检索结果-内蒙古大学图书馆

Emergence Model of Perception with Global-contour Precedence Based on Gestalt Theory and Primary Visual Cortex

IEEE Transactions on Image Processing 2025年 34卷 2721-2736页

作者： Li, Jingmeng Wei, Hui Fudan University Laboratory of Algorithms for Cognitive Models School of Computer Science Shanghai200438 China Fudan University Laboratory of Algorithms for Cognitive Models Innovation Center of Calligraphy and Painting Creation Technology MCT School of Computer Science Shanghai200438 China

Perceptual edge grouping is a technique for organizing the cluttered edge pixels into meaningful structures and further serves high-level vision tasks, which has long been a basic and critical task in computer vision. Existing methods usually have a poor performance when coping with the junctions caused by occlusion and noise in natural images. In this paper, we present GPGrouper, a perceptual edge grouping model based on gestalt theory and the primary visual cortex (V1). Different from the existing methods, GPGrouper leverages the edge representation and grouping matrix (ERGM), a functional structure inspired by V1 mechanisms, to represent edges in a way that can effectively reduce grouping errors caused by occlusion between objects. ERGM is trained with natural image contours and further provides a priori guidance for the construction of the edge connection graph (ECG) that is useful to minimize the impact of noise on grouping. In the experiment, we compared GPGrouper and the state-of-the-art (SOTA) method of perceptual grouping on the visual psychology pathfinder challenge. The results demonstrate that GPGrouper outperforms the SOTA method in grouping performance. Furthermore, in the grouping experiments involving line segments with varying lengths detected by the Line Segment Detector (LSD), as well as those involving superpixel segmentation results with significant levels of interfering noise using the SLIC algorithm, GPGrouper was superior to the existing methods in terms of grouping effect and robustness. Moreover, the results of applying the grouping results to the vision tasks objectness demonstrate that GPGrouper can contribute significantly to high-level visual tasks. © 1992-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Enhanced genetic algorithm for indoor low-illumination stereo matching energy function optimization

引用

Alexandria Engineering Journal 2025年 121卷 1-17页

作者： Hongjin, Zhang Hui, Wei Laboratory of Algorithms for Cognitive Models School of Computer Science Fudan University Handan Road 220 ShangHai China College of Engineering Science and Technology Shanghai Ocean University Huchenghuan Road 999 ShangHai China

This study presents an enhanced genetic algorithm to generate high-quality, dense disparity maps in low-illumination indoor stereo matching scenarios. The algorithm utilizes a novel biomimetic mutation strategy, dynamically adjusted through common allelic theory, to effectively reduce the search space and improve optimization efficiency. A multi-objective genetic approach is employed, optimizing both data fidelity and smoothness to achieve balanced and accurate results. The Integration of biological evolution principles, including a hierarchical performance index system, ensures the algorithm balances local and global features during optimization. Experimental results demonstrate that the proposed algorithm consistently converges within 10 iterations, reducing average disparity errors by 33.7% compared to state-of-the-art methods and by 20% compared to a control group. Additionally, the algorithm achieves a lower computational complexity of O(H), offering significant improvements in resource efficiency compared to standard algorithms. These findings validate the algorithm's reliability, advancement, and effectiveness for stereo matching under challenging conditions. © 2025 The Authors

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

On competing agents consistent with expert knowledge

On competing agents consistent with expert knowledge

引用

2nd International Workshop on Autonomous Intelligent System - Agents and Data Mining

作者： Pogossian, Edward Vahradyan, Vachagan Grigoryan, Arthur Cognitive Algorithms and Models Laboratory Academy of Sciences of Armenia (IPIA) State Engineering Universities of Armenia

ISBN: (纸本)9783540728382

We aim to advance in constructing collaborative agents able to acquire the contents of human vocabulary associated with competitions. Refining the framework and criteria of performance of agents we project the study on the class of game tree represented competition problems. For known representative of the class - chess like combinatorial games, we categorize the contents of a comprehensive repository of units of chess vocabulary by formal structures of attributes, goals, strategies, plans, etc. We define Personalized Planning and Integrated Testing algorithms able to elaborate moves in target positions dependent on those categories of chess knowledge. We then demonstrate the effectiveness of the algorithms by experiments in acquisition the solutions of two top Botvinnik's tests - the Reti and Nodareishvili etudes. For min max game tree based search algorithms these etudes appears to be computationally hard due the depth of the required analysis and very dependence on the expert knowledge.

关键词： competing agents knowledge acquisition consistent measures

来源：评论

学校读者我要写书评

暂无评论

Avoiding Non-Manhattan Obstacles Based on Projection of Spatial Corners in Indoor Environment

引用

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1190-1200页

作者： Luping Wang Hui Wei the School of Mechanical Engineering University of Shanghai for Science and TechnologyShanghai 200093China the Laboratory of Algorithms for Cognitive Models Shanghai Key Laboratory of Data ScienceSchool of Computer ScienceFudan UniversityShanghai 201203China

Monocular vision-based navigation is a considerable ability for a home mobile robot. However, due to diverse disturbances, helping robots avoid obstacles, especially nonManhattan obstacles, remains a big challenge. In indoor environments, there are many spatial right-corners that are projected into two dimensional projections with special geometric configurations. These projections, which consist of three lines,might enable us to estimate their position and orientation in 3 D scenes. In this paper, we present a method for home robots to avoid non-Manhattan obstacles in indoor environments from a monocular camera. The approach first detects non-Manhattan obstacles. Through analyzing geometric features and constraints,it is possible to estimate posture differences between orientation of the robot and non-Manhattan obstacles. Finally according to the convergence of posture differences, the robot can adjust its orientation to keep pace with the pose of detected non-Manhattan obstacles, making it possible avoid these obstacles by itself. Based on geometric inferences, the proposed approach requires no prior training or any knowledge of the camera’s internal parameters,making it practical for robots navigation. Furthermore, the method is robust to errors in calibration and image noise. We compared the errors from corners of estimated non-Manhattan obstacles against the ground truth. Furthermore, we evaluate the validity of convergence of differences between the robot orientation and the posture of non-Manhattan obstacles. The experimental results showed that our method is capable of avoiding non-Manhattan obstacles, meeting the requirements for indoor robot navigation.

关键词： Avoiding obstacle monocular vision navigation non-Manhattan obstacle spatial corner

来源：评论

学校读者我要写书评

暂无评论

Specifying personalized expertise

Specifying personalized expertise

引用

IADIS International Conference on Cognition and Exploratory Learning in Digital Age, CELDA 2006

作者： Pogossian, Edward Cognitive Algorithms and Models Laboratory Academy of Sciences and State Engineering University of Armenia # 24 Marshall Bagramyan Avenue 375019 Yerevan Armenia

ISBN: (纸本)9781627483315

We aim to understand the role and proportion of personalized expertise compared with common, communicable one. To make the studying constructive we concentrate on a particular class of game represented problems and go in the depth of a typical representative of the class, the chess. We simulate and analyze expert requests to the games storage in a natural language to find winning strategies of the specified types. The correspondence revealed between units of chess vocabulary and winning by zermelo classes of chess positions and strategies argues for a constructive nature of the content of the units, in principle, allowing to simulate them. At the same time it states that any real implementation of those contents, in principle, can be only an approximation to the original winning game tree structures due to a prohibitive complexity of computations required to prove correctness of the vast majority of the contents. Thus, we get a precedent of a measurable specification of human expertise where the learned contents of realities having the same vocabulary, as a rule, are essentially personalized.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Why Does the Cortex Have Such a Vast Storage Capacity?

arXiv

引用

arXiv 2024年

作者： Wei, Hui Yang, Surun Li, Yangwang Laboratory of Algorithms for Cognitive Models Fudan University Shanghai200433 China

The capacity of long-term memory seems to be extremely large, capable of storing information spanning almost a lifetime. Why does it have such a vast capacity? Why are some memories so enduring? What is the actual physical form of long-term memory? In the movie Inside Out, it is depicted as individual orbs containing information. Is that really the case? Simply explaining this by saying that the cortex has many neurons, numerous neural connections, and complex electrochemical activity between them is not sufficient to answer these fundamental questions. We need to uncover the theory hidden behind these *** essence, a neural network is equivalent to a very large directed graph, with a massive number of nodes and directed connections. This paper posits that the physical form of long-term memory is a connected subgraph within this complex directed graph. This subgraph is capable of linking together the disparate fragments of the same event, spread across different sensory cortices, to form associations. This provides a physical realization of the engram theory. The robustness of the connected subgraph and the resources it consumes can explain various memory *** on anatomical, brain imaging and electrophysiological evidence, this paper constructs a probabilistic connectivity model and uses theorems from graph theory to prove the ease of constructing connected subgraphs. Finally, it explains why the potential capacity for memory is immense. © 2024, CC BY-NC-ND.

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Important Clues that Facilitate Visual Emergence: Three Psychological Experiments

arXiv

引用

arXiv 2023年

作者： Li, Jingmeng Wei, Hui Laboratory of Algorithms for Cognitive Models School of Computer Science Fudan University Shanghai China

Visual emergence is the phenomenon in which the visual system obtains a holistic perception after grouping and reorganizing local signals. The picture Dalmatian dog is known for its use in explaining visual emergence. This type of image, which consists of a set of discrete black speckles (speckles), is called an emerging image. Not everyone can find the dog in Dalmatian dog, and among those who can, the time spent varies greatly. Although Gestalt theory summarizes perceptual organization into several principles, it remains ambiguous how these principles affect the perception of emerging images. This study, therefore, designed three psychological experiments to explore the factors that influence the perception of emerging images. In the first, we found that the density of speckles in the local area and the arrangements of some key speckles played a key role in the perception of an emerging case. We set parameters in the algorithm to characterize these two factors. We then automatically generated diversified emerging-test images (ETIs) through the algorithm and verified their effectiveness in two subsequent experiments. © 2023, CC BY-NC-ND.

关键词： Speckle

来源：评论

学校读者我要写书评

暂无评论

A neural dynamic model based on activation diffusion and a micro-explanation for cognitive operations

arXiv

引用

arXiv 2020年

作者： Wei, Hui Department of Computer Science Laboratory of Algorithms for Cognitive Models Fudan University Shanghai200433 China

The neural mechanism of memory has a very close relation with the problem of representation in artificial intelligence. In this paper a computational model was proposed to simulate the network of neurons in brain and how they process information. The model refers to morphological and electrophysiological characteristics of neural information processing, and is based on the assumption that neurons encode their firing sequence. The network structure, functions for neural encoding at different stages, the representation of stimuli in memory, and an algorithm to form a memory were presented. It also analyzed the stability and recall rate for learning and the capacity of memory. Because neural dynamic processes, one succeeding another, achieve a neuron-level and coherent form by which information is represented and processed, it may facilitate examination of various branches of Artificial Intelligence (AI), such as inference, problem solving, pattern recognition, natural language processing and learning. The processes of cognitive manipulation occurring in intelligent behavior have a consistent representation while all being modeled from the perspective of computational neuroscience. Thus, the dynamics of neurons make it possible to explain the inner mechanisms of different intelligent behaviors by a unified model of cognitive architecture at a micro-level. © 2020, CC BY-NC-ND.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Stereo Matching Algorithm for Improved Acquisition of Disparity Of Tiny Objects 14

Stereo Matching Algorithm for Improved Acquisition of Dispar...

引用

14th International Conference on Information Technology in Medicine and Education, ITME 2024

作者： Meng, Lingjiang Wei, Hui Wang, Haoming Zhang, Qing Li, Guangrong Nanning Vocational and Technical University School of Artifical Intellgence Nanning530000 China Shanghai Key Laboratory of Data Science Fudan University Laboratory of Algorithms for Cognitive Models Shanghai200000 China Harbin Institute of Technology School of Mechatronics Engineering Harbin150000 China

ISBN: (纸本)9798350356670

Deep-learning algorithms have an excellent nonlinear fitting ability. However, tiny objects in images do not approach the general properties of the fit, which causes the algorithms to have problems acquiring disparity for tiny objects. In addition, the results suffer from problems such as disparity inflation and warping variation. To address the shortcomings of deep learning algorithms, we propose an improved deep learning algorithm based on traditional algorithms. First, the algorithm divides the image into segments based on edges. Second, the edge error disparity and disparity expansion is corrected. Third, it finds the wrong disparity in a small segment, and removes it. The adjacent pixels with disparity removed are grouped into clusters. The matching relationship is established by combining the cluster's gray, gradient, and feature-point information into matching elements. Finally, removal of disparity warping variation and post-processing is performed. The algorithm can effectively correct error disparity, detect the disparity of tiny objects, and can be applied to practical scenarios where tiny objects are detected. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

On Adequate and Constructive models of Processing of Meanings

On Adequate and Constructive Models of Processing of Meaning...

引用

International Conference on Computer Science and Information Technologies

作者： Edward Pogossian Cognitive Algorithms and Models Laboratory of the Institute for Informatics and Automation Problems of NAS RA State Engineering University of Armenia

ISBN: (纸本)9781479924622

Humans promote themselves in the universe, the totality of their realities, while by processing of meanings they enhance the effectiveness and efficiency of the promotion. Humans communicate by explanation and acquisition of meanings, while acquire meanings by their understanding and learning. In paper we provide language explanations of meanings on some realities tended to specifications of constructive and adequate models of meaning processing. We discuss constrains on meanings induced by the models and corresponding constrains on cognition of realities as well as provide experimental evidence supporting a viability of the models.

关键词： Cognition Meanings Modeling Chess Explanations Understanding

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：