Role In Object Recognition Research Articles

HD-tDCS to the lateral occipital complex improves haptic object recognition.

High-definition transcranial direct current stimulation (HD-tDCS) is a non-invasive brain stimulation technique that has been shown to be safe and effective in modulating neuronal activity. The present study investigates the effect of anodal HD-tDCS on haptic object perception and memory through stimulation of the lateral occipital complex (LOC), a structure that has been shown to be involved in both visual and haptic object recognition. In this single-blind, sham-controlled, between-subjects study, blindfolded healthy, sighted participants used their right (dominant) hand to perform haptic discrimination and recognition tasks with 3D-printed, novel objects called "Greebles" while receiving 20min of 2 milliamp (mA) anodal stimulation (or sham) to the left or right LOC. Compared to sham, those who received left LOC stimulation (contralateral to the hand used) showed an improvement in haptic object recognition but not discrimination-a finding that was evident from the start of the behavioral tasks. A second experiment showed that this effect was not observed with right LOC stimulation (ipsilateral to the hand used). These results suggest that HD-tDCS to the left LOC can improve recognition of objects perceived via touch. Overall, this work sheds light on the LOC as a multimodal structure that plays a key role in object recognition in both the visual and haptic modalities.

The dominance of spatial information in object identity judgments: A persistent congruency bias even amidst conflicting statistical regularities.

Previous studies have posited that spatial location plays a special role in object recognition. Notably, the "spatial congruency bias (SCB)" is a tendency to report objects as the same identity if they are presented at the same location, compared to different locations. Here we found that even when statistical regularities were manipulated in the opposite direction (objects in the same location were three times more likely to be different identities), subjects still exhibited a robust SCB (more likely to report them as the same identity). We replicated this finding across two preregistered experiments. Only in a third experiment where we explicitly informed subjects of the manipulation did the SCB disappear, though the lack of a significantly reversed bias suggests the ingrained congruency bias was not completely overcome. The inclusion of catch trials where the second object was completely masked further bolsters previous evidence that the congruency bias is perceptual, not simply a guessing strategy. These results reinforce the dominant role of spatial information during object recognition and present the SCB as a strong perceptual phenomenon that is incredibly hard to overcome even in the face of opposing regularities and explicit instruction. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

AM³Net: Adaptive Mutual-Learning-Based Multimodal Data Fusion Network

Multimodal data fusion, e.g., hyperspectral image (HSI) and light detection and ranging (LiDAR) data fusion, plays an important role in object recognition and classification tasks. However, existing methods pay little attention to the specificity of HSI spectral channels and the complementarity of HSI and LiDAR spatial information. In addition, the utilized feature extraction modules tend to consider the feature transmission processes among different modalities independently. Therefore, a new data fusion network named AM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net is proposed for multimodal data classification; it includes three parts. First, an involution operator slides over the input HSI’s spectral channels, which can independently measure the contribution rate of the spectral channel of each pixel to the spectral feature tensor construction. Furthermore, the spatial information of HSI and LiDAR data is integrated and excavated in an adaptively fused, modality-oriented manner. Second, a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">spectral-spatial mutual-guided module</i> is designed for the feature collaborative transmission among spectral features and spatial information, which can increase the semantic relatedness connection through adaptive, multiscale, and mutual-learning transmission. Finally, the fused spatial-spectral features are embedded into a classification module to obtain the final results, which determines whether to continue updating the network weights. Experimental evaluations on HSI-LiDAR datasets indicate that AM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net possesses a better feature representation ability than the state-of-the-art methods. Additionally, AM <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> Net still maintains considerable performance when its input is replaced with multispectral and synthetic aperture radar data. The result indicates that the proposed data fusion framework is compatible with diversified data types.

Action planning modulates the representation of object features in human fronto-parietal and occipital cortex.

The visual cortex has been extensively studied to investigate its role in object recognition but to a lesser degree to determine how action planning influences the representation of objects' features. We used functional MRI and pattern classification methods to determine if during action planning, object features (orientation and location) could be decoded in an action‐dependent way. Sixteen human participants used their right dominant hand to perform movements (Align or Open reach) towards one of two 3D‐real oriented objects that were simultaneously presented and placed on either side of a fixation cross. While both movements required aiming towards target location, Align but not Open reach movements required participants to precisely adjust hand orientation. Therefore, we hypothesized that if the representation of object features is modulated by the upcoming action, pre‐movement activity pattern would allow more accurate dissociation between object features in Align than Open reach tasks. We found such dissociation in the anterior and posterior parietal cortex, as well as in the dorsal premotor cortex, suggesting that visuomotor processing is modulated by the upcoming task. The early visual cortex showed significant decoding accuracy for the dissociation between object features in the Align but not Open reach task. However, there was no significant difference between the decoding accuracy in the two tasks. These results demonstrate that movement‐specific preparatory signals modulate object representation in the frontal and parietal cortex, and to a lesser extent in the early visual cortex, likely through feedback functional connections.

Selective mGlu1 Potentiation Reverses Cortical Disinhibition and Schizophrenia‐like Social and Cognitive Deficits

There is a critical need to develop novel therapeutic strategies for addressing the negative and cognitive symptom domains in schizophrenia (SCZ). Multiple clinical and preclinical studies support the hypothesis that loss of GABAergic inhibitory transmission in the prefrontal cortex (PFC) and other forebrain regions may play a critical role in the pathophysiological changes underlying cognitive and social behavioral deficits in SCZ patients. Recently, we demonstrated that activation of the mGlu1 subtype of metabotropic glutamate receptor increases inhibitory transmission in the PFC by selective excitation of somatostatin‐expressing GABA interneurons. Genetic studies in humans reveal an association between deleterious non‐synonymous single nucleotide polymorphisms (nsSNPS) in of the human gene encoding mGlu1 (GRM1) and SCZ, raising the possibility that mGlu1 signaling is critical to the function of brain circuits underlying symptoms associated with this disorder.Here, we examine whether novel positive allosteric modulators (PAMs) selective for mGlu1 reverse electrophysiological effects and behavioral deficits in an MK‐801‐induced animal model of SCZ. We used ex vivo whole‐cell patch‐clamp electrophysiology to show that MK‐801 decreased the frequency of spontaneous inhibitory postsynaptic currents onto layer V pyramidal cells of the PFC, and this cortical disinhibition was reversed by mGlu1 activation. Furthermore, acute MK‐801 treatment induces inhibitory deficits onto PFC‐basolateral amygdala (BLA), but not PFC‐nucleus accumbens, projecting layer V pyramidal cells that can be reversed by selective mGlu1 activation. PFC‐BLA projections are known to contribute functionally to social‐approach behavior, while the BLA plays a critical role in object recognition and cognition broadly. We found that the mGlu1 PAM VU6004909 effectively reversed MK801‐induced deficits in social interaction and social novelty preference in a three‐chamber assay. Additionally, VU6004909 restored novel object recognition following MK‐801 treatment. In combination with our previous reports that mGlu1 PAMs reverse deficits in inhibitory transmission in the PFC, the current study provides strong evidence for mGlu1 PAMs as a promising novel approach for the treatment of social and cognitive deficits in SCZ patients.

Decoding Color Visual Working Memory from EEG Signals Using Graph Convolutional Neural Networks.

Color has an important role in object recognition and visual working memory (VWM). Decoding color VWM in the human brain is helpful to understand the mechanism of visual cognitive process and evaluate memory ability. Recently, several studies showed that color could be decoded from scalp electroencephalogram (EEG) signals during the encoding stage of VWM, which process visible information with strong neural coding. Whether color could be decoded from other VWM processing stages, especially the maintaining stage which processes invisible information, is still unknown. Here, we constructed an EEG color graph convolutional network model (ECo-GCN) to decode colors during different VWM stages. Based on graph convolutional networks, ECo-GCN considers the graph structure of EEG signals and may be more efficient in color decoding. We found that (1) decoding accuracies for colors during the encoding, early, and late maintaining stages were 81.58%, 79.36%, and 77.06%, respectively, exceeding those during the pre-stimuli stage (67.34%), and (2) the decoding accuracy during maintaining stage could predict participants' memory performance. The results suggest that EEG signals during the maintaining stage may be more sensitive than behavioral measurement to predict the VWM performance of human, and ECo-GCN provides an effective approach to explore human cognitive function.

Influence of colour on object motor representation

Colour conveys specific information about the status/quality of an object; whereas its role in object recognition has been widely studied, little is known about its role in sensorimotor processes. We performed three experiments to assess whether colour influences the motor representation of graspable objects. In Experiment 1, we used a grasp compatibility task, in which participants categorized each object as natural or artifact, by performing reach-to-grasp movements. Response grasps could be compatible or incompatible with the ones normally used to manipulate the objects. Results showed faster reaction times for natural objects displayed in the correct colour compared with both opposite colour and correct colour artifact objects. In Experiment 2, to directly assess the effect of colour on object motor representation, we used an interference task in which an irrelevant object was shown while performing a pre-specified reach-to-grasp movement (i.e., verbal cues: small vs. large). Results highlighted a reversed compatibility effect when objects were shown in their correct colour, but only at the beginning of the movement (10 ms SOA). Finally, we run a third experiment using the same task as in Experiment 2. In this experiment, we compared the grasp compatibility effect driven by natural objects with the grasp compatibility effect driven by dangerous natural objects (e.g., cactus), which are objects that should not elicit a grasping program. The results of Experiment 3 confirm those of Experiment 2, highlighting also specific processes related to dangerous objects. Taken together, these results revealed that colour can be significant for the motor system, highlighting the close link between colour and shape, and also specific processes related to dangerous objects.

Causal importance of low-level feature selectivity for generalization in image recognition

Although our brain and deep neural networks (DNNs) can perform high-level sensory-perception tasks, such as image or speech recognition, the inner mechanism of these hierarchical information-processing systems is poorly understood in both neuroscience and machine learning. Recently, Morcos et al. (2018) examined the effect of class-selective units in DNNs, i.e., units with high-level selectivity, on network generalization, concluding that hidden units that are selectively activated by specific input patterns may harm the network’s performance. In this study, we revisited their hypothesis, considering units with selectivity for lower-level features, and argue that selective units are not always harmful to the network performance. Specifically, by using DNNs trained for image classification, we analyzed the orientation selectivity of individual units, a low-level selectivity widely studied in visual neuroscience. We found that orientation-selective units exist in both lower and higher layers of these DNNs, as in our brain. In particular, units in lower layers became more orientation-selective as the generalization performance improved during the course of training. Consistently, networks that generalized better were more orientation-selective in the lower layers. We finally revealed that ablating these selective units in the lower layers substantially degraded the generalization performance of the networks, at least by disrupting the shift-invariance of the higher layers. These results suggest that orientation selectivity can play a causally important role in object recognition, and that, contrary to the triviality of units with high-level selectivity, lower-layer units with selectivity for low-level features may be indispensable for generalization, at least for the several network architectures.

Surface diagnosticity predicts the high-level representation of regular and irregular object shape in human vision

The human visual system has an extraordinary capacity to compute three-dimensional (3D) shape structure for both geometrically regular and irregular objects. The goal of this study was to shed new light on the underlying representational structures that support this ability. Observers (N = 85) completed two complementary perceptual tasks. Experiment 1 involved whole–part matching of image parts to whole geometrically regular and irregular novel object shapes. Image parts comprised either regions of edge contour, volumetric parts, or surfaces. Performance was better for irregular than for regular objects and interacted with part type: volumes yielded better matching performance than surfaces for regular but not for irregular objects. The basis for this effect was further explored in Experiment 2, which used implicit part–whole repetition priming. Here, we orthogonally manipulated shape regularity and a new factor of surface diagnosticity (how predictive a single surface is of object identity). The results showed that surface diagnosticity, not object shape regularity, determined the differential processing of volumes and surfaces. Regardless of shape regularity, objects with low surface diagnosticity were better primed by volumes than by surfaces. In contrast, objects with high surface diagnosticity showed the opposite pattern. These findings are the first to show that surface diagnosticity plays a fundamental role in object recognition. We propose that surface-based shape primitives—rather than volumetric parts—underlie the derivation of 3D object shape in human vision.

Conversion of object identity to object-general semantic value in the primate temporal cortex.

At the final stage of the ventral visual stream, perirhinal neurons encode the identity of memorized objects through learning. However, it remains elusive whether and how object percepts alone, or concomitantly a nonphysical attribute of the objects ("learned"), are decoded from perirhinal activities. By combining monkey psychophysics with optogenetic and electrical stimulations, we found a focal spot of memory neurons where both stimulations led monkeys to preferentially judge presented objects as "already seen." In an adjacent fringe area, where neurons did not exhibit selective responses to the learned objects, electrical stimulation induced the opposite behavioral bias toward "never seen before," whereas optogenetic stimulation still induced bias toward "already seen." These results suggest that mnemonic judgment of objects emerges via the decoding of their nonphysical attributes encoded by perirhinal neurons.

Faulty remembrance of objects past

Neuroscience The primate brain analyzes visual input along the ventral processing stream to extract the identity of an object. The final stage of this stream, the perirhinal cortex, plays a crucial role in object recognition. Tamura et al. systematically biased the judgments of monkeys in an old-new

A biologically inspired spatio-chromatic feature for color object recognition

Color information has been acknowledged for its important role in object recognition and scene classification. How to describe the color characteristics and extract combined spatial and chromatic feature is a challenging task in computer vision. In this paper we extend the robust SIFT feature on processed opponent color channels to obtain a spatio-chromatic descriptor for color object recognition. The color information processing is implemented under a biologically inspired hierarchical framework, where cone cells, single-opponent and double-opponent cells are simulated respectively to mimic the color perception of primate visual system. The biologically inspired method is tested for object recognition task on two public datasets, and the results support the potential of our proposed approach.

A Representation and Matching Algorithm for Planar Curve Based on Distance Ratio and Concentric Circles

Curve Matching plays a significant role in object recognition, target tracking and fragment reassembling. This paper presents a representation and matching algorithm for planar curve based on sub-matrix and concentric circles. The algorithm includes two steps, namely rough matching and exact matching. The rough matching uses a sub-matrix matching method. As for exact matching, first, the representation of curve uses concentric circles and then measures their similarity through two curve representation sets of concentric circles. Our algorithm which is robust to the translation, rotation and scaling, can be used to match block objects and SAR image registration. The experiment results show us the effectiveness and feasibility of algorithm.

Polar radius integral transform for affine invariant feature extraction

Affine transform is to describe the same target at different viewpoints to obtain the relationship between images of approximate model. Affine invariant feature extraction plays an important role in object recognition and image registration. Firstly, the definition of polar radius integral transform (PRIT) is put forward by means of the characterization of affine transform mapping straight line into straight line, where PRIT computes the integral along the polar radius direction and converts images into closed curves which keep the same affine transform with original images. Secondly, in order to extract affine invariant feature, an affine invariant feature extraction algorithm is also given based on PRIT. The proposed algorithm can be used to combine contour-based methods with region-based methods. It has some advantages of fewer amounts of computations and feasibility of feature extraction for objects with several components. Finally, the capability of anti-noise (Gaussian noise, salt and pepper noise) of PRIT is discussed. The simulation experiment results show that PRIT can effectively extract the affine invariant features, but also the low order PRIT has very strong robustness to noise.

Learning Warps Object Representations in the Ventral Temporal Cortex.

The human ventral temporal cortex (VTC) plays a critical role in object recognition. Although it is well established that visual experience shapes VTC object representations, the impact of semantic and contextual learning is unclear. In this study, we tracked changes in representations of novel visual objects that emerged after learning meaningful information about each object. Over multiple training sessions, participants learned to associate semantic features (e.g., "made of wood," "floats") and spatial contextual associations (e.g., "found in gardens") with novel objects. fMRI was used to examine VTC activity for objects before and after learning. Multivariate pattern similarity analyses revealed that, after learning, VTC activity patterns carried information about the learned contextual associations of the objects, such that objects with contextual associations exhibited higher pattern similarity after learning. Furthermore, these learning-induced increases in pattern information about contextual associations were correlated with reductions in pattern information about the object's visual features. In a second experiment, we validated that these contextual effects translated to real-life objects. Our findings demonstrate that visual object representations in VTC are shaped by the knowledge we have about objects and show that object representations can flexibly adapt as a consequence of learning with the changes related to the specific kind of newly acquired information.

Three-Dimensional Representations of Objects in Dorsal Cortex are Dissociable from Those in Ventral Cortex.

An established conceptualization of visual cortical function is one in which ventral regions mediate object perception while dorsal regions support spatial information processing and visually guided action. This division has been contested by evidence showing that dorsal regions are also engaged in the representation of object shape, even when actions are not required. The critical question is whether these dorsal, object-based representations are dissociable from ventral representations, and whether they play a functional role in object recognition. We examined the neural and behavioral profile of patients with impairments in object recognition following ventral cortex damage. In a functional magnetic resonanace imaging experiment, the blood oxygen level-dependent response in the ventral, but not dorsal, cortex of the patients evinced less sensitivity to object 3D structure compared with that of healthy controls. Consistently, in psychophysics experiments, the patients exhibited significant impairments in object perception, but still revealed residual sensitivity to object-based structural information. Together, these findings suggest that, although in the intact system there is considerable crosstalk between dorsal and ventral cortices, object representations in dorsal cortex can be computed independently from those in ventral cortex. While dorsal representations alone are unable to support normal object perception, they can, nevertheless, support a coarse description of object structural information.

Special issue on real-time color image processing

Color perception plays an important role in object recognition and scene understanding both for humans and intelligent vision systems. Recent advances in digital color imaging and computer hardware technology have led to an explosion in the use of color images in a variety of applications including medical imaging, content-based image retrieval, biometrics, watermarking, digital inpainting, remote sensing, visual quality inspection, among many others. As a result, automated processing and analysis of color images has become an active area of research, which is witnessed by the large number of publications during the past two decades. The multivariate nature of color image data presents new challenges for researchers and practitioners as the numerous methods developed for singlechannel images are often not directly applicable to multichannel images. In addition, common scalar image processing operations often become computationally intractable when performed in high-dimensional spaces. As a result, the development of computationally practical methods for color image processing has become an important research area. The goals of this special issue are to summarize the state-of-the-art in real-time color image processing and to provide future directions for this exciting subfield of image processing. The intended audience includes researchers and professionals, who are increasingly dealing with the processing and analysis of color images and video. The special issue opens with ‘‘Design of a Shift-andAdd Based Hardware Accelerator for Color Space Conversion’’ by Li et al. The authors propose a hardware/software co-design architecture for Nios II, a 32-bit embedded processor. The architecture integrates a pipelined color space converter hardware accelerator based on a genetic algorithm and an LCD touch module. When implemented on a system-on-a-programmable-chip, the proposed architecture is capable of converting a 512 512 RGB image to YCbCr in 0:11 s. The special issue continues with seven articles on color image enhancement. In ‘‘A Simple Gray-Edge Automatic White Balance Method with FPGA Implementation,’’ Tan et al. propose a real-time automatic white balance method based on the gray-edge hypothesis. To reduce computational time, the method employs horizontal downsampling using the mean filter and gradient computation using horizontal first-order difference operator. The authors demonstrate the practicality of their approach using an FPGA implementation. In ‘‘A Full Linear 3 3 Color Correction between Images,’’ Lecca describes a fast color correction algorithm that is capable of equalizing the colors of two images of the same scene that are acquired under different illuminants and/or by different devices. The author demonstrates the performance of her approach against two state-of-the-art approaches on a variety of synthetic and real-world image databases. The method has linear time complexity in the M. E. Celebi (&) Department of Computer Science, Louisiana State University, Shreveport, LA, USA e-mail: ecelebi@lsus.edu

Mechanisms of object recognition: what we have learned from pigeons.

Behavioral studies of object recognition in pigeons have been conducted for 50 years, yielding a large body of data. Recent work has been directed toward synthesizing this evidence and understanding the visual, associative, and cognitive mechanisms that are involved. The outcome is that pigeons are likely to be the non-primate species for which the computational mechanisms of object recognition are best understood. Here, we review this research and suggest that a core set of mechanisms for object recognition might be present in all vertebrates, including pigeons and people, making pigeons an excellent candidate model to study the neural mechanisms of object recognition. Behavioral and computational evidence suggests that error-driven learning participates in object category learning by pigeons and people, and recent neuroscientific research suggests that the basal ganglia, which are homologous in these species, may implement error-driven learning of stimulus-response associations. Furthermore, learning of abstract category representations can be observed in pigeons and other vertebrates. Finally, there is evidence that feedforward visual processing, a central mechanism in models of object recognition in the primate ventral stream, plays a role in object recognition by pigeons. We also highlight differences between pigeons and people in object recognition abilities, and propose candidate adaptive specializations which may explain them, such as holistic face processing and rule-based category learning in primates. From a modern comparative perspective, such specializations are to be expected regardless of the model species under study. The fact that we have a good idea of which aspects of object recognition differ in people and pigeons should be seen as an advantage over other animal models. From this perspective, we suggest that there is much to learn about human object recognition from studying the “simple” brains of pigeons.

A Novel Equation based Classifier for Detecting Human in Images

Shape based classification is one of the most challenging tasks in the field of computer vision. Shapes play a vital role in object recognition. The basic shapes in an image can occur in varying scale, position and orientation. And specially when detecting human, the task becomes more challenging owing to the largely varying size, shape, posture and clothing of human. So, in our work we detect human, based on the head-shoulder shape as it is the most unvarying part of human body. Here, firstly a new and a novel equation named as the Omega Equation that describes the shape of human head-shoulder is developed and based on this equation, a classifier is designed particularly for detecting human presence in a scene. The classifier detects human by analyzing some of the discriminative features of the values of the parameters obtained from the Omega equation. The proposed method has been tested on a variety of shape dataset taking into consideration the complexities of human head-shoulder shape. In all the experiments the proposed method demonstrated satisfactory results.

Perceptually motivated shape context which uses shape interiors

In this paper, we identify some of the limitations of current-day shape-matching techniques. We provide examples of how contour-based shape-matching techniques cannot provide a good match for certain visually similar shapes. To overcome this limitation, we propose a perceptually motivated variant of the well-known shape context descriptor. We identify that the interior properties of the shape play an important role in object recognition and develop a descriptor that captures these interior properties. We show that our method can easily be augmented with any other shape-matching algorithm. We also show from our experiments that the use of our descriptor can significantly improve the retrieval rates.