检索结果-南通市图书馆

Multi-Stage-Based Siamese Neural Network for Seal Image Recognition

Computer Modeling in Engineering & Sciences 2025年第1期142卷 405-423页

作者： Jianfeng Lu Xiangye Huang Caijin Li Renlin Xin Shanqing Zhang Mahmoud Emam School of Computer Science and Technology Hangzhou Dianzi UniversityHangzhou310018China Shangyu institute of Science and Engineering Hangzhou Dianzi UniversityShaoxing312300China Faculty of Artificial intelligence Menoufia UniversityShebin El-Koom32511Egypt

Seal authentication is an important task for verifying the authenticity of stamped seals used in various domains to protect legal documents from tampering and *** seal inspection is commonly audited manually to ensure document ***,manual assessment of seal images is tedious and laborintensive due to human errors,inconsistent placement,and completeness of the *** image recognition systems are inadequate enough to identify seal types accurately,necessitating a neural network-based method for seal image ***,neural network-based classification algorithms,such as Residual Networks(ResNet)andVisualGeometryGroup with 16 layers(VGG16)yield suboptimal recognition rates on stamp ***,the fixed training data categories make handling new categories to be a challenging *** paper proposes amulti-stage seal recognition algorithmbased on Siamese network to overcome these ***,the seal image is pre-processed by applying an image rotation correction module based on Histogram of Oriented Gradients(HOG).Secondly,the similarity between input seal image pairs is measured by utilizing a similarity comparison module based on the Siamese ***,we compare the results with the pre-stored standard seal template images in the database to obtain the seal *** evaluate the performance of the proposed method,we further create a new seal image dataset that contains two subsets with 210,000 valid labeled pairs in *** proposed work has a practical significance in industries where automatic seal authentication is essential as in legal,financial,and governmental sectors,where automatic seal recognition can enhance document security and streamline validation ***,the experimental results show that the proposed multi-stage method for seal image recognition outperforms state-of-the-art methods on the two established datasets.

关键词： Seal recognition seal authentication document tampering siamese network spatial transformer network similarity comparison network

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Toward understanding the role of genomic repeat elements in neurodegenerative diseases

引用

Neural Regeneration Research 2025年第3期20卷 646-659页

作者： Zhengyu An Aidi Jiang Jingqi Chen institute of Science and Technology for Brain-Inspired intelligence Fudan UniversityShanghaiChina MOE Frontiers Center for Brain Science Fudan UniversityShanghaiChina MOE Key Laboratory of Computational Neuroscience and Brain-Inspired intelligence Fudan UniversityShanghaiChina Zhangjiang Fudan International Innovation Center ShanghaiChina

Neurodegenerative diseases cause great medical and economic burdens for both patients and society;however, the complex molecular mechanisms thereof are not yet well understood. With the development of high-coverage sequencing technology, researchers have started to notice that genomic repeat regions, previously neglected in search of disease culprits, are active contributors to multiple neurodegenerative diseases. In this review, we describe the association between repeat element variants and multiple degenerative diseases through genome-wide association studies and targeted sequencing. We discuss the identification of disease-relevant repeat element variants, further powered by the advancement of long-read sequencing technologies and their related tools, and summarize recent findings in the molecular mechanisms of repeat element variants in brain degeneration, such as those causing transcriptional silencing or RNA-mediated gain of toxic function. Furthermore, we describe how in silico predictions using innovative computational models, such as deep learning language models, could enhance and accelerate our understanding of the functional impact of repeat element variants. Finally, we discuss future directions to advance current findings for a better understanding of neurodegenerative diseases and the clinical applications of genomic repeat elements.

关键词： Alzheimer's disease ataxia deep learning long-read sequencing neurodegeneration neurodegenerative diseases Parkinson's disease repeat element structural variant

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Improving performance of robots using human-inspired approaches: a survey

引用

Science China(Information Sciences) 2022年第12期65卷 5-35页

作者： Hong QIAO Shanlin ZHONG Ziyu CHEN Hongze WANG State Key Laboratory of Management and Control for Complex System Institute of Automation Chinese Academy of Sciences School of artifcial intelligence University of Chinese Academy of Sciences CAS Center for Excellence in Brain Science and intelligence Technology

Realizing high performance of ordinary robots is one of the core problems in robotic research. Improving the performance of ordinary robots usually relies on the collaborative development of multiple research fields, resulting in high costs and difficulty to complete some high-precision tasks. As a comparison,humans can realize extraordinary overall performance under the condition of limited computational-energy consumption and low absolute precision in sensing and controlling each body unit. Therefore, developing human-inspired robotic systems and algorithms is a promising avenue to improve the performance of robotic systems. In this review, the cutting-edge research work on human-inspired intelligent robots in decisionmaking, cognition, motion control, and system design is summarized from behavior-and neural-inspired aspects. This review aims to provide a significant insight into human-inspired intelligent robots, which may be beneficial for promoting the integration of neuroscience, machinery, and control, so as to develop a new generation of robotic systems.

关键词： human-inspired intelligent robots brain-inspired intelligence decision making visual cognition musculoskeletal robots

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

FairCF: fairness-aware collaborative filtering

引用

Science China(Information Sciences) 2022年第12期65卷 127-141页

作者： Pengyang SHAO Le WU Lei CHEN Kun ZHANG Meng WANG School of Computer Science and Information Engineering Hefei University of Technology Intelligent Interconnected Systems Laboratory of Anhui Province institute of artifcial intelligence Hefei Comprehensive National Science Center

Collaborative filtering(CF) techniques learn user and item embeddings from user-item interaction behaviors, and are commonly used in recommendation systems to help users find potentially desirable items. Most CF models optimize recommendation accuracy; however, they may lead to unwanted biases for particular demographic groups. Thus, we focus on learning fair representations of CF-based recommendations. We formulate this problem as an optimization task with two competing goals: embedding representations better meet accuracy requirements of recommendations, and simultaneously obfuscate information hidden in the embedding space, which is related to the users’ sensitive attributes for fairness. Here,the intuitive idea is to use fair representation learning from machine learning to train a classifier with a sensitive attribute predictor from the user side to satisfy the fairness goal. However, such fair machine learning models assume entity independence, which differs greatly from CF because users and items are correlated collaboratively via user-item behaviors. Therefore, sensitive user information can be exposed from the users’ preferred items. Consequently, defining only fairness constraints on users cannot achieve fairness in recommendation systems. In this paper, we propose FairCF framework for fairness-aware collaborative *** particular, we first define fairness constraints in a fair embedding space, where both a user classifier and an item classifier are employed to fit the fairness constraints. We then design an item classifier without item sensitive labels. The proposed framework can be trained in an end-to-end manner under most embedding based CF models. Extensive experiments conducted on three datasets(Movie Lens-100K, Movie Lens-1M,and Lastfm-360K) clearly demonstrate the superiority of the proposed FairCF framework relative to various fairness metrics(i.e., performance of newly-trained classifiers) than other state-of-the-art fairness-aware CF mode

关键词： recommendation systems fairness adversarial learning

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Resting-state brain network remodeling after different nerve reconstruction surgeries:a functional magnetic resonance imaging study in brachial plexus injury rats

引用

Neural Regeneration Research 2025年第5期20卷 1495-1504页

作者： Yunting Xiang Xiangxin Xing Xuyun Hua Yuwen Zhang Xin Xue Jiajia Wu Mouxiong Zheng He Wang Jianguang Xu School of Rehabilitation Science Shanghai University of Traditional Chinese MedicineShanghaiChina Engineering Research Center of Traditional Chinese Medicine Intelligent Rehabilitation Ministry of EducationShanghaiChina Department of Rehabilitation Medicine Yueyang Hospital of Integrated Traditional Chinese and Western MedicineShanghai University of Traditional Chinese MedicineShanghaiChina Department of Traumatology and Orthopedics Yueyang Hospital of Integrated Traditional Chinese and Western MedicineShanghai University of Traditional Chinese MedicineShanghaiChina institute of Science and Technology for Brain-Inspired intelligence Fudan UniversityShanghaiChina Key Laboratory of Computational Neuroscience and Brain-Inspired intelligence(Fudan University) Ministry of EducationShanghaiChina Human Phenome institute Fudan UniversityShanghaiChina

Distinct brain remodeling has been found after different nerve reconstruction strategies,including motor representation of the affected ***,differences among reconstruction strategies at the brain network level have not been *** study aimed to explore intranetwork changes related to altered peripheral neural pathways after different nerve reconstruction surgeries,including nerve repair,endto-end nerve transfer,and end-to-side nerve ***–Dawley rats underwent complete left brachial plexus transection and were divided into four equal groups of eight:no nerve repair,grafted nerve repair,phrenic nerve end-to-end transfer,and end-to-side transfer with a graft sutured to the anterior upper ***-state brain functional magnetic resonance imaging was obtained 7 months after *** independent component analysis algorithm was utilized to identify group-level network components of interest and extract resting-state functional connectivity values of each voxel within the *** in intra-network resting-state functional connectivity were compared among the *** muscle reinnervation was assessed by behavioral observation(elbow flexion)and *** results showed that alterations in the sensorimotor and interoception networks were mostly related to changes in the peripheral neural *** repair was related to enhanced connectivity within the sensorimotor network,while end-to-side nerve transfer might be more beneficial for restoring control over the affected limb by the original motor *** thalamic-cortical pathway was enhanced within the interoception network after nerve repair and end-to-end nerve *** areas related to cognition and emotion were enhanced after end-to-side nerve *** study revealed important brain networks related to different nerve *** networks may be potential targets for enhancing motor recovery.

关键词： brain functional networks end-to-end nerve transfer end-to-side nerve transfer independent component analysis nerve repair peripheral plexus injury resting-state functional connectivity

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Hierarchical Approximate Matching for Retrieval of Chinese Historical Calligraphy Character

引用

Journal of Computer Science & Technology 2007年第4期22卷 633-640页

作者：章夏芬庄越挺吴江琴吴飞 institute of Artificial intelligence Zhejiang University

As historical Chinese calligraphy works are being digitized, the problem of retrieval becomes a new challenge. But, currently no OCR technique can convert calligraphy character images into text, nor can the existing Handwriting Character Recognition approach does not work for it. This paper proposes a novel approach to efficiently retrieving Chinese calligraphy characters on the basis of similarity： calligraphy character image is represented by a collection of discriminative features, and high retrieval speed with reasonable effectiveness is achieved. First, calligraphy characters that have no possibility similar to the query are filtered out step by step by comparing the character complexity, stroke density and stroke protrusion. Then, similar calligraphy characters axe retrieved and ranked according to their matching cost produced by approximate shape match. In order to speed up the retrieval, we employed high dimensional data structure - PK-tree. Finally, the efficiency of the algorithm is demonstrated by a preliminary experiment with 3012 calligraphy character images.

关键词： Chinese calligraphy approximate matching character retrieval

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Image meshing via hierarchical optimization

引用

Frontiers of Information Technology & Electronic Engineering 2016年第1期17卷 32-40页

作者： Hao XIE Ruo-feng TONG institute of Artificial intelligence Zhejiang University

Vector graphic, as a kind of geometric representation of raster images, has many advantages, e.g.,definition independence and editing facility. A popular way to convert raster images into vector graphics is image meshing, the aim of which is to find a mesh to represent an image as faithfully as possible. For traditional meshing algorithms, the crux of the problem resides mainly in the high non-linearity and non-smoothness of the ob jective,which makes it difficult to find a desirable optimal solution. To ameliorate this situation, we present a hierarchical optimization algorithm solving the problem from coarser levels to finer ones, providing initialization for each level with its coarser ascent. To further simplify the problem, the original non-convex problem is converted to a linear least squares one, and thus becomes convex, which makes the problem much easier to solve. A dictionary learning framework is used to combine geometry and topology elegantly. Then an alternating scheme is employed to solve both parts. Experiments show that our algorithm runs fast and achieves better results than existing ones for most images.

关键词： Image meshing, Hierarchical optimization, Convexification

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Toward the third generation artificial intelligence

引用

Science China(Information Sciences) 2023年第2期66卷 5-23页

作者： Bo ZHANG Jun ZHU Hang SU institute for Artificial intelligence Tsinghua University

There have been two competing paradigms in artificial intelligence(AI) development ever since its birth in 1956, i.e., symbolism and connectionism(or sub-symbolism). While symbolism dominated AI research by the end of 1980s, connectionism gained momentum in the 1990s and is gradually displacing symbolism. This paper considers symbolism as the first generation of AI and connectionism as the second generation. However, each of these two paradigms simulates the human mind from only one *** cannot achieve true human behaviors by relying on only one paradigm. In order to develop novel AI technologies that are safe, reliable, and extensible, it is necessary to establish a new explainable and robust AI theory. To this end, this paper looks toward developing a third generation artificial intelligence by combining the current paradigms.

关键词： artificial intelligence symbolism connectionism dual-space model single-space model triple-space model

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

A novel spiking neural network of receptive field encoding with groups of neurons decision

引用

Frontiers of Information Technology & Electronic Engineering 2018年第1期19卷 139-150页

作者： Yong-qiang MA Zi-ru WANG Si-yu YU Ba-dong CHEN Nan-ning ZHENG Peng-ju REN institute of Artificial intelligence and Robotics Xi'an Jiaotong University

Human information processing depends mainly on billions of neurons which constitute a complex neural network,and the information is transmitted in the form of neural *** this paper,we propose a spiking neural network(SNN),named MD-SNN,with three key features:(1) using receptive field to encode spike trains from images;(2) randomly selecting partial spikes as inputs for each neuron to approach the absolute refractory period of the neuron;(3) using groups of neurons to make *** test MD-SNN on the MNIST data set of handwritten digits,and results demonstrate that:(1) Different sizes of receptive fields influence classification results significantly.(2) Considering the neuronal refractory period in the SNN model,increasing the number of neurons in the learning layer could greatly reduce the training time,effectively reduce the probability of over-fitting,and improve the accuracy by 8.77%.(3) Compared with other SNN methods,MD-SNN achieves a better classification;compared with the convolution neural network,MD-SNN maintains flip and rotation invariance(the accuracy can remain at 90.44% on the test set),and it is more suitable for small sample learning(the accuracy can reach 80.15%for 1000 training samples,which is 7.8 times that of CNN).

关键词： Tempotron Receptive field Difference of Gaussian(DoG) Flip invariance Rotation invariance

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Form Properties of Moving Targets Bias Smooth Pursuit Target Selection in Monkeys

引用

Neuroscience Bulletin 2023年第8期39卷 1246-1262页

作者： Huixi Dou Huan Wang Sainan Liu Jun Huang Zuxiang Liu Tiangang Zhou Yan Yang State Key Laboratory of Brain and Cognitive Science Institute of BiophysicsChinese Academy of SciencesBeijing 100101China institute of artifcial intelligence Hefei Comprehensive National Science CenterHefei 230088China Division of Life Sciences and Medicine University of Science and Technology of ChinaHefei 230026China University of Chinese Academy of Sciences Beijing 100049China

During natural viewing,we often recognize multiple objects,detect their motion,and select one object as the target to *** remains to be determined how such behavior is guided by the integration of visual form and motion *** address this,we studied how monkeys made a choice to track moving targets with different forms by smooth pursuit eye movements in a two-target *** found that pursuit responses were biased toward the motion direction of a target with a *** computing the relative weighting,we found that the target with a hole exhibited a larger weight for vector *** global hole feature dominated other form *** dominance failed to account for changes in pursuit responses to a target with different forms moving *** findings suggest that the integration of visual form and motion perception can reshape the competition in sensorimotor networks to guide behavioral selection.

关键词： Global hole feature Smooth pursuit eye movements Sensorimotor transformation Visual form perception Visual motion perception Monkeys

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：