检索结果-内蒙古大学图书馆

visual object recognition From Single-Trial EEG Signals Using Machine Learning Wrapper Techniques

IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING 2022年第7期69卷 2176-2183页

作者： Yavandhasani, Mojtaba Ghaderi, Foad Tarbiat Modares Univ Human Comp Interact Lab Elect & Comp Engn Dept Tehran *** Iran

Responses of the human brain to different visual stimuli elicit specific patterns in electroencephalography (EEG) signals. It is confirmed that by analyzing these patterns, we can recognize the category of the visited objects. However, high levels of noise and artifacts in EEG signals and the discrepancies between the recorded data from different subjects in visual object recognition task make classification of cognitive states of subjects a serious challenge. In this research, we present a framework for evaluating machine learning and wrapper channel selection algorithms used for classifying single-trial EEG signals recorded in response to photographic stimuli. It is shown that by correctly mapping the entire EEG data space to informative feature spaces (IFS), the performance of the classification methods can improve significantly. Results outperform the state-of-the-art results and confirm efficiency of the proposed feature selection methods in capturing the most informative EEG channels. This can help to achieve high separability of object categories in single-trial visual object recognition task.

关键词： Electroencephalography visualization Task analysis Feature extraction Classification algorithms Brain modeling object recognition Dimensionality reduction informative feature space (IFS) wrapper channel selection single-trial EEG visual object recognition

来源：评论

学校读者我要写书评

暂无评论

visual object recognition using probabilistic kernel subspace similarity

引用

PATTERN recognition 2005年第7期38卷 997-1008页

作者： Lee, JG Wang, JD Zhang, CS Bian, ZQ Tsinghua Univ Dept Automat Beijing 100084 Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci Hong Kong Hong Kong Peoples R China

Probabilistic subspace similarity-based face matching is an efficient face recognition algorithm proposed by Moghaddam et al. It makes one basic assumption: the intra-class face image set spans a linear space. However, there are yet no rational geometric interpretations of the similarity under that assumption. This paper investigates two subjects. First, we present one interpretation of the intra-class linear subspace assumption from the perspective of manifold analysis, and thus discover the geometric nature of the similarity. Second, we also note that the linear subspace assumption does not hold in some cases, and generalize it to nonlinear cases by introducing kernel tricks. The proposed model is named probabilistic kernel subspace similarity (PKSS). Experiments on synthetic data and real visual object recognition tasks show that PKSS can achieve promising performance, and outperform many other current popular object recognition algorithms. (c) 2005 Pattern recognition Society. Published by Elsevier Ltd. All rights reserved.

关键词： subspace analysis tangent distance kernel methods visual object recognition manifold analysis

来源：评论

学校读者我要写书评

暂无评论

visual object recognition USING DAISY DESCRIPTOR

VISUAL OBJECT RECOGNITION USING DAISY DESCRIPTOR

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhu, Chao Bichot, Charles-Edmond Chen, Liming Univ Lyon CNRS Ecole Cent Lyon LIRISUMR5205 F-69134 Lyon France

ISBN: (纸本)9781612843490

visual content description is a key issue for the task of machine-based visual object categorization (VOC). A good visual descriptor should be both discriminative enough and computationally efficient while possessing some properties of robustness to viewpoint changes and lighting condition variations. The recent literature has featured local image descriptors, e. g. SIFT, as the main trend in VOC. However, it is well known that SIFT is computationally expensive, especially when the number of objects/concepts and learning data increase significantly. In this paper, we investigate the DAISY, which is a new fast local descriptor introduced for wide baseline matching problem, in the context of VOC. We carefully evaluate and compare the DAISY descriptor with SIFT both in terms of recognition accuracy and computation complexity on two standard image benchmarks - Caltech 101 and PASCAL VOC 2007. The experimental results show that DAISY outperforms the state-of-the-art SIFT while using shorter descriptor length and operating 3 times faster. When displaying a similar recognition accuracy to SIFT, DAISY can operate 12 times faster.

关键词： visual object recognition local image descriptors DAISY SIFT

来源：评论

学校读者我要写书评

暂无评论

Multiple Kernel Learning for visual object recognition: A Review

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2014年第7期36卷 1354-1369页

作者： Bucak, Serhat S. Jin, Rong Jain, Anil K. Michigan State Univ Dept Comp Sci & Engn E Lansing MI 48824 USA Korea Univ Dept Brain & Cognit Engn Seoul South Korea

Multiple kernel learning (MKL) is a principled approach for selecting and combining kernels for a given recognition task. A number of studies have shown that MKL is a useful tool for object recognition, where each image is represented by multiple sets of features and MKL is applied to combine different feature sets. We review the state-of-the-art for MKL, including different formulations and algorithms for solving the related optimization problems, with the focus on their applications to object recognition. One dilemma faced by practitioners interested in using MKL for object recognition is that different studies often provide conflicting results about the effectiveness and efficiency of MKL. To resolve this, we conduct extensive experiments on standard datasets to evaluate various approaches to MKL for object recognition. We argue that the seemingly contradictory conclusions offered by studies are due to different experimental setups. The conclusions of our study are: (i) given a sufficient number of training examples and feature/kernel types, MKL is more effective for object recognition than simple kernel combination (e.g., choosing the best performing kernel or average of kernels);and (ii) among the various approaches proposed for MKL, the sequential minimal optimization, semi-infinite programming, and level method based ones are computationally most efficient.

关键词： Multiple kernel learning support vector machine visual object recognition convex optimization

来源：评论

学校读者我要写书评

暂无评论

Invariant visual object recognition: biologically plausible approaches

引用

BIOLOGICAL CYBERNETICS 2015年第4-5期109卷 505-535页

作者： Robinson, Leigh Rolls, Edmund T. Univ Warwick Dept Comp Sci Coventry CV4 7AL W Midlands England Oxford Ctr Computat Neurosci Oxford England

Key properties of inferior temporal cortex neurons are described, and then, the biological plausibility of two leading approaches to invariant visual object recognition in the ventral visual system is assessed to investigate whether they account for these properties. Experiment 1 shows that VisNet performs object classification with random exemplars comparably to HMAX, except that the final layer C neurons of HMAX have a very non-sparse representation (unlike that in the brain) that provides little information in the single-neuron responses about the object class. Experiment 2 shows that VisNet forms invariant representations when trained with different views of each object, whereas HMAX performs poorly when assessed with a biologically plausible pattern association network, as HMAX has no mechanism to learn view invariance. Experiment 3 shows that VisNet neurons do not respond to scrambled images of faces, and thus encode shape information. HMAX neurons responded with similarly high rates to the unscrambled and scrambled faces, indicating that low-level features including texture may be relevant to HMAX performance. Experiment 4 shows that VisNet can learn to recognize objects even when the view provided by the object changes catastrophically as it transforms, whereas HMAX has no learning mechanism in its S-C hierarchy that provides for view-invariant learning. This highlights some requirements for the neurobiological mechanisms of high-level vision, and how some different approaches perform, in order to help understand the fundamental underlying principles of invariant visual object recognition in the ventral visual stream.

关键词： visual object recognition Invariant representations Inferior temporal visual cortex VisNet HMAX Trace learning rule

来源：评论

学校读者我要写书评

暂无评论

Brain-inspired models for visual object recognition: an overview

引用

ARTIFICIAL INTELLIGENCE REVIEW 2022年第7期55卷 5263-5311页

作者： Yang, Xi Yan, Jie Wang, Wen Li, Shaoyi Hu, Bo Lin, Jian Northwestern Polytech Univ Sch Astronaut 127 West Youyi Rd Xian 710072 Shaanxi Peoples R China Fourth Mil Med Univ Tangdu Hosp Dept Radiol Funct & Mol Imaging Key Lab Shaanxi Prov 569 Xinsi Rd Xian 710038 Shaanxi Peoples R China Northwestern Polytech Univ Unmanned Syst Res Inst 127 West Youyi Rd Xian 710072 Shaanxi Peoples R China

visual object recognition is one of the most fundamental and challenging research topics in the field of computer vision. The research on the neural mechanism of the primates' recognition function may bring revolutionary breakthroughs in brain-inspired vision. This Review aims to systematically review the recent works on the intersection of computational neuroscience and computer vision. It attempts to investigate the current brain-inspired object recognition models and their underlying visual neural mechanism. According to the technical architecture and exploitation methods, we describe the brain-inspired object recognition models and their advantages and disadvantages in realizing brain-inspired object recognition. We focus on analyzing the similarity between the artificial and biological neural network, and studying the biological credibility of the current popular DNN-based visual benchmark models. The analysis provides a guide for researchers to measure the occasion and condition when conducting visual object recognition research.

关键词： Brain-inspired visual object recognition visual cortex Neural mechanism DNN-based Biological credibility

来源：评论

学校读者我要写书评

暂无评论

Next Generation Imaging in Consumer Technology for ERP Detection-Based EEG Cross-Subject visual object recognition

引用

IEEE TRANSACTIONS ON CONSUMER ELECTRONICS 2024年第1期70卷 3688-3696页

作者： Bhatt, Mohammed Wasim Sharma, Sparsh Natl Inst Technol Srinagar Dept Comp Sci & Engn Srinagar 190006 India

The perception and recognition of objects are essential for meeting consumer needs in the realm of consumer technology. Current research exploring the association between variations in brain activity and their prospective application in user-friendly brain-machine interfaces (BMIs) has been growing significant momentum. To this end, a novel model is proposing that enhance the detection of event-related potentials (ERP) from EEG signals, particularly for visual object recognition across different subjects, incorporating next generation imaging technology tailored for consumer electronics. It utilizes a graph representation that captures EEG spatial information, across all subjects and tasks. It merges a convolutional neural network (CNN) with a long short-term memory network (LSTM), creating a solid CNN-LSTM architecture followed by dual-attention mechanism. It includes both selective kernel convolution and self-attention mechanisms. They jointly work to precisely capture the unique spatiotemporal characteristics of EEG signals from various subjects. This results in boosting the accuracy of ERP detection for individuals. Experimental validation of the proposed model shows promising results. It was tested on a comprehensive benchmark dataset designed around the rapid serial visual presentation paradigm. The data shows that this new method outperforms seven existing ERP detection techniques in scenarios involving different subjects.

关键词： Event-related potentials visual object recognition cross-subject analysis graph representation consumer technology

来源：评论

学校读者我要写书评

暂无评论

Non-accidental properties, metric invariance, and encoding by neurons in a model of ventral stream visual object recognition, VisNet

引用

NEUROBIOLOGY OF LEARNING AND MEMORY 2018年 152卷 20-31页

作者： Rolls, Edmund T. Mills, W. Patrick C. Oxford Ctr Computat Neurosci Oxford England Univ Warwick Dept Comp Sci Coventry W Midlands England

When objects transform into different views, some properties are maintained, such as whether the edges are convex or concave, and these non-accidental properties are likely to be important in view-invariant object recognition. The metric properties, such as the degree of curvature, may change with different views, and are less likely to be useful in object recognition. It is shown that in a model of invariant visual object recognition in the ventral visual stream, VisNet, non-accidental properties are encoded much more than metric properties by neurons. Moreover, it is shown how with the temporal trace rule training in VisNet, non-accidental properties of objects become encoded by neurons, and how metric properties are treated invanantly. We also show how VisNet can generalize between different objects if they have the same non-accidental property, because the metric properties are likely to overlap. VisNet is a 4-layer unsupervised model of visual object recognition trained by competitive learning that utilizes a temporal trace learning rule to implement the learning of invariance using views that occur close together in time. A second crucial property of this model of object recognition is, when neurons in the level corresponding to the inferior temporal visual cortex respond selectively to objects, whether neurons in the intermediate layers can respond to combinations of features that may be parts of two or more objects. In an investigation using the four sides of a square presented in every possible combination, it was shown that even though different layer 4 neurons are tuned to encode each feature or feature combination orthogonally, neurons in the intermediate layers can respond to features or feature combinations present is several objects. This property is an important part of the way in which high capacity can be achieved in the four-layer ventral visual cortical pathway. These findings concerning non-accidental properties and the use of neurons in interme

关键词： visual object recognition Non-accidental properties visual coding Unsupervised learning Invariant representations Inferior temporal visual cortex VisNet Trace learning rule Slow learning

来源：评论

学校读者我要写书评

暂无评论

Individual differences in involvement of the visual object recognition system during visual word recognition

引用

BRAIN AND LANGUAGE 2015年 145卷 42-52页

作者： Laszlo, Sarah Sacchi, Elizabeth SUNY Binghamton Dept Psychol Binghamton NY 13902 USA SUNY Binghamton Program Linguist Binghamton NY 13902 USA

Individuals with dyslexia often evince reduced activation during reading in left hemisphere (LH) language regions. This can be observed along with increased activation in the right hemisphere (RH), especially in areas associated with object recognition - a pattern referred to as RH compensation. The mechanisms of RH compensation are relatively unclear. We hypothesize that RH compensation occurs when the RH object recognition system is called upon to supplement an underperforming LH visual word form recognition system. We tested this by collecting ERPs while participants with a range of reading abilities viewed words, objects, and word/object ambiguous items (e.g., "SMILE" shaped like a smile). Less experienced readers differentiate words, objects, and ambiguous items less strongly, especially over the RH. We suggest that this lack of differentiation may have negative consequences for dyslexic individuals demonstrating RH compensation. (C) 2015 Elsevier Inc. All rights reserved.

关键词： Event-related potentials visual word recognition visual object recognition Individual differences

来源：评论

学校读者我要写书评

暂无评论

Hemispheric Organization for visual object recognition: A Theoretical Account and Empirical Evidence*

引用

PERCEPTION 2020年第4期49卷 373-404页

作者： Behrmann, Marlene Plaut, David C. Carnegie Mellon Univ Dept Psychol Pittsburgh PA 15213 USA Carnegie Mellon Univ Neurosci Inst Pittsburgh PA 15213 USA

Despite the similarity in structure, the hemispheres of the human brain have somewhat different functions. A traditional view of hemispheric organization asserts that there are independent and largely lateralized domain-specific regions in ventral occipitotemporal (VOTC), specialized for the recognition of distinct classes of objects. Here, we offer an alternative account of the organization of the hemispheres, with a specific focus on face and word recognition. This alternative account relies on three computational principles: distributed representations and knowledge, cooperation and competition between representations, and topography and proximity. The crux is that visual recognition results from a network of regions with graded functional specialization that is distributed across both hemispheres. Specifically, the claim is that face recognition, which is acquired relatively early in life, is processed by VOTC regions in both hemispheres. Once literacy is acquired, word recognition, which is co-lateralized with language areas, primarily engages the left VOTC and, consequently, face recognition is primarily, albeit not exclusively, mediated by the right VOTC. We review psychological and neural evidence from a range of studies conducted with normal and brain-damaged adults and children and consider findings which challenge this account. Last, we offer suggestions for future investigations whose findings may further refine this account.

关键词： hemispheric organization visual object recognition neural basis distributed organization

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：