attention directed to 1 of 2 similar priming objects is capable of influencing experienced motion direction within a subsequently presented line. The endogenous effect on ILM was consistent with a concomitant response-time discrimination task, was robust across naive and informed participants, occurred whether eye fixation was monitored or not, and occurred under conditions where multiple motion response categories were available to participants. The endogenous effect disappeared when participants moved their eyes to the attended item, when there was no motivation to endogenously attend, and when the presentation methods of P. Downing and A. Treisman (1997) were used.     

The semantic deficit hypothesis: Perceptual parsing and object classification by aphasic patients

Many aphasic patients are impaired in their ability to provide or to recognize the names of objects, but little is known about the processing deficits that underlie these difficulties. In this report, a model of object naming/name recognition is proposed, and a prediction is tested concerning one possible functional locus of impairment in name-recognition and object-naming disorders. A subgroup of aphasic patients is found to be impaired in the ability to perform perceptual similarity judgments for pairs of stimulus objects, and to be unable to classify the objects into one of two lexical categories. It is concluded that the classification disorder suffered by these patients results from an impairment at the level of the semantically guided perceptual parsing of objects.     

The generation effect in primed word-fragment completion reexamined

Summary Two experiments were designed to test a claim made by Gardiner (1988) that there are generation effects in implicit memory as measured by word-fragment completion. Subjects either read words at study or generated the words from fragments. As in previous research, fragments were completed to a greater extent if they were identical at study and test than if they differed. In Experiment 1 it was found that subjects could recognize explicitly the exact form of fragments that had been used for self-generation and distinguish these from other forms of fragments. An analysis of the contingency relations between recognition of fragments and fragment completion showed a high degree of dependence between the two tests. In Experiment 2 it was found that the match of surface features between study and test was a necessary, but not sufficient, condition to produce enhancement of priming. The results are interpreted as supporting the claim that generation does involve a data-driven component in addition to semantic elaboration.This research was supported by a grant from the Swedish Council for Research in the Humanities and Social Sciences to Lars-Göran Nilsson.