检索结果-内蒙古大学图书馆

A Developmental Neuro-Robotics Approach for Boosting the recognition of Handwritten Digits

A Developmental Neuro-Robotics Approach for Boosting the Rec...

International Joint Conference on Neural Networks (IJCNN) held as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

作者： Di Nuovo, Alessandro Sheffield Hallam Univ Sheffield Robot Dept Comp Sheffield S1 1WB S Yorkshire England

ISBN: (纸本)9781728169262

Developmental psychology and neuroimaging research identified a close link between numbers and fingers, which can boost the initial number knowledge in children. Recent evidence shows that a simulation of the children's embodied strategies can improve the machine intelligence too. This article explores the application of embodied strategies to convolutional neural network models in the context of developmental neurorobotics, where the training information is likely to be gradually acquired while operating rather than being abundant and fully available as the classical machine learning scenarios. The experimental analyses show that the proprioceptive information from the robot fingers can improve network accuracy in the recognition of handwritten Arabic digits when training examples and epochs are few. This result is comparable to brain imaging and longitudinal studies with young children. In conclusion, these findings also support the relevance of the embodiment in the case of artificial agents' training and show a possible way for the humanization of the learning process, where the robotic body can express the internal processes of artificial intelligence making it more understandable for humans.

关键词： Neurorobotics Cognitive Science computer vision and pattern recognition Machine Intelligence Number Cognition

来源：评论

学校读者我要写书评

暂无评论

BIOLOGICALLY INSPIRED HEXAGONAL DEEP LEARNING FOR HEXAGONAL IMAGE GENERATION

BIOLOGICALLY INSPIRED HEXAGONAL DEEP LEARNING FOR HEXAGONAL ...

引用

IEEE International Conference on Image Processing (ICIP)

作者： Schlosser, Tobias Beuth, Frederik Kowerko, Danny Tech Univ Chemnitz Media Comp D-09107 Chemnitz Germany

ISBN: (纸本)9781728163956

Whereas conventional state-of-the-art image processing systems of recording and output devices almost exclusively utilize square arranged methods, biological models, however, suggest an alternative, evolutionarily-based structure. Inspired by the human visual perception system, hexagonal image processing in the context of machine learning offers a number of key advantages that can benefit both researchers and users alike. The hexagonal deep learning framework Hexnet leveraged in this contribution serves therefore the generation of hexagonal images by utilizing hexagonal deep neural networks (H-DNN). As the results of our created test environment show, the proposed models can surpass current approaches of conventional image generation. While resulting in a reduction of the models' complexity in the form of trainable parameters, they furthermore allow an increase of test rates in comparison to their square counterparts.

关键词： computer vision and pattern recognition Deep Learning Convolutional Neural Networks Hexagonal Image Processing Hexagonal Lattice Hexagonal Sampling Image Generation

来源：评论

学校读者我要写书评

暂无评论

Translating Visual Art into Music 17

Translating Visual Art into Music

引用

IEEE/CVF International Conference on computer vision (ICCV)

作者： Mueller-Eberstein, Maximilian van Noord, Nanne Univ Amsterdam Amsterdam Netherlands

ISBN: (纸本)9781728150239

The Synesthetic Variational Autoencoder (SynVAE) introduced in this research is able to learn a consistent mapping between visual and auditive sensory modalities in the absence of paired datasets. A quantitative evaluation on MNIST as well as the Behance Artistic Media dataset (BAM) shows that SynVAE is capable of retaining sufficient information content during the translation while maintaining cross-modal latent space consistency. In a qualitative evaluation trial, human evaluators were furthermore able to match musical samples with the images which generated them with accuracies of up to 73%.

关键词： Art Audio processing computer vision and pattern recognition Cross modal translation Human computer interaction Machine learning Multimedia

来源：评论

学校读者我要写书评

暂无评论

Visual Search and recognition for Robot Task Execution and Monitoring 1

Visual Search and Recognition for Robot Task Execution and M...

引用

1st International Conference on Applications of Intelligent Systems (APPIS)

作者： Mauro, Lorenzo Puja, Francesco Grazioso, Simone Ntouskos, Valsamis Sanzari, Marta Alati, Edoardo Freda, Luigi Pirri, Fiora Sapienza Univ Rome ALCOR Lab DIAG Rome Italy

ISBN: (纸本)9781614999294;9781614999287

Visual search of relevant targets in the environment is a crucial robot skill. We propose a preliminary framework for the execution monitor of a robot task, taking care of the robot attitude to visually searching the environment for targets involved in the task. Visual search is also relevant to recover from a failure. The framework exploits deep reinforcement learning to acquire a common sense scene structure and it takes advantage of a deep convolutional network to detect objects and relevant relations holding between them. The framework builds on these methods to introduce a vision-based execution monitoring, which uses classical planning as a backbone for task execution. Experiments show that with the proposed vision-based execution monitor the robot can complete simple tasks and can recover from failures in autonomy.

关键词： Artificial Intelligence computer vision and pattern recognition Robotics

来源：评论

学校读者我要写书评

暂无评论

Cooperative and Graph Signal Processing: Principles and Applications

引用

2018年

作者： Petar M Djurić Cdric Richard

ISBN: (数字)9780128136782

ISBN: (纸本)9780128136775

Cooperative and Graph Signal Processing: Principles and Applications presents the fundamentals of signal processing over networks and the latest advances in graph signal processing. A range of key concepts are clearly explained, including learning, adaptation, optimization, control, inference and machine learning. Building on the principles of these areas, the book then shows how they are relevant to understanding distributed communication, networking and sensing and social networks. Finally, the book shows how the principles are applied to a range of applications, such as Big data, Media and video, Smart grids, Internet of Things, Wireless health and Neuroscience. With this book readers will learn the basics of adaptation and learning in networks, the essentials of detection, estimation and filtering, Bayesian inference in networks, optimization and control, machine learning, signal processing on graphs, signal processing for distributed communication, social networks from the perspective of flow of information, and how to apply signal processing methods in distributed settings. Presents the first book on cooperative signal processing and graph signal processing Provides a range of applications and application areas that are thoroughly coveredIncludes an editor in chief and associate editor from the IEEE Transactions on Signal Processing and Information Processing over Networks who have recruited top contributors for the book

关键词： computer vision and pattern recognition machine vision

来源：评论

学校读者我要写书评

暂无评论

The recognition of traffic speed limit sign in hazy weather

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2017年第2期33卷 873-883页

作者： Yan, Gang Yu, Ming Shi, Shuo Feng, Chao Hebei Univ Technol Sch Elect & Informat Engn Tianjin Peoples R China Hebei Univ Technol Sch Comp Sci & Engn Tianjin Peoples R China North Informat Control Grp Co Ltd Nanjing Jiangsu Peoples R China

Hazy weather affects drivers' sightline seriously and causes a high potential safety hazard. This paper proposes a novel approach for recognizing the speed limit sign in hazy weather. It consists of three major modules: haze removal, speed limit sign location, and sign recognition. In haze removal, this paper proposes to dehaze image with the dark channel prior. The speed limit sign is located by Histogram of Oriented Gradient (HOG) feature extraction and Support Vector Machine (SVM) classification and is recognized by the seven layers Convolutional Neural Networks (CNN). Experimental results show that the proposed method has better performance than the state-of-art dehazing methods and the processing time is also reduced. The recognition rate of the speed limit signs is 98.51% that is better than the human performance, and the classifier can recognize the speed limit sign with rotation, shift, scale and other distortions.

关键词： computer vision and pattern recognition speed limit sign haze removal dark channel prior HOG CNN

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Drug Sensitivity 1st Edition

引用

2016年

作者： Pal, Ranadip

ISBN: (数字)9780128054314

ISBN: (纸本)9780128052747

Predictive Modeling of Drug Sensitivity gives an overview of drug sensitivity modeling for personalized medicine that includes data characterizations, modeling techniques, applications, and research challenges. It covers the major mathematical techniques used for modeling drug sensitivity, and includes the requisite biological knowledge to guide a user to apply the mathematical tools in different biological scenarios. This book is an ideal reference for computer scientists, engineers, computational biologists, and mathematicians who want to understand and apply multiple approaches and methods to drug sensitivity modeling. The reader will learn a broad range of mathematical and computational techniques applied to the modeling of drug sensitivity, biological concepts, and measurement techniques crucial to drug sensitivity modeling, how to design a combination of drugs under different constraints, and the applications of drug sensitivity prediction *** mathematical and computational approaches to biological problemsCovers all aspects of drug sensitivity modeling, starting from initial data generation to final experimental validationIncludes the latest results on drug sensitivity modeling that is based on updated research findingsProvides information on existing data and software resources for applying the mathematical and computational tools available

关键词： Computational Biology computer vision and pattern recognition

来源：评论

学校读者我要写书评

暂无评论

14th International Machine vision and Image Processing Conference: IMVIP 2010

引用

2011年

作者： Martin J Leahy Marie Louise O'Connell

ISBN: (数字)9781527550766

ISBN: (纸本)9781443829625

Established in 1997, the International Machine vision and Image Processing (IMVIP) conferences bring together theoreticians, practitioners, industrialists and academics, from the numerous related disciplines involved in the processing and analysis of image-based information. These events provide a platform for communication and exchange between participants whereby cutting edge research and advances within the field can be communicated, discussed and information *** events are hosted annually by different universities on the island of Ireland. These proceedings reflect the manuscripts selected for oral presentation at the 14th instalment of the series hosted by the University of Limerick, Ireland in 2010 in association with the Irish pattern recognition and Classification Society (IPRCS), a member organisation of the International Association of Patten recognition (IAPR).

关键词： Graphics, CAD, HCI Sociology computer vision and pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Digital Geometry: Geometric Methods for Digital Picture Analysis 1

引用

丛书名： The Morgan Kaufmann Series in computer Graphics

2004年

作者： Klette, Reinhard Rosenfeld, Azriel

ISBN: (数字)9780080477268

ISBN: (纸本)9781558608610

Digital geometry is about deriving geometric information from digital pictures. The field emerged from its mathematical roots some forty-years ago through work in computer-based imaging, and it is used today in many fields, such as digital image processing and analysis (with applications in medical imaging, pattern recognition, and robotics) and of course computer graphics. Digital Geometry is the first book to detail the concepts, algorithms, and practices of the discipline. This comphrehensive text and reference provides an introduction to the mathematical foundations of digital geometry, some of which date back to ancient times, and also discusses the key processes involved, such as geometric algorithms as well as operations on pictures.*A comprehensive text and reference written by pioneers in digital geometry, image processing and analysis, and computer vision*Provides a collection of state-of-the-art algorithms for a wide variety of geometrical picture analysis tasks, including extracting data from digital images and making geometric measurements on the data*Includes exercises, examples, and references to related or more advanced work

关键词： computer vision and pattern recognition computer graphics applied mathematics

来源：评论

学校读者我要写书评

暂无评论

A new approach to object-related image retrieval

引用

JOURNAL OF VISUAL LANGUAGES AND COMPUTING 2000年第3期11卷 345-363页

作者： Martínez, AM Serra, AR Sch Elect & Comp Engn Robot Vis Lab W Lafayette IN 47906 USA Sony Comp Sci Lab F-75005 Paris France SOC Comp Palma de Mallorca 07002 Balears Spain

Image retrieval has been commonly attempted using non-semantic approaches. It is clear though, that semantic retrieval is more desirable because it facilitates the user's task. In this paper, we present a new approach to semantic access of a database of images by asking for the presence of certain objects;this is known as object-related image retrieval. This approach is built within a classical computer vision framework (i.e. localization, segmentation and identification). Our approach first searches for the main areas of attention (most salient areas of an image) and then applies appearance-based methods to classify (index) all images by 'symbolic' names. These names are referred to objects, which finally allows the use of semantics driven by these object names, e.g. retrieve 'all those images that have a bull and Melissa's face'. The use of a totally automatic system would cause some errors of indexing (and so retrieval). To solve this we use a human-in-the-loop strategy where a human expert is placed after the two outputs of the system to confirm. their 'correctness'. An experimental result using a database of 3000 images is presented. (C) 2000 Academic Press

关键词： multimedia databases indexing and image retrieval semantic access to databases computer vision and pattern recognition

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：