检索结果-南通市图书馆

Stroke Based Painterly Rendering with Mass Data through Auto Warping Generation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2022年第3期130卷 1441-1457页

作者： Taemin Lee Beomsik Kim sanghyun seo Kyunghyun Yoon Davinci SW Education Institute Chung-Ang UniversitySeoul06974South Korea School of Computer Science and Engineering Chung-Ang UniversitySeoul06974South Korea College of Art&Technology Chung-Ang UniversityGyeonggi-do17546South Korea

Painting is done according to the artist’s *** most representative of the style is the texture and shape of the brush *** simulations allow the artist’s painting to be produced by taking this stroke and pasting it onto the *** is called stroke-based *** quality of the result depends on the number or quality of this stroke,since the stroke is taken to create the *** is not easy to render using a large amount of information,as there is a limit to having a stroke *** this work,we intend to produce rendering results using mass data that produces large amounts of strokes by expanding existing strokes through *** this,we have produced results that have higher quality than conventional ***,we also compare the correlation between the amount of data and the results.

关键词： Painterly rendering stroke based rendering image mass data stroke warping non-photorealistic rendering

Explicitly Color-Inspired Neural Style Transfer Using

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Modeling in Engineering & Sciences 2024年第12期141卷 2143-2164页

作者： Bumsoo Kim Wonseop Shin Yonghoon Jung Youngsup Park sanghyun seo Department of Applied Art and Technology Chung-Ang UniversityAnseong17546Republic of Korea Department of Advanced Imaging Science Multimedia&Film Chung-Ang UniversitySeoul06974Republic of Korea Innosimulation Co. Ltd.Gangseo-gu07794Republic of Korea School of Art and Technology Chung-Ang UniversityAnseong17546Republic of Korea

Arbitrary style transfer aims to perceptually reflect the style of a reference image in artistic creations with visual *** style transfer models,particularly those using adaptive instance normalization(AdaIN)layer,rely on global statistics,which often fail to capture the spatially local color distribution,leading to outputs that lack variation despite geometric *** address this,we introduce Patchified AdaIN,a color-inspired style transfer method that applies AdaIN to localized patches,utilizing local statistics to capture the spatial color distribution of the reference *** approach enables enhanced color awareness in style transfer,adapting dynamically to geometric transformations by leveraging local image *** Patchified AdaIN builds on AdaIN,it integrates seamlessly into existing frameworks without the need for additional training,allowing users to control the output quality through adjustable blending *** comprehensive experiments demonstrate that Patchified AdaIN can reflect geometric transformations(e.g.,translation,rotation,flipping)of images for style transfer,thereby achieving superior results compared to state-of-the-art *** experiments show the compatibility of Patchified AdaIN for integration into existing networks to enable spatial color-aware arbitrary style transfer by replacing the conventional AdaIN layer with the Patchified AdaIN layer.

关键词： Neural style transfer image synthesis image stylization

An Efficient and Robust Hand Gesture Recognition System of Sign Language Employing Finetuned Inception-V3 and Efficientnet-B0 Network

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第9期46卷 3509-3525页

作者： Adnan Hussain Sareer Ul Amin Muhammad Fayaz sanghyun seo Department of Computer Science Islamia College UniversityPeshawar25120Pakistan Department of Computer Science and Engineering Chung-Ang UniversitySeoul06974Korea Department of Computer Engineering Cyprus International UniversityLefkosa99010Rep.of North Cyprus College of Art and Technology Chung-Ang.UniversityAnseong17546Korea

Hand Gesture Recognition(HGR)is a promising research area with an extensive range of applications,such as surgery,video game techniques,and sign language translation,where sign language is a complicated structured form of hand *** fundamental building blocks of structured expressions in sign language are the arrangement of the fingers,the orientation of the hand,and the hand’s position concerning the *** importance of HGR has increased due to the increasing number of touchless applications and the rapid growth of the hearing-impaired ***,real-time HGR is one of the most effective interaction methods between computers and *** a user-free interface with good recognition performance should be the goal of real-time HGR ***,Convolutional Neural Network(CNN)shows great recognition rates for different image-level classification *** is challenging to train deep CNN networks like VGG-16,VGG-19,Inception-v3,and Efficientnet-B0 from scratch because only some significant labeled image datasets are available for static hand gesture ***,an efficient and robust hand gesture recognition system of sign language employing finetuned Inception-v3 and Efficientnet-Bo network is proposed to identify hand gestures using a comparative small HGR *** show that Inception-v3 achieved 90%accuracy and 0.93%precision,0.91%recall,and 0.90%f1-score,respectively,while EfficientNet-B0 achieved 99%accuracy and 0.98%,0.97%,0.98%,precision,recall,and f1-score respectively.

关键词： Pretrained CNN hand gesture recognition transfer learning

An Efficient False-Positive Reduction System for Cerebral Microbleeds Detection

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 2021年第3期66卷 2301-2315页

作者： Sitara Afzal Muazzam Maqsood Irfan Mehmood Muhammad Tabish Niaz sanghyun seo Department of Computer Science COMSATS University IslamabadAttock CampusAttockPakistan Department of Media Design and Technology Faculty of Engineering&InformaticsUniversity of BradfordBradfordBD71AZUK Department of Smart Device Engineering School of Intelligent Mechatronics EngineeringSejong UniversitySeoulSouth Korea School of Computer Art College of Art&TechnologyChung-Ang UniversityAnseong17546South Korea

Cerebral Microbleeds(CMBs)are microhemorrhages caused by certain abnormalities of brain *** can be found in people with Traumatic Brain Injury(TBI),Alzheimer’s disease,and in old individuals having a brain *** research reveals that CMBs can be highly dangerous for individuals having dementia and *** CMBs seriously impact individuals’life which makes it crucial to recognize the CMBs in its initial phase to stop deterioration and to assist individuals to have a normal *** existing work report good results but often ignores false-positive’s perspective for this research *** this paper,an efficient approach is presented to detect CMBs from the Susceptibility Weighted Images(SWI).The proposed framework consists of four main phases(i)making clusters of brain Magnetic Resonance Imaging(MRI)using k-mean classifier(ii)reduce false positives for better classification results(iii)discriminative feature extraction specific to CMBs(iv)classification using a five layers convolutional neural network(CNN).The proposed method is evaluated on a public dataset available for 20 *** proposed system shows an accuracy of 98.9%and a 1.1%false-positive rate *** results show the superiority of the proposed work as compared to existing states of the art methods.

关键词： Microbleeds detection false-positive deep learning CNN

An Efficient Attention-Based Strategy for Anomaly Detection in Surveillance Video

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computer Systems Science & Engineering 2023年第9期46卷 3939-3958页

作者： Sareer Ul Amin Yongjun Kim Irfan Sami Sangoh Park sanghyun seo Department of Computer Science and Engineering Chung-Ang UniversitySeoul06974Korea Intelligent Convergence Research Lab. ETRIDaeJeon34129Korea Department of Electrical and Electronics Engineering Chung-Ang UniversitySeoul06974Korea College of Art and Technology Chung-Ang UniversityAnseong17546Korea

In the present technological world,surveillance cameras generate an immense amount of video data from various sources,making its scrutiny tough for computer vision *** is difficult to search for anomalous events manually in thesemassive video records since they happen infrequently and with a low probability in real-world monitoring ***,intelligent surveillance is a requirement of the modern day,as it enables the automatic identification of normal and aberrant behavior using artificial intelligence and computer vision *** this article,we introduce an efficient Attention-based deep-learning approach for anomaly detection in surveillance video(ADSV).At the input of the ADSV,a shots boundary detection technique is used to segment prominent ***,The Lightweight ConvolutionNeuralNetwork(LWCNN)model receives the segmented frames to extract spatial and temporal information from the intermediate *** that,spatial and temporal features are learned using Long Short-Term Memory(LSTM)cells and Attention Network from a series of frames for each anomalous activity in a *** detect motion and action,the LWCNN received chronologically sorted ***,the anomaly activity in the video is identified using the proposed trained ADSV *** experiments are conducted on complex and challenging benchmark *** addition,the experimental results have been compared to state-ofthe-artmethodologies,and a significant improvement is attained,demonstrating the efficiency of our ADSV method.

关键词： Attention-based anomaly detection video shots segmentation video surveillance computer vision deep learning smart surveillance system violence detection attention model

Proxy-Based Hierarchical Distributed Mobility Management for Tactical 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

Computers, Materials & Continua 2022年第2期70卷 2381-2399页

作者： Myoung-hun Han Bong-Soo Roh Kyungwoo Kim Dae-Hoon Kwon Jae-Hyun Ham KyungHyun Yoon sanghyun seo Agency for Defense Development Daejeon34186Korea Department of Computer Science and Engineering Chung-Ang UniversitySeoul06974Korea College of Art&Technology Chung-Ang UniversityAnseong17546Korea

An important requirement in a military domain is a highly reliable mobility management method,especially when components of the networks aremoving in tactical network *** increase reliability,themobility management technology of the tactical network should be able to reflect the characteristics of the tactical network,such as a limited environment,failure,and hierarchical unit *** this paper,we propose a proxy-based hierarchical distributedmobilitymanagement scheme,which is highly focused on tactical *** the characteristics of tactical networks,the proposed scheme is composed of the following:1)a proxy-based method,2)a distributed mobility management method that synchronizes a mobility database between entities,and 3)a method of managing mobility by dividing the tactical network into upper and lower *** analysis and modeling and simulation results demonstrate that the method outperforms the existing state-of-the-art method in overcoming entity failure,handover cost,and delay in tactical environments.

关键词： Mobility management tactical networks PMIP DMM