A cortical framework for invariant object categorization and recognition

In this paper we present a new model for invariant object categorization and recognition. It is based on explicit multi-scale features: lines, edges and keypoints are extracted from responses of simple, complex and end-stopped cells in cortical area V1, and keypoints are used to construct saliency maps for Focus-of-Attention. The model is a functional but dichotomous one, because keypoints are employed to model the “where” data stream, with dynamic routing of features from V1 to higher areas to obtain translation, rotation and size invariance, whereas lines and edges are employed in the “what” stream for object categorization and recognition. Furthermore, both the “where” and “what” pathways are dynamic in that information at coarse scales is employed first, after which information at progressively finer scales is added in order to refine the processes, i.e., both the dynamic feature routing and the categorization level. The construction of group and object templates, which are thought to be available in the prefrontal cortex with “what” and “where” components in PF46d and PF46v, is also illustrated. The model was tested in the framework of an integrated and biologically plausible architecture.

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.     

Influencesicture context on object recognition

The effect of sorrounding context on the recognition of objects from briefly presented pictures was investigated. Forty-eight undergraduates saw 100 msec displays of either line drawings containing several objects embedded in context or drawings of object arrays without background context. Following each exposure they were required to select from among four objects the one that had been contained in the picture. Presentation of objects in context aided recognition only when incorrect response alternatives were inconsistent with the picture context. The results suggest that context contributes to the construction of a general characterization of the pictures which provides expectancies regarding the identity of specific objects.     

One-trial object recognition by rats

Four experiments examined the ability of rats to solve problems analogous to those used with primates, where they were required to remember an object seen on a single trial. In the first experiment, rats were rewarded for selecting the novel of two goal boxes in a Y-maze (nonmatching). Different pairs of goal boxes were used for every trial within a session in order to increase the salience of the positive stimulus and to exclude the use of odour trails. The animals rapidly learnt this one-trial object recognition task and performed well above chance after retention intervals as long as 120 sec. A control experiment confirmed that the rats could not use spatial cues to solve the task. A third experiment showed that rats could also learn to select the familiar of two boxes in a one-trial test of object matching. In the final experiment the rats were unable to acquire a win-stay/lose-shift strategy when tested in a comparable manner.     

Coordinate transformations in object recognition

A basic problem of visual perception is how human beings recognize objects after spatial transformations. Three central classes of findings have to be accounted for: (a) Recognition performance varies systematically with orientation, size, and position; (b) recognition latencies are sequentially additive, suggesting analogue transformation processes; and (c) orientation and size congruency effects indicate that recognition involves the adjustment of a reference frame. All 3 classes of findings can be explained by a transformational framework of recognition: Recognition is achieved by an analogue transformation of a perceptual coordinate system that aligns memory and input representations. Coordinate transformations can be implemented neurocomputationally by gain (amplitude) modulation and may be regarded as a general processing principle of the visual cortex.     

Color diagnosticity in object recognition

Does color influence object recognition? In the present study, the degree to which an object was associated with a specific color was referred to ascolor diagnosticity. Using a feature listing and typicality measure, objects were identified as either high in color diagnosticity or low in color diagnosticity. According to the color diagnosticity hypothesis, color should more strongly influence the recognition of high color diagnostic (HCD) objects (e.g., a banana) than the recognition of low color diagnostic (LCD) objects (e.g., a lamp). This prediction was supported by results from classification, naming, and verification experiments, in which subjects were faster to identify color versions of HCD objects than they were to identify achromatic versions and incongruent color versions. In contrast, subjects were no faster to identify color versions of LCD objects than they were to identify achromatic and incongruent color versions. Moreover, when shape information was degraded but color information preserved, subjects were less impaired in their recognition of degraded HCD objects than of degraded LCD objects, relative to their nondegraded versions. Collectively, these results suggest that color plays a role in the recognition of HCD objects.     

Three-dimensional features facilitate object recognition

Abstract

A priming paradigm was used to investigate the contribution of local features and global shape information in object recognition. Five types of incomplete forms were used as primes: (1) forms with both maxima (local curvature) and midsegments of edges present and aligned on the outline contour; (2) forms similar in global shape to the first version of stimuli, but with misaligned elements; (3) forms with only maxima; (4) forms with only midsegments of edges; and (5) forms containing 3D comer junctions (in Experiments 3 and 4). The target was an outline drawing of an object from which the incomplete prime was derived. Subjects were asked to name the target as rapidly as possible. Primes were presented at levels of contrast corresponding to identification thresholds, as well as above and below threshold levels (determined in Experiments 1 and 3). Facilitation effects relative to a neutral (no prime) condition occurred at threshold and above threshold for primes with aligned elements, forms with only maxima, and forms with only midsegments. Priming occurred only above threshold for forms with non-aligned elements. In Experiment 4 the presence of 3D local features increased the magnitude of priming relative to forms with midsegments and to forms with flat corners (in Experiment 2). This result suggests that 3D features facilitate object identification either because objects are stored in the form of volumetric entities or because 3D features are extracted early in visual processing.     

The role of object recognition in young infants' object segregation

Needham's (2001, this issue) new results confirm that young infants draw on experientially derived representations in resolving individuation ambiguities due to shared boundaries between adjacent objects. They extend previous findings in a surprising way: The memory representations that infants draw upon have bound together information about shape, color, and pattern. Our commentary on these important results draws a distinction between two senses of "recognition" and asks in which sense object recognition contributes to object individuation in these experiments.     

Color diagnosticity in object recognition.

Does color influence object recognition? In the present study, the degree to which an object was associated with a specific color was referred to as color diagnosticity. Using a feature listing and typicality measure, objects were identified as either high in color diagnosticity or low in color diagnosticity. According to the color diagnosticity hypothesis, color should more strongly influence the recognition of high color diagnostic (HCD) objects (e.g., a banana) than the recognition of low color diagnostic (LCD) objects (e.g., a lamp). This prediction was supported by results from classification, naming, and verification experiments, in which subjects were faster to identify color versions of HCD objects than they were to identify achromatic versions and incongruent color versions. In contrast, subjects were no faster to identify color versions of LCD objects than they were to identify achromatic and incongruent color versions. Moreover, when shape information was degraded but color information preserved, subjects were less impaired in their recognition of degraded HCD objects than of degraded LCD objects, relative to their nondegraded versions. Collectively, these results suggest that color plays a role in the recognition of HCD objects.     

The subjective experience of object recognition: comparing metacognition for object detection and object categorization

Perceptual decisions seem to be made automatically and almost instantly. Constructing a unitary subjective conscious experience takes more time. For example, when trying to avoid a collision with a car on a foggy road you brake or steer away in a reflex, before realizing you were in a near accident. This subjective aspect of object recognition has been given little attention. We used metacognition (assessed with confidence ratings) to measure subjective experience during object detection and object categorization for degraded and masked objects, while objective performance was matched. Metacognition was equal for degraded and masked objects, but categorization led to higher metacognition than did detection. This effect turned out to be driven by a difference in metacognition for correct rejection trials, which seemed to be caused by an asymmetry of the distractor stimulus: It does not contain object-related information in the detection task, whereas it does contain such information in the categorization task. Strikingly, this asymmetry selectively impacted metacognitive ability when objective performance was matched. This finding reveals a fundamental difference in how humans reflect versus act on information: When matching the amount of information required to perform two tasks at some objective level of accuracy (acting), metacognitive ability (reflecting) is still better in tasks that rely on positive evidence (categorization) than in tasks that rely more strongly on an absence of evidence (detection).     

A neural basis for expert object recognition

Although most adults are considered to be experts in the identification of faces, fewer people specialize in the recognition of other objects, such as birds and dogs. In this research, the neurophysiological processes associated with expert bird and dog recognition were investigated using event-related potentials. An enhanced early negative component (N170, 164 ms) was found when bird and dog experts categorized objects in their domain of expertise relative to when they categorized objects outside their domain of expertise. This finding indicates that objects from well-learned categories are neurologically differentiated from objects from lesser-known categories at a relatively early stage of visual processing.     

Sleep deprivation impairs object recognition in mice

Many studies in animals and humans suggest that sleep facilitates learning, memory consolidation, and retrieval. Moreover, sleep deprivation (SD) incurred after learning, impaired memory in humans, mice, rats, and hamsters. We investigated the importance of sleep and its timing in an object recognition task in OF1 mice subjected to 6h SD either immediately after the acquisition phase (0-6 SD) or 6h later (7-12 SD), and in corresponding undisturbed controls. Motor activity was continuously recorded with infrared sensors. All groups explored two familiar, previously encountered objects to a similar extent, both at the end of the acquisition phase and 24h later during the test phase, indicating intact familiarity detection. During the test phase 0-6 SD mice failed to discriminate between the single novel and the two familiar objects. In contrast, the 7-12 SD group and the two control groups explored the novel object significantly longer than the two familiar objects. Plasma corticosterone levels determined after SD did not differ from time-matched undisturbed controls, but were significantly below the level measured after learning alone. ACTH did not differ between the groups. Therefore, it is unlikely that stress contributed to the memory impairment. We conclude that the loss of sleep and the activities the mice engaged in during the SD, impaired recognition memory retrieval, when they occurred immediately after acquisition. The delayed SD enabled memory consolidation during the 6h when the mice were allowed to sleep, and had no detrimental effect on memory. Neither SD schedule impaired object familiarity processing, suggesting that only specific cognitive abilities were sensitive to the intervention. Sleep may either actively promote memory formation, or alternatively, sleep may provide optimal conditions of non-interference for consolidation.     

Attention to distinguishing features in object recognition

This study advances the hypothesis that, in the course of object recognition, attention is directed to distinguishing features: visual information that is diagnostic of object identity in a specific context. In five experiments, observers performed an object categorization task involving drawings of fish (Experiments 1–4) and photographs of natural sea animals (Experiment 5). Allocation of attention to distinguishing and non-distinguishing features was examined using primed-matching (Experiment 1) and visual probe (Experiments 2, 4, 5) methods, and manipulated by spatial precuing (Experiment 3). Converging results indicated that in performing the object categorization task, attention was allocated to the distinguishing features in a context-dependent manner, and that such allocation facilitated performance. Based on the view that object recognition, like categorization, is essentially a process of discrimination between probable alternatives, the implications of the findings for the role of attention to distinguishing features in object recognition are discussed.     

The role of context in object recognition

In the real world, objects never occur in isolation; they co-vary with other objects and particular environments, providing a rich source of contextual associations to be exploited by the visual system. A natural way of representing the context of an object is in terms of its relationship to other objects. Alternately, recent work has shown that a statistical summary of the scene provides a complementary and effective source of information for contextual inference, which enables humans to quickly guide their attention and eyes to regions of interest in natural scenes. A better understanding of how humans build such scene representations, and of the mechanisms of contextual analysis, will lead to a new generation of computer vision systems.     

Indirect object recognition: evidence for associative processes in recognition memory

Rats' exploration of stimulus P (e.g., a domestic object) is reduced following either its direct exposure or its indirect exposure and is taken to indicate recognition memory. Procedures for demonstrating indirect object recognition involve an initial presentation of object P with stimulus X (and of an object Q with stimulus Y). On test, stimulus X is presented with objects P and Q and rats' exploration of Q exceeds their exploration of P. One interpretation here is that the presentation of stimulus X on test associatively activates the memory of object P, which diminishes exploration of P relative to Q. It is possible, instead, that performance is simply the result of a novel pattern of stimulation generated by the unfamiliar combination of X and Q. The authors modified this procedure to reduce the likelihood of such a process. Their procedure involved first the presentation of PX and QY before the presentation of stimulus X alone. During the test that followed, objects P and Q were presented but stimulus X was removed. The authors found that exploration of Q remained greater than that of P despite these modifications and discuss some theoretical implications of indirect, associative processes in recognition memory.     

An ERP study on self-relevant object recognition

We performed an event-related potential study to investigate the self-relevance effect in object recognition. Three stimulus categories were prepared: SELF (participant's own objects), FAMILIAR (disposable and public objects, defined as objects with less-self-relevant familiarity), and UNFAMILIAR (others' objects). The participants' task was to watch the stimuli passively. Results showed that left-lateralized N250 activity differentiated SELF and FAMILIAR from UNFAMILIAR, but SELF and FAMILIAR were not differentiated. In the later time-course, SELF was dissociated from FAMILIAR, indicating the self-relevance effect in object recognition at this stage. This activity did not show consistent lateralization, in contrast to previous studies reporting right lateralization in self-relevant face and name recognition. We concluded that in object recognition, self-relevance was processed by higher-order cognitive functions later than 300ms after stimulus onset.