发布求助
文献互助 智能选刊 最新文献

Proceedings of the 4th International Conference on Graphics and Signal Processing最新文献

筛选
英文 中文
Research and Implementation of Violation Monitoring System for Electric Customer Service Hall 电子客服大厅违规监控系统的研究与实现
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406986
Shiwen Dong, Peng Wu, Junfeng Qiao
{"title":"Research and Implementation of Violation Monitoring System for Electric Customer Service Hall","authors":"Shiwen Dong, Peng Wu, Junfeng Qiao","doi":"10.1145/3406971.3406986","DOIUrl":"https://doi.org/10.1145/3406971.3406986","url":null,"abstract":"Automatic detection of violations will improve the efficiency of enterprise management and reduce the workload of employees. In this paper, an electric customer service hall monitoring system based on Improved Tiny-yolo v3 is developed for common violation in the services of electric customer hall: mobile phone playing behavior, smoking behavior, sleeping behavior, manicuring behavior and fighting behavior. The experimental results show that the system can meet the requirements of real-time and accuracy in electric customer service hall monitoring.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115651862","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Enhancement Spatial Transformer Networks for Text Classification 用于文本分类的增强空间变换网络
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406981
Ka‐Hou Chan, S. Im, Vai-Kei Ian, Ka-Man Chan, W. Ke
{"title":"Enhancement Spatial Transformer Networks for Text Classification","authors":"Ka‐Hou Chan, S. Im, Vai-Kei Ian, Ka-Man Chan, W. Ke","doi":"10.1145/3406971.3406981","DOIUrl":"https://doi.org/10.1145/3406971.3406981","url":null,"abstract":"This paper introduces a 2D transformation based framework for arbitrary-oriented text detection in natural scene images. We present the localization networks within Spatial Transformer Networks (STN), which are designed to generate proposals with text orientation affine information including translation, scaling and rotation. This information will then be adapted as learning parameters to make the proposals to be fitted into the text regular form in terms of the orientation more accurately. Localization network is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. Compared with any previous text detection systems, this work ensures the relationship between the learning parameters, which can lead to a better approximation for orientation. As a result, this new layer greatly enhances the training accuracy. Moreover, the design and implementation can be easily deployed in the current systems built upon the standard CNNs architecture.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126969146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 3
Image Retrieval Algorithm Based on Deep Learning 基于深度学习的图像检索算法
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406984
Yidan Li, Mingjie Wang
{"title":"Image Retrieval Algorithm Based on Deep Learning","authors":"Yidan Li, Mingjie Wang","doi":"10.1145/3406971.3406984","DOIUrl":"https://doi.org/10.1145/3406971.3406984","url":null,"abstract":"The traditional hashing method of manual feature extraction uses image tags as the supervision information to obtain the loss function, and the retrieval accuracy is low and the effect is not good. This paper proposes a new deep learning image retrieval algorithm based on the traditional supervised hash algorithm. The algorithm integrates feature learning and hash code learning in an end-to-end framework, and converts multi-labels of images into binary paired labels. Based on the AlexNet framework, a feature learning module is established, and a pair of loss function and a balanced hash code loss function are combined to generate a loss function for network training. After the experimental test of the CIFAR-10 data set, the method of this paper greatly improves the average accuracy of image retrieval.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123852858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Knowledge Management System Model for Hospital (Indonesian Context) 医院知识管理系统模型(印尼背景)
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406979
Yohannes Kurniawan, Fredy Jingga, Natalia Limantara
{"title":"Knowledge Management System Model for Hospital (Indonesian Context)","authors":"Yohannes Kurniawan, Fredy Jingga, Natalia Limantara","doi":"10.1145/3406971.3406979","DOIUrl":"https://doi.org/10.1145/3406971.3406979","url":null,"abstract":"The main healthcare provider in every country is hospital, the hospital is the organization very high depending on the capabilities of human resources, so the organization need to manage the tacit and explicit knowledge from the medical personnel. This research explained the knowledge management model focus on how to manage tacit and explicit knowledge of medical personnel in hospital at Indonesia, because the main problem is how the senior medical personnel transfer the knowledge to explicit form or vice versa. The research used descriptive statistic to analysis from thirty-three hospitals knowledge mode or conversion from tacit-explicit or explicit-tacit. The results showed the hospital still need to increase the explicit knowledge from medical personnel in the hospital to increase the learning process of junior medical personnel.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"520 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116188164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Mammogram Denoising Using High Boost Filter and Vectorization Convolutional Neural Networks 基于高升压滤波和矢量化卷积神经网络的乳房x线照片去噪
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406982
Varakorn Kidsumran
{"title":"Mammogram Denoising Using High Boost Filter and Vectorization Convolutional Neural Networks","authors":"Varakorn Kidsumran","doi":"10.1145/3406971.3406982","DOIUrl":"https://doi.org/10.1145/3406971.3406982","url":null,"abstract":"Mammogram screening is the effective way to prevent breast cancer in the early detection stage. However, low dose radiation from x-ray machine causes a degradation of visuality of mammograms that make interpretation error to radiologists. In this paper, high boost filter and vectorization convolutional neural networks are combined to improve visual quality of mammograms. The experimental results illustrate that the proposed method can improve contrast and suppress noise in mammograms comparing to the traditional denoising methods.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128984684","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
SVM Based Hiragana and Katakana Recognition Algorithm with Neural Network Based Segmentation 基于支持向量机的平假名和片假名识别算法与神经网络分割
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406978
Piotr Szymkowski, K. Saeed, N. Nishiuchi
{"title":"SVM Based Hiragana and Katakana Recognition Algorithm with Neural Network Based Segmentation","authors":"Piotr Szymkowski, K. Saeed, N. Nishiuchi","doi":"10.1145/3406971.3406978","DOIUrl":"https://doi.org/10.1145/3406971.3406978","url":null,"abstract":"A Japanese writing system, unlike the European system, is complex. It contains three types of signs: hiragana, katakana and Kanji. For daily use, more than 2000 characters are used, and each symbol can consist of 6 or more strokes. That is why it seems possible to recognise each sign by using a similar approach to fingerprint recognition. Authors are using the minutiae-finding algorithm to find three types of characteristic points. For preprocessing and classification, machine learning algorithms were used. The presented system uses the image of a single sign as an input.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"24 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133686494","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Fault-Tolerate Control for Distance-Only Multi-agent Formation Using Discrete Fourier Transform 基于离散傅里叶变换的距离多智能体编队容错控制
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406992
Hao-Yu Wang
{"title":"Fault-Tolerate Control for Distance-Only Multi-agent Formation Using Discrete Fourier Transform","authors":"Hao-Yu Wang","doi":"10.1145/3406971.3406992","DOIUrl":"https://doi.org/10.1145/3406971.3406992","url":null,"abstract":"Multi-agent formation is a mobile robot cluster based on wireless sensor network(WSN), in which each agent has the ability of sensing and computing. It has a wide range of applications in the fields of transportation, aerospace, exploration, etc. The main difficulty of formation control is positioning accuracy and fault tolerance. Existing technology is generally realized by combining distance information and other auxiliary information. However, these technologies have limitations both in cost and generality, so it is infeasible for a large-scale formation system. In this paper, a fault-tolerate formation control method for distance-only multi-agent formation is proposed. The main technique we use is Discrete Fourier Transform (DFT). On the premise of combination in circle and linear motion, the motion parameters of agent are estimated by DFT during discrete time series. On this basis, by monitoring the associated reference points of related targets, each individual in the formation can accurately locate the coordinates of neighbors in its own local coordinate system. In the noise simulation experiment, this method reduces formation distance error by about 20%. The experiment results also show efficiency in non-rigid formation shape control.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122626637","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Moiré Pattern Removal with a Generative Adversarial Network 基于生成对抗网络的moir<s:1>模式去除
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406973
Jinhui Wang, Lijiang Chen, Pengfei Chen, Xia Mao
{"title":"Moiré Pattern Removal with a Generative Adversarial Network","authors":"Jinhui Wang, Lijiang Chen, Pengfei Chen, Xia Mao","doi":"10.1145/3406971.3406973","DOIUrl":"https://doi.org/10.1145/3406971.3406973","url":null,"abstract":"Moiré patterns can be seen in camera-captured digital screen photos due to the interference between the pixel grids of the camera sensor and the pixel grids of the digital screen. It severely degrades the quality of the photos. With the rapid development of personal devices, people are using digital camera to take photos more and more often. Among them, it's very common to see camera-captured screen photos, so the work of Moiré pattern removal is very meaningful for improving user experience. In this paper, we introduce a novel method of Moiré pattern removal based on the Generative Adversarial Network (GAN). To train our model, we built a dataset of paired Ground and Moiré images, which has 16,500 images totally. Experiments showed that, given Moiré images as the input, the trained generator of our GAN nets can produce Moiré-free images of high quality.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115811341","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Hierarchical and Compact Bitmap Based Data Structure of Human Dynamics Data for Visualization 基于分层和紧凑位图的人体动态数据可视化数据结构
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406980
H. Kimata, Wu Xiaojun, Ryuichi Tanida
{"title":"Hierarchical and Compact Bitmap Based Data Structure of Human Dynamics Data for Visualization","authors":"H. Kimata, Wu Xiaojun, Ryuichi Tanida","doi":"10.1145/3406971.3406980","DOIUrl":"https://doi.org/10.1145/3406971.3406980","url":null,"abstract":"Analysis and prediction of human dynamics are key technologies to evolve various services for cognizing real world events, and they have been intensively studied in the field of data science. Technologies that support such studies have been advanced, in fields of sensing, analysis, and database. Thanks to recent sensing technologies, precision of sensing human movement is increasing, and a large amount of data is been generated continuously. Accordingly data that indicate a very large population can be efficiently collected, stored and visualized. To enable such a large amount of data to be visualized quickly, we propose data structure for two dimensional space data that has a compact one byte representation and hierarchical structure that can efficiently handle human dynamics data.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122793159","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 1
Classification of Vigilance Based on EEG 基于脑电图的警觉性分类
Proceedings of the 4th International Conference on Graphics and Signal Processing Pub Date : 2020-06-26 DOI: 10.1145/3406971.3406987
Meiyan Zhang, Jinwei Sun, Qisong Wang, Dan Liu
{"title":"Classification of Vigilance Based on EEG","authors":"Meiyan Zhang, Jinwei Sun, Qisong Wang, Dan Liu","doi":"10.1145/3406971.3406987","DOIUrl":"https://doi.org/10.1145/3406971.3406987","url":null,"abstract":"Vigilance (also known as continuous attention) is an important type of human attention, closely related to the cognitive activities of life and work. Many human-computer interaction systems require vigilance of the operators to be kept at a certain level in critical tasks. In view of the problem that the vigilance of operators decreases as the time and difficulty of performing tasks in crucial positions increase, it is necessary to monitor the vigilance. This paper summarizes the advantages and disadvantages of physiological signal evaluation vigilance, and proposes classifying vigilance based on EEG method. The results show that the vigilance can be well evaluated, remedial measures can hence be taken avoiding the loss caused by the decreased vigilance.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126261866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信