Object Classification Tasks Research Articles

Fast and accurate 3D object recognition directly from digital holograms

Pattern recognition methods can be used in the context of digital holography to perform the task of object detection, classification, and position extraction directly from the hologram rather than from the reconstructed optical field. These approaches may exploit the differences between the holographic signatures of objects coming from distinct object classes and/or different depth positions. Direct matching of diffraction patterns, however, becomes computationally intractable with increasing variability of objects due to the very high dimensionality of the dictionary of all reference diffraction patterns. We show that most of the diffraction pattern variability can be captured in a lower dimensional space. Good performance for object recognition and localization is demonstrated at a reduced computational cost using a low-dimensional dictionary. The principle of the method is illustrated on a digit recognition problem and on a video of experimental holograms of particles.

Multi-local model image set matching based on domain description

Image set matching attracted increasing attention in the field of pattern recognition. Recently, there are a number of effective image set-based matching methods under controlled environment. However in the more complex environment, like multi-view and illumination changed, it is still a challenging problem to develop unsupervised image set matching method to handle multi-local model data. To solve this problem, in this paper, we present a novel multi-local model image set matching method based on data description techniques. First, every image set is divided into multi-local models, and each local model corresponds to a data domain, that is, we innovatively train a support vector data domain to describe each local model by means of the excellent data description ability of support vector data domain, hence each image set can be expressed by a plurality of support vector data domain. Second, a new similarity measure based on domain–domain distance is proposed, and then the distance between two image sets is converted to integrate the distance between pair-wise domains. Finally, the proposed method is evaluated on both set-based face recognition and object classification tasks. Extensive experimental results show that the proposed method outperforms other state of the art set-based matching methods in three public video databases.

Does a yellow filter improve visual object categorization in normal aging?

ABSTRACTPrevious studies have shown that a yellow filter (CPF450) can increase contrast, motion sensitivity, vergence, and accommodation. We investigated whether a yellow filter can reduce age-related visual deficits. We tested two groups of 60 observers (mean age 24 vs. 72) in an object categorization task. Grayscale photographs of natural objects and artifacts were displayed either centrally or peripherally (21°) at low (8%) or medium (30%) contrast. There were three filter conditions (no filter, placebo filter, and yellow filter). Both groups of observers performed similarly on central and medium-contrast pictures. The deleterious effects of reduced contrast and eccentricity were stronger in elderly individuals. Moreover, the yellow filter globally improved the speed of categorization for the elderly participants. The decrease in response time in the yellow filter condition was larger when the stimuli were displayed peripherally in both groups. A yellow filter should be considered as a potential means for visual improvement in normal aging.

The benefits and costs of comparisons in a novel object categorization task: Interactions with development

We investigated how children use within- or between-category comparisons to generalize novel names for novel objects on the basis of a nonsalient dimension (texture) rather than a salient one (shape). Previous studies have not experimentally addressed the costs associated with comparisons. We conjectured that increasing the number of stimuli to be compared (and thus, converging evidence in favor of the target texture-based generalization), might not necessarily be beneficial, especially in young children (3- to 4-year-olds vs. 5- to 6-year-olds). Our results showed that more evidence in favor of texture (i.e., more within-category exemplars sharing the same texture) did not linearly increase texture-based choices in the same way for younger and older children. They also revealed that between-category comparisons gave rise to texture-based generalizations in both age groups. Overall, our results show that even though within- and between-category comparisons contribute to generalizations based on texture, they also generate cognitive constraints that interact with age.

Low-level and high-level modulations of fixational saccades and high frequency oscillatory brain activity in a visual object classification task.

Until recently induced gamma-band activity (GBA) was considered a neural marker of cortical object representation. However, induced GBA in the electroencephalogram (EEG) is susceptible to artifacts caused by miniature fixational saccades. Recent studies have demonstrated that fixational saccades also reflect high-level representational processes. Do high-level as opposed to low-level factors influence fixational saccades? What is the effect of these factors on artifact-free GBA? To investigate this, we conducted separate eye tracking and EEG experiments using identical designs. Participants classified line drawings as objects or non-objects. To introduce low-level differences, contours were defined along different directions in cardinal color space: S-cone-isolating, intermediate isoluminant, or a full-color stimulus, the latter containing an additional achromatic component. Prior to the classification task, object discrimination thresholds were measured and stimuli were scaled to matching suprathreshold levels for each participant. In both experiments, behavioral performance was best for full-color stimuli and worst for S-cone isolating stimuli. Saccade rates 200–700 ms after stimulus onset were modulated independently by low and high-level factors, being higher for full-color stimuli than for S-cone isolating stimuli and higher for objects. Low-amplitude evoked GBA and total GBA were observed in very few conditions, showing that paradigms with isoluminant stimuli may not be ideal for eliciting such responses. We conclude that cortical loops involved in the processing of objects are preferentially excited by stimuli that contain achromatic information. Their activation can lead to relatively early exploratory eye movements even for foveally-presented stimuli.

Electrophysiological correlates of object-repetition effects: sLORETA imaging with 64-channel EEG and individual MRI

BackgroundWe investigated the electrophysiological correlates of object-repetition effects using an object categorization task, standardized low-resolution electromagnetic tomography (sLORETA), and individual magnetic resonance imaging. Sixteen healthy adults participated, and a total of 396 line drawings of living and non-living objects were used as stimuli. Of these stimuli, 274 were presented only once, and 122 were repeated after one to five intervening pictures. Participants were asked to categorize the objects as living or non-living things by pressing one of two buttons.ResultsThe old/new effect (i.e., a faster response time and more positive potentials in response to repeated stimuli than to stimuli initially presented) was observed at 350-550 ms post-stimulus. The distributions of cortical sources for the old and new stimuli were very similar at 250-650 ms after stimulus-onset. Activation in the right middle occipital gyrus/cuneus, right fusiform gyrus, left superior temporal gyrus, and right inferior frontal gyrus was significantly reduced in response to old compared with new stimuli at 250-350, 350-450, 450-550, and 550-650 ms after stimulus-onset, respectively. Priming in response time was correlated with the electrophysiological priming at left parietal area and repetition suppression at left superior temporal gyrus in 450-550 ms.ConclusionsThese results suggest processing of repeated objects is facilitated by sharpening perceptual representation and by efficient detection or attentional control of repeated objects.

P2-23: Deficits on Preference but Not Attention in Patients with Depression: Evidence from Gaze Cue

Gaze is an important social cue and can easily capture attention. Our preference judgment is biased by others' gaze; that is, we prefer objects gazed by happy or neutral faces and dislike objects gazed by disgust faces. Since patients with depression have a negative bias in emotional perception, we hypothesized that they may have different preference judgment on the gazed objects than healthy controls. Twenty-one patients with major depressive disorder and 21 healthy age-matched controls completed an object categorization task and then rated their preference on those objects. In the categorization task, a schematic face either gazed toward or away from the to-be-categorized object. The results showed that both groups categorized faster for gazed objects than non-gazed objects, suggesting that patients did not have deficits on their attention to gaze cues. Nevertheless, healthy controls preferred gazed objects more than non-gazed objects, while patients did not have significant preference. Our result indicated that patients with depression have deficits on their social cognition rather than basic attentional mechanism.

Efficient Image Classification via Multiple Rank Regression

The problem of image classification has aroused considerable research interest in the field of image processing. Traditional methods often convert an image to a vector and then use a vector-based classifier. In this paper, a novel multiple rank regression model (MRR) for matrix data classification is proposed. Unlike traditional vector-based methods, we employ multiple-rank left projecting vectors and right projecting vectors to regress each matrix data set to its label for each category. The convergence behavior, initialization, computational complexity, and parameter determination are also analyzed. Compared with vector-based regression methods, MRR achieves higher accuracy and has lower computational complexity. Compared with traditional supervised tensor-based methods, MRR performs better for matrix data classification. Promising experimental results on face, object, and hand-written digit image classification tasks are provided to show the effectiveness of our method.

Deformable Bayesian Network: A Robust Framework for Underwater Sensor Fusion

The dynamic tree (DT) graphical model is a popular analytical tool for image segmentation and object classification tasks. A DT is a useful model in this context because its hierarchical property enables the user to examine information in multiple scales and its flexible structure can more easily fit complex region boundaries compared to rigid quadtree structures such as tree-structured Bayesian networks. This paper proposes a novel framework for data fusion called a deformable Bayesian network (DFBN) by using a DT model to fuse measurements from multiple sensing platforms into a nonredundant representation. The structural flexibility of the DFBN will be used to fuse common information across different sensor measurements. The appropriate structure update strategies for the DFBN and its parameters for the data fusion application are discussed. A real-world example application using sonar images collected from a survey mission is presented. The fusion results using the presented DFBN framework are shown to outperform state-of-the-art approaches such as the Gaussian mean shift and spectral clustering algorithms. The DFBN's complexity and scalability are discussed to address its potential for a larger data set.

Cutting Affine Moment Invariants

The extraction of affine invariant features plays an important role in many fields of image processing. In this paper, the original image is transformed into new images to extract more affine invariant features. To construct new images, the original image is cut in two areas by a closed curve, which is called general contour (GC). GC is obtained by performing projections along lines with different polar angles. New image is obtained by changing gray value of pixels in inside area. The traditional affine moment invariants (AMIs) method is applied to the new image. Consequently, cutting affine moment invariants (CAMIs) are derived. Several experiments have been conducted to evaluate the proposed method. Experimental results show that CAMIs can be used in object classification tasks.

Reentrant Visual Processing Affects Rapid Object Categorization in Natural Scenes

The human visual system is very fast and efficient at extracting information about objects present in complex natural scenes. For example, Thorpe, Fize, and Marlot (1996) showed that participants were able to decide whether a natural scene contained an animal even when the image was presented briefly. Moreover, Rousselet, Fabre-Thorpe, and Thorpe (2002) used the animal versus non-animal categorization task and showed that participants could reliably indicate the side containing an animal when two images were simultaneously flashed in the left and right hemi-fields. Together, these results suggest that a great deal of visual information is processed in a fast and feedforward way so that object categorization in natural scenes can be achieved rapidly. The current study aimed to examine whether recurrent visual processing plays a role in rapid object categorization in natural scenes by using an object substitution masking paradigm. We had participants perform an object categorization task. On each trial, two images were simultaneously presented for 20 ms in the left and right visual fields; participants then had to indicate whether an animal or a vehicle appeared in the target picture, which was surrounded by eight dots. These dots either disappeared simultaneously with the target and distractor pictures or remained on the screen for 200 ms. According to Di Lollo, Enns, and Rensink (2000), object substitution masking occurs when a lateral mask (e.g., small dots) persists beyond the duration of a target, reflecting reentrant processes in vision. Therefore, the trailing dots should not affect categorization performance if rapid object categorization requires no reentrant processing from higher-level visual areas. However, our results showed that the trailing dots impaired participants' categorization performance, suggesting that reentrant visual processing affects rapid object categorization in natural scenes.

Object categorization using bone graphs

The bone graph (Macrini et al., in press, 2008) [23,25] is a graph-based medial shape abstraction that offers improved stability over shock graphs and other skeleton-based descriptions that retain unstable ligature structure. Unlike the shock graph, the bone graph’s edges are attributed, allowing a richer specification of relational information, including how and where two medial parts meet. In this paper, we propose a novel shape matching algorithm that exploits this relational information. Formulating the problem as an inexact directed acyclic graph matching problem, we extend a leading bipartite graph-based algorithm for matching shock graphs (Siddiqi et al., 1999) [41]. In addition to accommodating the relational information, our new algorithm is better able to enforce hierarchical and sibling constraints between nodes, resulting in a more general and more powerful matching algorithm. We evaluate our algorithm with respect to a competing shock graph-based matching algorithm, and show that for the task of view-based object categorization, our algorithm applied to bone graphs outperforms the competing algorithm. Moreover, our algorithm applied to shock graphs also outperforms the competing shock graph matching algorithm, demonstrating the generality and improved performance of our matching algorithm.

Visual object detection, categorization, and identification tasks are associated with different time courses and sensitivities.

Recent evidence suggests that the recognition of an object's presence and its explicit recognition are temporally closely related. Here we re-examined the time course (using a fine and a coarse temporal resolution) and the sensitivity of three possible component processes of visual object recognition. In particular, participants saw briefly presented (Experiment I to III) or noise masked (Experiment IV) static images of objects and non-object textures. Participants reported the presence of an object, its basic level category, and its subordinate category while we measured recognition performance by means of accuracy and reaction times. All three recognition tasks were clearly separable in terms of their time course and sensitivity. Finally, the use of a coarser temporal sampling of presentation times decreased performance differences between the detection and basic level categorization task suggesting that a fine temporal sampling for the dissociation of recognition performances is important. Overall the three probed recognition processes were associated with different time courses and sensitivities.

Does audiovisual speech offer a fountain of youth for old ears? An event-related brain potential study of age differences in audiovisual speech perception.

The current study addressed the question whether audiovisual (AV) speech can improve speech perception in older and younger adults in a noisy environment. Event-related potentials (ERPs) were recorded to investigate age-related differences in the processes underlying AV speech perception. Participants performed an object categorization task in three conditions, namely auditory-only (A), visual-only (V), and AVspeech. Both age groups revealed an equivalent behavioral AVspeech benefit over unisensory trials. ERP analyses revealed an amplitude reduction of the auditory P1 and N1 on AVspeech trials relative to the summed unisensory (A + V) response in both age groups. These amplitude reductions are interpreted as an indication of multisensory efficiency as fewer neural resources were recruited to achieve better performance. Of interest, the observed P1 amplitude reduction was larger in older adults. Younger and older adults also showed an earlier auditory N1 in AVspeech relative to A and A + V trials, an effect that was again greater in the older adults. The degree of multisensory latency shift was predicted by basic auditory functioning (i.e., higher hearing thresholds were associated with larger latency shifts) in both age groups. Together, the results show that AV speech processing is not only intact in older adults, but that the facilitation of neural responses occurs earlier in and to a greater extent than in younger adults. Thus, older adults appear to benefit more from additional visual speech cues than younger adults, possibly to compensate for more impoverished unisensory inputs because of sensory aging.

Processing western high- and low-ranking buildings by east asian participants: an event-related potential study

Event Abstract Back to Event Processing western high- and low-ranking buildings by east asian participants: an event-related potential study Olga Kriukova1*, Thomas Grunwald2, Heiner Mühlmann3, Xuchu Weng4 and Axel Mecklinger1 1 Saarland University, Germany 2 Swiss Epilepsy Center, Switzerland 3 Karlsruhe University of Arts and Design, Germany 4 Hangzhou Normal University, China Western architectural system traditionally distinguishes between high and low-ranking buildings. Prior research (Oppenheim et al., 2010) showed that Western participants are sensitive to the high/low ranking-building distinction even without awareness. Specifically, event related potentials (ERPs), recorded in a visual object categorization task, showed modulation of the early negative and late positive components (ENP and LPC, respectively) – components, taken to reflect early and secondary categorization processes. This tentatively suggests facilitated visual categorization of high-ranking buildings, possibly due to their cultural prominence. Here we explored whether East Asian (Chinese) participants, who have only limited exposure to Western-style architecture, would show similar sensitivity to Western high/low-ranking building distinction. ERPs were recorded in a visual object categorization task in which participants had to discriminate between objects and buildings. Building-type manipulation was not known to participants. Preliminary analysis indicates an asymmetric pattern of results in that LPC, but not ENP was modulated by the architectural rank. This suggests that Asian participants are sensitive to Western architectural ranking on the level of secondary categorization that presumably involves explicit mnemonic processes, but not on the level of early categorization processes. Taken together, the results imply that processing of architectural ranking is influenced by the (culturally-determined) amount of exposure to a particular architectural style. Funding: Supported by German Research Foundation (IRTG 1475). Keywords: EEG, Perception Conference: XI International Conference on Cognitive Neuroscience (ICON XI), Palma, Mallorca, Spain, 25 Sep - 29 Sep, 2011. Presentation Type: Poster Presentation Topic: Poster Sessions: Neurophysiology of Sensation and Perception Citation: Kriukova O, Grunwald T, Mühlmann H, Weng X and Mecklinger A (2011). Processing western high- and low-ranking buildings by east asian participants: an event-related potential study. Conference Abstract: XI International Conference on Cognitive Neuroscience (ICON XI). doi: 10.3389/conf.fnhum.2011.207.00363 Copyright: The abstracts in this collection have not been subject to any Frontiers peer review or checks, and are not endorsed by Frontiers. They are made available through the Frontiers publishing platform as a service to conference organizers and presenters. The copyright in the individual abstracts is owned by the author of each abstract or his/her employer unless otherwise stated. Each abstract, as well as the collection of abstracts, are published under a Creative Commons CC-BY 4.0 (attribution) licence (https://creativecommons.org/licenses/by/4.0/) and may thus be reproduced, translated, adapted and be the subject of derivative works provided the authors and Frontiers are attributed. For Frontiers’ terms and conditions please see https://www.frontiersin.org/legal/terms-and-conditions. Received: 23 Nov 2011; Published Online: 28 Nov 2011. * Correspondence: Dr. Olga Kriukova, Saarland University, Saarland, Germany, olga.kriukova@googlemail.com Login Required This action requires you to be registered with Frontiers and logged in. To register or login click here. Abstract Info Abstract The Authors in Frontiers Olga Kriukova Thomas Grunwald Heiner Mühlmann Xuchu Weng Axel Mecklinger Google Olga Kriukova Thomas Grunwald Heiner Mühlmann Xuchu Weng Axel Mecklinger Google Scholar Olga Kriukova Thomas Grunwald Heiner Mühlmann Xuchu Weng Axel Mecklinger PubMed Olga Kriukova Thomas Grunwald Heiner Mühlmann Xuchu Weng Axel Mecklinger Related Article in Frontiers Google Scholar PubMed Abstract Close Back to top Javascript is disabled. Please enable Javascript in your browser settings in order to see all the content on this page.

What are the visual features underlying rapid object recognition?

Research progress in machine vision has been very significant in recent years. Robust face detection and identification algorithms are already readily available to consumers, and modern computer vision algorithms for generic object recognition are now coping with the richness and complexity of natural visual scenes. Unlike early vision models of object recognition that emphasized the role of figure-ground segmentation and spatial information between parts, recent successful approaches are based on the computation of loose collections of image features without prior segmentation or any explicit encoding of spatial relations. While these models remain simplistic models of visual processing, they suggest that, in principle, bottom-up activation of a loose collection of image features could support the rapid recognition of natural object categories and provide an initial coarse visual representation before more complex visual routines and attentional mechanisms take place. Focusing on biologically plausible computational models of (bottom-up) pre-attentive visual recognition, we review some of the key visual features that have been described in the literature. We discuss the consistency of these feature-based representations with classical theories from visual psychology and test their ability to account for human performance on a rapid object categorization task.

Real-Time Measurement of Face Recognition in Rapid Serial Visual Presentation

Event-related potentials (ERPs) have been used extensively to study the processes involved in recognition memory. In particular, the early familiarity component of recognition has been linked to the FN400 (mid-frontal negative deflection between 300 and 500 ms), whereas the recollection component has been linked to a later positive deflection over the parietal cortex (500–800 ms). In this study, we measured the ERPs elicited by faces with varying degrees of familiarity. Participants viewed a continuous sequence of faces with either low (novel faces), medium (celebrity faces), or high (faces of friends and family) familiarity while performing a separate face-identification task. We found that the level of familiarity was significantly correlated with the magnitude of both the early and late recognition components. Additionally, by using a single-trial classification technique, applied to the entire evoked response, we were able to distinguish between familiar and unfamiliar faces with a high degree of accuracy. The classification of high versus low familiarly resulted in areas under the curve of up to 0.99 for some participants. Interestingly, our classifier model (a linear discriminant function) was developed using a completely separate object categorization task on a different population of participants.

Induced gamma-band activity and fixational eye movements are differentially influenced by low and high-level factors in a visual object classification task

Induced gamma-band activity and fixational eye movements are differentially influenced by low and high-level factors in a visual object classification task

Induced Gamma-Band Activity and Fixational Eye Movements are Differentially Influenced by Low-and High-Level Factors in a Visual Object Classification Task

Until recently induced high frequency oscillatory activity (gamma-band activity; >30 Hz) was considered a neural marker of cortical object representation. However, Yuval-Greenberg et al (2008; Neuron) demonstrated that induced gamma-band activity (GBA) in the elecetroencephalogram (EEG) is susceptible to artifacts caused by miniature eye movements, which account for the major part of the signal in the crucial time window of 200-400 ms after stimulus onset. Is there an underlying cortical-induced gamma-band response that is obscured by ocular artifacts but can still be recorded with EEG? Furthermore, if object-specific modulations of induced GBA in previous studies were caused by ocular artifacts, should we instead study fixational eye movements as a response that can reflect higher-level representational processes in vision? In order to investigate this, we conducted an eye tracking experiment and an EEG experiment using the same design. Participants were asked to classify line drawings of objects or non-objects. To introduce low-level differences, their contours were defined along different directions in cardinal colour space: 1) S-cone-isolating (S), or 2) intermediate isoluminant (S and L-M), or 3) a full-colour stimulus, containing an additional achromatic component (S; L-M; L+M+S). In both experiments, behavioural performance was optimal for full-colour stimuli. In the eye tracking experiment, fixational eye movement rates 200-400 ms after stimulus onset depended on low-level factors, with no difference between objects and non-objects. In the EEG experiment, miniature eye movements were identified and removed using the saccadic filter approach. The artifact-free induced GBA exhibited a lateralised distribution, with enhancements at left and right posterior sites. Activity was higher for full-colour objects on the left, with the opposite effect observed on the right. We conclude that induced GBA can be observed in the EEG. While it showed high-level object-specific modulations, miniature eye movements were driven solely by low-level information.

A unified context assessing model for object categorization

In this paper, we investigate how to appropriately use contextual information for object categorization tasks, especially in the statistical bag-of-features (BoF) framework. Our main contributions are two-folds. Firstly, we propose a context measuring mechanism which could explicitly assess roles of context features for different object recognition tasks. By analyzing information entropy and data ambiguity, only the useful and confident context information would have a final impact on categorization. Secondly, based on the context assessing results, under the BoF framework, we design unified object representations that incorporate the object appearance and contextual information from multiple spatial levels without the need of prior scene segmentations or context annotations. We evaluate the proposed method by the PASCAL object categorization task. The experimental results demonstrate that the proposed context modeling approach improves object categorization significantly and outperforms several state-of-the-art context models.