检索结果-南通市图书馆

Synthesis,Style Editing,and Animation of 3D Cartoon Face

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第2期29卷 506-516页

作者： Ming Guo Feng Xu Shunfei Wang Zhibo Wang Ming Lu Xiufen Cui Xiao Ling School of Software and BNRist Tsinghua UniversityBeijing 100084China department of multimedia and Smart Guangdong OPPO Mobile Telecommunications Corp.Ltd.Dongguan 523860China Intel Labs IntelBeijing 100089China

As a popular kind of stylized face,cartoon faces have rich application *** is challenging to create personalized 3D cartoon faces directly from 2D real ***,in order to adapt to more application scenarios,automatic style editing,and animation of cartoon faces is also a crucial problem that is urgently needed to be solved in the industry,but has not yet had a perfect *** solve this problem,we first propose“3D face cartoonizer”,which can generate high-quality 3D cartoon faces with texture when fed into 2D facial *** contribute the first 3D cartoon face hybrid dataset and a new training strategy which first pretrains our network with low-quality triplets in a reconstruction-then-generation manner,and then finetunes it with high-quality triplets in an adversarial manner to fully leverage the hybrid ***,we implement style editing for 3D cartoon faces based on k-means,which can be easily achieved without retrain the neural *** addition,we propose a new cartoon faces'blendshape generation method,and based on this,realize the expression animation of 3D cartoon faces,enabling more practical *** dataset and code will be released for future research.

关键词： cartoon 3D face animation computer graphics

A Novel Insertion Solution for the Travelling Salesman Problem

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第4期79卷 1581-1597页

作者： Emmanuel Oluwatobi Asani Aderemi Elisha Okeyinka Sunday Adeola Ajagbe Ayodele Ariyo Adebiyi Roseline Oluwaseun Ogundokun Temitope Samson Adekunle Pragasen Mudali Matthew Olusegun Adigun department of Computer Science Landmark UniversityOmu Aran251103Nigeria SDG 11 Group Landmark UniversityOmu Aran251103Nigeria department of Computing MiVA UniversityAbuja900211Nigeria department of Computer Science Ibrahim Badamasi Babangida UniversityLapai911101Nigeria department of Computer Science University of ZululandKwadlangezwa3886South Africa department of Computer&Industrial Production Engineering First Technical UniversityIbadan200243Nigeria department of multimedia Engineering Kaunas University of TechnologyKaunasLT-44249Lithuania department of Computer Science Colorado State UniversityFort Collins80523USA

The studypresents theHalfMax InsertionHeuristic (HMIH) as a novel approach to solving theTravelling SalesmanProblem (TSP). The goal is to outperform existing techniques such as the Farthest Insertion Heuristic (FIH) andNearest Neighbour Heuristic (NNH). The paper discusses the limitations of current construction tour heuristics,focusing particularly on the significant margin of error in FIH. It then proposes HMIH as an alternative thatminimizes the increase in tour distance and includes more nodes. HMIH improves tour quality by starting withan initial tour consisting of a ‘minimum’ polygon and iteratively adding nodes using our novel Half Max *** paper thoroughly examines and compares HMIH with FIH and NNH via rigorous testing on standard TSPbenchmarks. The results indicate that HMIH consistently delivers superior performance, particularly with respectto tour cost and computational efficiency. HMIH’s tours were sometimes 16% shorter than those generated by FIHand NNH, showcasing its potential and value as a novel benchmark for TSP solutions. The study used statisticalmethods, including Friedman’s Non-parametric Test, to validate the performance of HMIH over FIH and *** guarantees that the identified advantages are statistically significant and consistent in various situations. Thiscomprehensive analysis emphasizes the reliability and efficiency of the heuristic, making a compelling case for itsuse in solving TSP issues. The research shows that, in general, HMIH fared better than FIH in all cases studied,except for a few instances (pr439, eil51, and eil101) where FIH either performed equally or slightly better thanHMIH. HMIH’s efficiency is shown by its improvements in error percentage (δ) and goodness values (g) comparedto FIH and NNH. In the att48 instance, HMIH had an error rate of 6.3%, whereas FIH had 14.6% and NNH had20.9%, indicating that HMIH was closer to the optimal solution. HMIH consistently showed superior performanceacross many benchmarks,

关键词： Nearest neighbour heuristic farthest insertion heuristic half max insertion heuristic tour construction travelling salesman problem

Deep Transfer Learning Models for mobile-Based Ocular Disorder Identification on Retinal Images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 139-161页

作者： Roseline Oluwaseun Ogundokun Joseph Bamidele Awotunde Hakeem Babalola Akande Cheng-Chi Lee Agbotiname Lucky Imoize department of multimedia Engineering Kaunas University of TechnologyKaunas44249Lithuania department of Computer Science Landmark UniversityOmu Aran251103Nigeria department of Computer Science Faculty of Information and Communication SciencesUniversity of IlorinIlorin240003Nigeria department of Telecommunication Science University of IlorinIlorin230003Nigeria department of Library and Information Science Fu Jen Catholic UniversityNew Taipei City24205Taiwan department of Computer Science and Information Engineering Fintech and Blockchain Research CenterAsia UniversityTaichung City41354Taiwan department of Electrical and Electronics Engineering Faculty of EngineeringUniversity of LagosAkokaLagos100213Nigeria department of Electrical Engineering and Information Technology Institute of Digital CommunicationRuhr UniversityBochum44801Germany

mobile technology is developing *** phone technologies have been integrated into the healthcare industry to help medical ***,computer vision models focus on image detection and classification ***2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to *** leads to increased *** biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational ***,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is *** pre-trainedCNN(PCNN)mobileNetV2 architecture combined with a SupportVectorMachine(SVM)compacts the model representation and reduces the computational cost and memory *** proposed novel approach combines quantized pre-trained CNN(PCNN)mobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and *** contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from mobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable *** model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class *** the experiment outcomes,it is observed that the suggested mobileNetV2-SVM model size is *** testing accuracy formobileNetV2-SVM,InceptionV3,andmobileNetV2 is 90.11%,86.88%,and 89

关键词： Retinal images ocular disorder deep transfer learning disease identification mobile device

Dynamic resource allocation schemes for eMBB and URLLC services in 5G wireless networks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Intelligent and Converged Networks 2022年第2期3卷 145-160页

作者： Xianghui Han Kai Xiao Ruiqi Liu Xing Liu George C.Alexandropoulos Shi Jin State Key Laboratory of mobile Network and mobile multimedia Technology Shenzhen 518055Chinaand also with the Wireless Research InstituteZTE CorporationBeijing 100029China National mobile Communications Research Laboratory Southeast UniversityNanjing 210096China department of Informatics and Telecommunications National and Kapodistrian University of AthensAthens 15784Greece

The fifth generation(5G)of wireless networks features three core use cases,namely ultra-reliable and low latency communications(URLLC),massive machine type communications(mMTC),and enhanced mobile broadband(eMBB).These use cases co-exist in many practical scenarios and compete for the same set of time and frequency resources,resulting in a natural trade-off in their *** this paper,a network supporting both URLLC and eMBB modes of operation is *** guarantee the ultra low latency requirement of URLLC,a dynamic resource allocation scheme indicated by a two-dimensional bitmap is *** approach is capable to achieve finer granularity as well as lower false cancellation rate compared to the state-of-the-art methods.A novel power control and indication method is also proposed to dynamically provide different power control parameters to the user equipment(UE),while guaranteeing the reliability requirement of URLLC and minimizing the impact to *** addition,we devise a dynamic selection mechanism(DSM)to accommodate diverse scenarios,which is empowered with load prediction to become more *** extensive system-level simulation results for eMBB-URLLC co-existence scenarios showcase that the perceived throughput of eMBB UEs is increased by 45.3%,while about 13.3% more UEs are enjoying URLLC services with at most 84% transmit power savings compared to the state-of-the-art methods.

关键词： the fifth generation(5G) co-existence enhanced mobile broadband(eMBB) multiplexing resource allocation power control ultra-reliable and low latency communications(URLLC) uplink

Access Control Mechanism for Blog Posts with Fine- Grained Ability Using Simple Operations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2017年第2期15卷 194-198页

作者： Yi-Hui Chen Chi-Shiang Chan Yuan-Yu Tsai department of M-commerce and multimedia Applications Asia University Taichung 41354

Access control enables the owners to assign different users different permissions to see different views. The current blog system does not support fine-grained authorization. That is, the bloggers disallow to just assign partial contents of the blog posts （i.e., a paragraph or several paragraphs） to readers. The management cost is no doubt to be significantly increased while handling the authorizations on the huge amount of blog articles. In this paper, we propose a scheme for supporting a fine-grained access control mechanism on blog articles. The advantage is that bloggers are able to authorize partial contents of blog posts to different users or groups of users.

关键词： Index Terms Authorization blog articles finegrained access control.

Handheld 3D Scanner for Small Objects Using Kinect

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2016年第4期14卷 377-383页

作者： Chia-Chi Hsu Chung-Lin Huang Taiwan Residents Army department of M-commerce and multimedia Applications Asia UniversityTaichung 41354

This paper presents a handheld 3D vision-based scanner for small objects by using Kinect. It is different from the previous color-glove-based approaches which require segmenting the target object. First, we eliminate the noises and the outliers caused by holding hands. Second, we apply Kinect-fusion algorithm and truncated signed distance function （TSDF） to represent 3D surfaces. Third, we propose a modified integration strategy to eliminate the hand effect. Fourth, we take advantage of the parallel computation of GPUs for real-time operation. The major contributions of this paper are （1） the registration precision is improved, （2） the oflline amendment and loop closure operation are not required, and （3） concave 3D object reconstruction is feasible.

关键词： Handheld 3D scanning Kinect-fusion,Truncated signed distance function (TSDF).

A Genetic Algorithm Based Approach for Campus Equipment Management System in Cloud Server

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2013年第2期11卷 187-191页

作者： Yu-Cheng Lin department of multimedia and mobile commerce at Kainan University

In this paper, we proposed a campus equipment ubiquitous-management system which is based on a genetic algorithm approach in cloud server. The system uses radio frequency identification （RFID） to monitor the status of equipment in real time, and uses wire or wireless network to send real-time situation to display on manager＇s PC or PDA. In addition, the system will also synchronize with database to record and reserve message. Furthermore, the status will display not only to a single manager but also a number of managers. In order to increase efficiency between graphical user interface （GUI） and database, the system adopts SqlDependency object of *** so that any changed situation of the database could be known immediately and synchronized with manager＇s PC or PDA. Because the problem of the equipment utilization is an NP-complete （non-deterministic polynomial） problem, we apply genetic algorithm to enhance the efficiency of finding optimum solution for equipment utilization. We assign constraints into the system, and the system will post back the optimum solution simultaneously on the screen. As a consequence, we compare our genetic algorithm based approach （GA） with the simulated annealing based approach （SA） for maximizing the equipment utilization. Experimental result shows that our GA approach achieves an average 79.66% improvement in equipment utilization in an acceptable run time.

关键词： Campus equipment cloud server genetic algorithm RFID ubiquitous-managementsystem.

Access Control Policy Analysis and Access Denial Method for Cloud Services

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2013年第2期11卷 176-180页

作者： Chi-Lun Liu department of multimedia and mobile commerce Kainan University

Personal cloud computing is an emerging trend in the computer industry. For a sustainable service, cloud computing services must control user access. The essential business characteristics of cloud computing are payment status and service level agreement. This work proposes a novel access control method for personal cloud service business. The proposed method sets metadata, policy analysis rules, and access denying rules. Metadata define the structure of access control policies and user requirements for cloud services. The policy analysis rules are used to compare conflicts and redundancies between access control policies. The access denying rules apply policies for inhibiting inappropriate access. The ontology is a theoretical foundation of this method. In this work, ontologies for payment status, access permission, service level, and the cloud provide semantic information needed to execute rules. A scenario of personal data backup cloud service is also provided in this work. This work potentially provides cloud service providers with a convenient method of controlling user access according to changeable business and marketing strategies.

关键词： Access control cloud services ontology payment service level agreement.

Human Action Recognition Based on Dense Trajectories Analysis and Random Forest

在线全文

学校读者我要写书评

暂无评论

Journal of Electronic Science and Technology 2016年第4期14卷 370-376页

作者： Pin-Zhong Pan Chung-Lin Huang Sonix Technology HsinChu 30265HsinChu department of M-commerce and multimedia Applications Asia UniversityTaichung 41354Taichung

This paper presents a human action recognition method. It analyzes the spatio-temporal grids along the dense trajectories and generates the histogram of oriented gradients （HOG） and histogram of optical flow （HOF） to describe the appearance and motion of the human object. Then, HOG combined with HOF is converted to bag-of-words （BoWs） by the vocabulary tree. Finally, it applies random forest to recognize the type of human action. In the experiments, KTH database and URADL database are tested for the performance evaluation. Comparing with the other approaches, we show that our approach has a better performance for the action videos with high inter-class and low inter-class variabilities.

关键词： Bag-of-words (BoWs) dense trajectories histogram of optical flow (HOF) histogram of oriented gradient (HOG) random forest vocabulary tree.