检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Zhao, Mengqiao Hochuli, Andre G. Cheddad, Abbas Faculty of Computing Blekinge Institute of Technology Karlskrona371 79 Sweden R. Imaculada Conceição 1155 Curitiba80215-901 Brazil

the plethora of digitalised historical document datasets released in recent years has rekindled interest in advancing the field of handwriting pattern recognition. In the same vein, a recently published data set, known as ARDIS, presents handwritten digits manually cropped from 15.000 scanned documents of Swedish church books and exhibiting various handwriting styles. To this end, we propose an end-to-end segmentation- free deep learning approach to handle this challenging ancient handwriting style of dates present in the ARDIS dataset (4-digits long strings). We show that with slight modifications in the VGG-16 deep model, the framework can achieve a recognition rate of 93.2%, resulting in a feasible solution free of heuristic methods, segmentation, and fusion methods. Moreover, the proposed approach outperforms the well-known CRNN method (a model widely applied in handwriting recognition tasks).[Cite as: Mengqiao Zhao, Andre G. Hochuli and Abbas Cheddad, End-to-End Approach for recognition of Historical Digit Strings, to appear in the 16th international conference on Document Analysis and recognition (ICDAR 2021), LNCS, Springer, Lausanne, Switzerland.] © 2021, CC BY.

关键词： Heuristic methods

来源：评论

学校读者我要写书评

暂无评论

Visual Effects for Real Time Ocean Water Rendering

Visual Effects for Real Time Ocean Water Rendering

引用

IIAI international conference on Advanced Applied Informatics (IIAIAAI)

作者： Leonard D. Litvak Leonidas Deligiannidis School of Computing and Data Science Wentworth Institute of Technology Boston MA USA

ISBN: (纸本)9781665424219

It is complex to visually represent the surface of ocean water because it is comprised of a multitude of visual effects such as transparency, translucency, and subsurface scattering. We implemented a diverse set of real time rendering techniques by which we achieved a fast and realistic looking ocean simulation. though our combination of techniques, we are able to achieve realistic-looking ocean water while staying within the technical constraints of real-time rendering at 60 frames per second. To illustrate this, we created a GPU-accelerated rendered utilizing OpenGL containing an implementation of these techniques, combined, for the purpose of rendering ocean water. A full suite of systems was implemented for the ocean rendering engine, including waveform simulation, efficient projection of the ocean onto a perceived infinite grid, dynamic lighting, and all the associated rendering subsystems. through our combination of our selected techniques, we were able to create a realistic approximation of an infinite ocean surface rendered in only several milliseconds per frame.

关键词： Sea surface Surface waves Scattering Lighting Rendering (computer graphics) Visual effects Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Updating BCI paradigms: Why to design in terms of the user?

Updating BCI paradigms: Why to design in terms of the user?

引用

international IEEE/EMBS conference on Neural Engineering, CNE

作者： L. M. Alonso-Valerdi V. R. Mercado-García Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Monterrey N.L. México Univ. Rennes INSA IRISA Inria CNRS

Towards the adaptation of Brain-Computer Interfaces (BCIs) from the laboratories to real contexts, the challenge of providing an efficient interaction becomes more notorious. Current paradigms are adapted to a technical perspective which suffices only a fraction of requirements to control a computational application with neural activity. For example, human aspects have been usually considered a secondary factor in non-invasive BCI research community, what has resulted in a poor user adaptation process and a system underperformance. this phenomenon has been named as “BCI-Illiteracy”. this concept is questioned since its inclusion in literature may have led to a strong bias in the outcome interpretation, pointing towards the user underperformance rather than the system inefficiency. this paper explores alternative designs proposed in terms of system architecture, experimental procedures and user-centered design as key factors to update current BCI paradigms towards a balance between user needs, and current technology. Several cues, results and findings proposed in recent research are presented as options to be considered for the design of new interactive paradigms, which could lead to an efficient application, and thus matching the expectations currently surrounding BCI systems.

关键词： Feature detection User centered design Neural activity Laboratories Systems architecture Psychology pattern classification

来源：评论

学校读者我要写书评

暂无评论

Extraction of main elements from a TEM composite laser pattern 10

Extraction of main elements from a TEM composite laser patte...

引用

10th international Congress of Physics Engineering, CIIF 2020

作者： Zúiga, V Torres Velázquez Aguilar, V.M. Bauelos Mueton, J.G. Licenciatura en Ciencia Forense Facultad de Medicina Universidad Nacional Autónoma de México Circuito de la Investigación Científica Ciudad Universitaria s/n Coyoacán Ciudad de México04360 Mexico Facultad de Ciencias Universidad Nacional Autónoma de México Circuito Interior Ciudad Universitaria Ciudad de México04360 Mexico Instituto de Ciencias Aplicadas y Tecnologiá Universidad Nacional Autónoma de México Circuito de la Investigación Científica Ciudad Universitaria S/n Coyoacán Ciudad de México04360 Mexico

We examined the atypical formation and superposition of transverse electromagnetic modes (TEM) of high order in a commercial He-Ne laser (@543.5 nm). the competence of the dominant modes exhibits a periodic and stable dynamic, uncommon in industrialized systems. Also, the intensity shows a smooth transition. the origin of the phenomenon is only a product of intra-cavity diffractive components. We found the promotors are a stable optical cavity but quasi-degenerated, with large transversal section (the Fresnel number is irregular), and a breaking the axial symmetry (producing astigmatism). the analysis of the average intensity patterns, and a correlation algorithm-via bi-orthogonal decomposition based on Hermite-Gauss polynomials-expose the five principal TEM elements. these results could be meaningful and inspiring both in courses of optics, laser engineering as in image processing. © Published under licence by IOP Publishing Ltd.

关键词： Polynomials

来源：评论

学校读者我要写书评

暂无评论

Converting Java Source Code for Programming Education Support Tool pgtracer

Converting Java Source Code for Programming Education Suppor...

引用

IIAI international conference on Advanced Applied Informatics (IIAIAAI)

作者： Masateru Kishikawa Tetsuro Kakeshita Computing Division Saga University Saga Japan

ISBN: (纸本)9781665424219

We have proposed a programming education support tool pgtracer for effective programming education. Pgtracer utilizes source codes and trace tables that represent execution results of the source code and creates programming exercises by defining blanks in some of them. the difficulty level of the exercises can be freely adjusted since the fill-in-the-blanks in the programs and trace tables can be defined freely. Furthermore, we can realize learning analytics by collecting the data of students' response process. In this paper, we extend pgtracer to incorporate Java for the effective education of object-oriented programming. We convert Java programs into an XML format that can be processed by pgtracer to effectively teach object-oriented programming using Java. By expressing the source code in XML format, it becomes possible to create flexible fill-in-the-blank questions. For this purpose, we utilize JavaCC to create an XML generator, which implements a program for each syntactic rule of the Java grammar to convert the source code into the specified XML format. the XML generator is implemented by combining these programs.

关键词： Java Codes Education XML Syntactics Generators Grammar

来源：评论

学校读者我要写书评

暂无评论

Joint Face Alignment and 3D Face Reconstruction with Efficient Convolution Neural Networks

Joint Face Alignment and 3D Face Reconstruction with Efficie...

引用

international conference on pattern recognition

作者： Keqiang Li Huaiyu Wu Xiuqin Shang Zhen Shen Gang Xiong Xisong Dong Bin Hu Fei-Yue Wang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing China The Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Dongguan China

3D face reconstruction from a single 2D facial image is a challenging and concerned problem. Recent methods based on CNN typically aim to learn parameters of 3D Morphable Model (3DMM) from 2D images to render face alignment and 3D face reconstruction. Most algorithms are designed for faces with small, medium yaw angles, which is extremely challenging to align faces in large poses. At the same time, they are not efficient usually. the main challenge is that it takes time to determine the parameters accurately. In order to address this challenge with the goal of improving performance, this paper proposes a novel and efficient end-to-end framework. We design an efficient and lightweight network model combined with Depthwise Separable Convolution and Muti-scale Representation, Lightweight Attention Mechanism, named Mobile-FRNet. Simultaneously, different loss functions are used to constrain and optimize 3DMM parameters and 3D vertices during training to improve the performance of the network. Meanwhile, extensive experiments on the challenging datasets show that our method significantly improves the accuracy of face alignment and 3D face reconstruction. Model parameters and complexity of our method are also improved greatly.

关键词： Training Solid modeling three-dimensional displays Convolution Face recognition Neural networks Complexity theory

来源：评论

学校读者我要写书评

暂无评论

LiDAR system benchmarking for VRU detection in heavy goods vehicle blind spots

LiDAR system benchmarking for VRU detection in heavy goods v...

引用

IEEE international conference on Intelligent Computer Communication and Processing (ICCP)

作者： Topi Miekkala Pasi Pyykönen Matti Kutila Arto Kyytinen VTT Technical Research Center of Finland Ltd. Tampere Finland TTS Kehitys Ltd. Finland

ISBN: (纸本)9781665409773

this article is related to using modern LiDARs and neural networks based algorithms for vulnerable road users (VRU) detection. the problem is obvious especially when considering blind spots of heavy goods vehicles. LiDARs have developed a lot recently and the results indicate that adults can be detected up-to 75 m distance from the sensor even thought that pattern recognition requires sufficient point cloud-resolution. Two different LiDAR brands have been compared to understand costbenefits between LiDAR technologies. the results have been conducted using an automated passenger car while considering feasibility to big trucks. Due to automotive requirements, the processing rate is also considered since usually, the main bottleneck is computation power, which is limited in automotive products. the used neural network algorithm is Yolo based and has been designed for VRU detection.

关键词： Cloud computing Laser radar three-dimensional displays Roads conferences Neural networks Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

引用

international conference on Information Science and Technology (ICIST)

作者： Zhongqing Wang Yan Yang Yingli Zhong School of Computer Science Technology Heilongjiang University Harbin China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

Graph similarity search is an important research problem in many applications, such as finding result graphs that have a similar structure to a given entity in biochemistry, data mining, and pattern recognition. Top-k graph similarity search is one of graph similarity search tasks, which aims to find the top-k graphs that are most similar to the query graph in a given graph database. In this paper, the top-k similarity search problem based on the graph edit distance is studied according to the corollary of the partitioned similarity theorem. Firstly, in order to speed up the online search process and avoid scanning each graph in the database one by one, an offline hierarchical inverted index is constructed to satisfy top-k search. Secondly, the offline hierarchical inverted index is used to filter the candidate graphs online and verify them, which reduces the time of searching the graphs. Finally, the good performance of the algorithm in running time and scalability is verified by running the similarity algorithm on real dataset and synthetic dataset.

关键词： Information science Databases Scalability Filtering algorithms Search problems Partitioning algorithms Indexes

来源：评论

学校读者我要写书评

暂无评论

Opposition-based Grey Wolf Optimization Approaches for Feature Selection

Opposition-based Grey Wolf Optimization Approaches for Featu...

引用

international conference on Intelligent System and Knowledge Engineering, ISKE

作者： Zhi Cao Hongmei Chen School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu China

ISBN: (纸本)9781665405546

Feature selection is an approach to select the important and key feature subset from a large number of redundant features, which can effectively reduce the computational cost and storage cost in the data processing process. therefore, feature selection is widely used in data mining and pattern recognition. the grey Wolf optimization algorithm can solve the problem of feature selection by simulating the predation behavior of gray wolves to obtain the optimal feature subset step by step. In this paper, we propose an opposition based learning grey Wolf optimization algorithm(OGWO), which uses opposition-based learning to initialize and update the population to improve the exploration ability of the population. In order to avoid the local optimum, a nonlinear parameter adjustment strategy is used to update the important parameters of the grey Wolf optimization algorithm. Experiments on 12 datasets demonstrate the effectiveness of the proposed method. Experimental results show that OGWO has better classification performance compared with other swarm intelligence algorithms.

关键词： Knowledge engineering Sociology Packaging Feature extraction Data processing Classification algorithms Statistics

来源：评论

学校读者我要写书评

暂无评论

Gas Discrimination & Quantification using Sensor Array with 3D Convolution Regression Dual Network

Gas Discrimination & Quantification using Sensor Array with ...

引用

IEEE international Workshop on Intelligent Data Acquisition and Advanced computing Systems: Technology and Applications

作者： Vishakha Pareek Santanu Chaudhury Sanjay Singh CSIR - Central Electronics Engineering Research Institute Pilani India Academy of Scientific and Innovative Research (AcSIR) Ghaziabad India Indian Institute of Technology Delhi India

ISBN: (纸本)9781665426060

Smart sensor system design requires intelligent data processing, which analyzes raw time-series sensor data to efficiently and precisely discriminate and quantify target gases. the work presented here utilizes the response of twin gas sensor arrays for gases such as ethanol, ethylene, methane, and carbon monoxide to discriminate and quantify the target gases. We propose a 3D convolution neural-based regression dual network (3D-CNRDN) for both gas quantification and discrimination. the spatiotemporal correlation of sensor array responses inspired us to design the deep neural network for the gas concentration estimation model. the sensor array set is spatially correlated, and all the twin array responses are temporally related. 3D-CNRDN uses raw time-series gas sensor array data. the data is fed to the network as the 3D pattern, which contains 2D spatial information varying with third dimension time to recognize patterns that eventually predict the concentration. the model evaluation shows that the proposed methods are an effective technique for gas quantification and identification with $\text{RMSE}=0.3179$ and classification accuracy 94.37%. Furthermore, the proposed method outperforms and provides higher discrimination accuracy and lower RMSE than other machine learning and deep learning methods.

关键词： Deep learning Gases three-dimensional displays Convolution Neural networks Spatiotemporal phenomena 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：