发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems最新文献

筛选
英文 中文
Scotopic Vision Image Enhancement Algorithm Based on Retinex Model 基于Retinex模型的暗位视觉图像增强算法
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416108
Lijuan Xiang, Lingyun Gao, Ying Zhao, Qin Zhang, Zhiqiang Zhao
{"title":"Scotopic Vision Image Enhancement Algorithm Based on Retinex Model","authors":"Lijuan Xiang, Lingyun Gao, Ying Zhao, Qin Zhang, Zhiqiang Zhao","doi":"10.1145/3415048.3416108","DOIUrl":"https://doi.org/10.1145/3415048.3416108","url":null,"abstract":"Scotopic vision image enhancement has problems of over-enhancement and halo artifacts, based on retinex theory, this article proposes illumination map estimate method to enhancement image to solve those problems. Specifically, we extracted the image of Max-RGB and Y channel as global and local initial illumination map respectively. Then, we improved weighted guided filter to reduce halo artifacts. Next, we refined the initial illumination maps with weighted average, improved weighted guided filtering and gamma correction, as the final illumination map. Finally, the enhanced result is obtained by the corrected illumination map according to retinex theory. Experiments shown that the method can obtain results with less lightness distortion and reduce halo artifacts compared with that of several state-of-the-art methods.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126340264","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
Optimized Phase-Shift Control Method Based on Load Current Feedforward for Bidirectional Full Bridge DC-DC Converters 基于负载电流前馈的双向全桥DC-DC变换器优化相移控制方法
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416112
Jiawei Zhang
{"title":"Optimized Phase-Shift Control Method Based on Load Current Feedforward for Bidirectional Full Bridge DC-DC Converters","authors":"Jiawei Zhang","doi":"10.1145/3415048.3416112","DOIUrl":"https://doi.org/10.1145/3415048.3416112","url":null,"abstract":"In all-DC offshore wind farms, DC transformer is as an essential part of energy collection, as well as transformation and transmission. However, the intermittency of wind energy could not be avoided, which makes the transmission power of the system unstable, so an excellent dynamic performance for DC transformer is extremely important. This paper proposes an optimal phase-shift control method based on current feedforward to enhance the dynamic characteristic. By leading the load current in a certain proportion into the calculation of the optimal phase-shift, the phase-shift of the converter is recalculated immediately when the load suddenly changes, so as to achieve faster dynamic response speed. At last, based on the MATLAB / Simulink simulation software, the proposed method is verified by a series of experimental results. The effectiveness of the method is verified by simulation analysis.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124190155","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
A Review of Sonar Image Segmentation for Underwater Small Targets 水下小目标声纳图像分割研究进展
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416098
Yuanyuan Tian, Luyu Lan, Linna Sun
{"title":"A Review of Sonar Image Segmentation for Underwater Small Targets","authors":"Yuanyuan Tian, Luyu Lan, Linna Sun","doi":"10.1145/3415048.3416098","DOIUrl":"https://doi.org/10.1145/3415048.3416098","url":null,"abstract":"The existing image segmentation methods are various, but due to the particularity of sonar images, the ordinary image segmentation methods often fail to achieve ideal results when processing sonar images and have limitations. On the basis of studying a large number of image segmentation methods at home and abroad, the authors recommends the following methods with comprehensive characteristics that are more suitable for sonar image segmentation, such as thresholding, edge detection, MRF and clustering algorithm. For nearly a decade, many scholars have improved the traditional segmentation methods by combining the characteristics of sonar images, or improved the algorithms by combining various segmentation methods to make up for the shortcomings of the original segmentation methods applied to sonar images.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122762583","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: 4
Research on Voxel Time-Density Model in Cone-Beam CT Functional Imaging 锥束CT功能成像体素时间密度模型研究
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416110
Ying Qian, Can Xia
{"title":"Research on Voxel Time-Density Model in Cone-Beam CT Functional Imaging","authors":"Ying Qian, Can Xia","doi":"10.1145/3415048.3416110","DOIUrl":"https://doi.org/10.1145/3415048.3416110","url":null,"abstract":"In the current study we study the variation law of the voxel time-density (TDC) curve in the arteries, tissues and tumors regions, and apply this rule to functional CBCT imaging, which solve the problem that functional CBCT imaging could not directly obtain the TDC curve. Methods: In the arteries, tumors and tissue regions on the DCE-CT sequence image, a 3 ×3 pixels is selected as the region of interest (ROI) respectively, and acquired CBCT projection data. The TDC model was established according to the shape of arterial, tissue and tumor curve respectly. The TDC model is substituted into the CBCT projection data, the approximate TDC (SimuTDC) and attribute (the voxel is located in the artery, tumor or tissue area) of each voxel is obtained by inverse solution. European distance and recall rate were used to evaluate the accuracy of SimuTDC measurements and attribute with the TDC model. Results: European distance (arteries, 0.0644; tumors, 0.0557; tissues, 0.1673) analyses revealed highly significant correlations between SimuTDC values calculated with our method and TrueTDC. Recall rate (arteries, 1; tumors, 1; tissues, 1)analyses revealed that using our method can well predict whether the voxel is located in the artery, tumor or tissue area. Conclusion: The SimuTDC and attribute of each voxel can be obtained using our method. Due to computational speed and hardware equipment, the data used in the experiment is limited, which reduces the reliability and reproducibility of this approach.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129426447","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
Filter Pruning Based on Connection Sensitivity 基于连接灵敏度的过滤器剪枝
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416114
Yinong Xu, Yunsen Liao, Ying Zhao
{"title":"Filter Pruning Based on Connection Sensitivity","authors":"Yinong Xu, Yunsen Liao, Ying Zhao","doi":"10.1145/3415048.3416114","DOIUrl":"https://doi.org/10.1145/3415048.3416114","url":null,"abstract":"For the goal of reducing the remarkable redundancy in deep convolutional neural networks (CNNs), we propose an efficient framework to compress and accelerate CNN models. This work focus on pruning at filter level, mainly removing those less important filters. Firstly, we measure the importance of the filter by introducing a saliency criterion based on its corresponding connection sensitivity. In addition, we apply an algorithm, which transform a vanilla CNN module, to provide a quantitative ranking. Next, we prune the redundancy by discarding unimportant filters. Finally, we fine-tune the network to improve its accuracy. We verify the effectiveness of our method with VGGNet and ResNet on multiple datasets, such as CIFAR-10 and ImageNet ILSVRC-12. For instance, we achieve more than 50% FLOPs reduction on ResNet-56 with virtually the same accuracy as the reference network.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124020320","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
Hand Movement Direction Decoding from EEG Signals under Dual Movement Tasks 双运动任务下手脑电信号的运动方向解码
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416096
Jiarong Wang, Luzheng Bi
{"title":"Hand Movement Direction Decoding from EEG Signals under Dual Movement Tasks","authors":"Jiarong Wang, Luzheng Bi","doi":"10.1145/3415048.3416096","DOIUrl":"https://doi.org/10.1145/3415048.3416096","url":null,"abstract":"Decoding human motor intention from electroencephalograms (EEG) signals is valuable for developing intelligent driver-assistive systems. However, existing studies about human motion decoding from EEG signals are only focused on one main movement task without considering the influence of other movement tasks. In this work, we explore the decoding of right-hand movement direction from EEG signals in the presence of a left-hand movement. A corresponding experimental paradigm was designed. The phase-locking value (PLV), amplitude in the time domain, and spectrum energy in the frequency domain from different frequency bands were used as classification features, respectively, and linear discrimination analysis (LDA) was used as a classifier to decode movement direction of the right hand. Experimental results showed that the decoding model based on the amplitude in the delta band performed best with a mean accuracy of 73.01% for the left-and-right direction pair, showing the feasibility of movement direction decoding of a single hand from EEG signals under a movement of the other hand.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128845615","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: 2
Robotic Manipulation Based on 3D Vision: A Survey 基于三维视觉的机器人操作研究进展
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416116
Huahua Lin
{"title":"Robotic Manipulation Based on 3D Vision: A Survey","authors":"Huahua Lin","doi":"10.1145/3415048.3416116","DOIUrl":"https://doi.org/10.1145/3415048.3416116","url":null,"abstract":"Grasping has long been studied in the field of robotics. In this paper, we divide the process of robotic grasp into sensing and control. In terms of sensing, 2D vision based sensing relies on accurate feature matching and object surface texture features, resulting in poor performance in the complex environment with occlusion. By contrast, some sensors based on 3D vision are more robust to noise. Processing point clouds in a deep learning method can achieve high accuracy as well as reducing the computation time compared with those using cost volume regularization. For the control part, the traditional trajectory motion methods are limited to generalization and grasping with high degrees of freedom. On the contrary, the methods of reinforcement learning can improve the grasping strategy in the continuous interaction with the environment. We propose some commonly used benchmarks and simulation platforms for simulation experiment using reinforcement learning.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"41 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123728384","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
An Investigation on High-Speed Optical Transmission Technology for Datacenter 数据中心高速光传输技术研究
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416115
Wenxin Zeng
{"title":"An Investigation on High-Speed Optical Transmission Technology for Datacenter","authors":"Wenxin Zeng","doi":"10.1145/3415048.3416115","DOIUrl":"https://doi.org/10.1145/3415048.3416115","url":null,"abstract":"Datacenter is an important product of information society and an important supporting part for the development of new Internet businesses. With the emergence of a large number of new Internet technologies, the network demand and data traffic of users are growing rapidly. Datacenter needs larger data capacity and better system performance. High-speed optical interconnection technology has attracted more and more attention and become the main solution to the problem of traffic growth in datacenter, with its characteristics of high bandwidth, low loss and low cost. In this paper, several mainstream signal modulation formats, digital signal processing (DSP) compensation algorithms and signal damage compensation algorithms are investigated for intra datacenter optical interconnection and inter/extended datacenter optical interconnection, respectively. Their principles, performance, advantages and disadvantages are analyzed and compared in detail, and the future development of datacenter optical transmission is prospected.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122296585","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
Techniques for Complex Analysis of Contemporary Data 当代数据的复杂分析技术
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416097
J. Peschel, Michal Batko, P. Zezula
{"title":"Techniques for Complex Analysis of Contemporary Data","authors":"J. Peschel, Michal Batko, P. Zezula","doi":"10.1145/3415048.3416097","DOIUrl":"https://doi.org/10.1145/3415048.3416097","url":null,"abstract":"Contemporary data objects are typically complex, semi-structured, or unstructured at all. Besides, objects are also related to form a network. In such a situation, data analysis requires not only the traditional attribute-based access but also access based on similarity as well as data mining operations. Though tools for such operations do exist, they usually specialise in operation and are available for specialized data structures supported by specific computer system environments. In contrary, advance analyses are obtained by application of several elementary access operations which in turn requires expert knowledge in multiple areas. In this paper, we propose a unification platform for various data analytical operators specified as a general-purpose analytical system ADAMiSS. An extensible data-mining and similarity-based set of operators over a common versatile data structure allow the recursive application of heterogeneous operations, thus allowing the definition of complex analytical processes, necessary to solve the contemporary analytical tasks. As a proof-of-concept, we present results that were obtained by our prototype implementation on two real-world data collections: the Twitter Higg's boson and the Kosarak datasets.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"8 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126076309","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: 2
Investigation of Faster-RCNN Inception Resnet V2 on Offline Kanji Handwriting Characters 快速rcnn Inception renet V2对离线汉字手写汉字的研究
Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416104
Anthony Adole, E. Edirisinghe, Baihua Li, Chris Bearchell
{"title":"Investigation of Faster-RCNN Inception Resnet V2 on Offline Kanji Handwriting Characters","authors":"Anthony Adole, E. Edirisinghe, Baihua Li, Chris Bearchell","doi":"10.1145/3415048.3416104","DOIUrl":"https://doi.org/10.1145/3415048.3416104","url":null,"abstract":"In recent years detection and recognition of Offline handwriting character has being a major task in the computer vision sector, researchers are looking at developing deep learning models to avoid the traditional approaches which involves the tedious task of using the conventional methods for feature extraction and localization. However, state-of-the-art object detection models rely upon region proposal algorithms as a result, they settle for object location principles, such network reduces the time period of those detection network, exposing region proposal computation as a bottleneck. Faster-RCNN is a popular model used for recognition purpose in many recognition tasks, the goal of this paper is to serve as a guide for Multi-Classification on offline Handwriting Document using Pre-trained Faster-RCNN with inception resnet v2 feature Extractor. The result obtained from the experiments shows improved pre-trained models can be used in solving the research question concerning handwriting detection and recognition.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124042967","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: 6
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