首页 > 最新文献

2018 7th International Conference on Digital Home (ICDH)最新文献

英文 中文
2D Chebyshev-Sine Map for Image Encryption 用于图像加密的二维切比雪夫正弦映射
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00008
Chaotic systems are extremely sensitive to initial conditions and system parameters, ergodicity, unpredictable, which are applied to the field of image encryption widely. This paper proposes a new scheme of combining chaos theory and image encryption–2D Chebyshev-Sine map. Through the analysis of the trajectory contours mapping and other chaos mappings, the method has a wide range of chaos and good ergodicity. And it is sensitive to initial conditions and system parameters, which cost relatively low. On this basis, a linear mixed layer image encryption algorithm is proposed. In this algorithm, row shift and column mixing are used to change the pixel space position and pixel frequency domain, And the diffusion principle of Chinese remainder theorem is applied. The results of simulation and analysis show that this encryption algorithm has low time efficiency, relatively high security, resistance to differential attack and performance against selective plaintext attack.
混沌系统具有对初始条件和系统参数极其敏感、遍历性强、不可预测等特点,被广泛应用于图像加密领域。本文提出了一种将混沌理论与图像加密相结合的新方案——二维切比雪夫正弦映射。通过对轨迹等高线映射和其他混沌映射的分析,该方法具有广泛的混沌范围和良好的遍历性。并且对初始条件和系统参数敏感,成本相对较低。在此基础上,提出了一种线性混合层图像加密算法。该算法采用行移和列混合来改变像素空间位置和像素频域,并应用了中国剩余定理的扩散原理。仿真和分析结果表明,该加密算法具有时间效率低、安全性较高、抗差分攻击和抗选择性明文攻击的性能。
{"title":"2D Chebyshev-Sine Map for Image Encryption","authors":"Y. Zhong, Huayi Liu, Rushi Lan, Ting Wang, Xiyan Sun, Xiaonan Luo","doi":"10.1109/ICDH.2018.00008","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00008","url":null,"abstract":"Chaotic systems are extremely sensitive to initial conditions and system parameters, ergodicity, unpredictable, which are applied to the field of image encryption widely. This paper proposes a new scheme of combining chaos theory and image encryption–2D Chebyshev-Sine map. Through the analysis of the trajectory contours mapping and other chaos mappings, the method has a wide range of chaos and good ergodicity. And it is sensitive to initial conditions and system parameters, which cost relatively low. On this basis, a linear mixed layer image encryption algorithm is proposed. In this algorithm, row shift and column mixing are used to change the pixel space position and pixel frequency domain, And the diffusion principle of Chinese remainder theorem is applied. The results of simulation and analysis show that this encryption algorithm has low time efficiency, relatively high security, resistance to differential attack and performance against selective plaintext attack.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"152 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116190740","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: 7
A Method of Feature Extraction for BCG Signal Based on Wavelet and Bispectrum 基于小波和双谱的BCG信号特征提取方法
Pub Date : 2018-11-01 DOI: 10.1109/icdh.2018.00027
The ballistocardiogram (BCG) is a useful information signal reflecting the state of cardiovascular system. In order to improve the monitoring level of cardiovascular diseases in China, a wavelet-bispectrum analysis method was proposed to extract the characteristic of BCG signal. First, the BCG signal was preprocessed. Then, wavelet decomposition and reconstruction were performed by choosing the appropriate wavelet function and decomposing levels, and the sub-bands were bispectrum analyzed for reconstruction. Finally, the maximum amplitude of slice spectrum and energy of each sub-band of BCG signal were extracted. The results have shown that the method can obtain the high-order time-frequency information in the BCG signal, and has obvious advantage for the non-stationary and non-Gaussian processing of BCG signal, it also provide a reliable basis for the application of BCG signal in clinical diagnosis.
BCG是反映心血管系统状态的有用信息信号。为了提高中国心血管疾病的监测水平,提出了一种提取BCG信号特征的小波-双谱分析方法。首先,对BCG信号进行预处理。然后选择合适的小波函数和分解层次进行小波分解和重构,并对子带进行双谱分析进行重构。最后提取出BCG信号的最大切片谱幅值和各子带能量。结果表明,该方法能获得卡介苗信号中的高阶时频信息,对卡介苗信号的非平稳、非高斯处理具有明显优势,为卡介苗信号在临床诊断中的应用提供了可靠依据。
{"title":"A Method of Feature Extraction for BCG Signal Based on Wavelet and Bispectrum","authors":"Zimin Wang, Li Zeng, Yumeng Wang, Man Wang","doi":"10.1109/icdh.2018.00027","DOIUrl":"https://doi.org/10.1109/icdh.2018.00027","url":null,"abstract":"The ballistocardiogram (BCG) is a useful information signal reflecting the state of cardiovascular system. In order to improve the monitoring level of cardiovascular diseases in China, a wavelet-bispectrum analysis method was proposed to extract the characteristic of BCG signal. First, the BCG signal was preprocessed. Then, wavelet decomposition and reconstruction were performed by choosing the appropriate wavelet function and decomposing levels, and the sub-bands were bispectrum analyzed for reconstruction. Finally, the maximum amplitude of slice spectrum and energy of each sub-band of BCG signal were extracted. The results have shown that the method can obtain the high-order time-frequency information in the BCG signal, and has obvious advantage for the non-stationary and non-Gaussian processing of BCG signal, it also provide a reliable basis for the application of BCG signal in clinical diagnosis.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"284 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127557209","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
User Interface Layout Recommendation Based on Pairing Model 基于配对模型的用户界面布局推荐
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00041
In order to facilitate the generation of user interfaces from mockups, an approach was proposed to recommend User Interface (UI) layout based on Pairing Model. The absolute layout data of interfaces, including types, text, positions and sizes of components, are input into the model to generate layout. Paring Model is trained by machine-learning algorithms with features extracted from UI galleries. On the levels of functional and spatial relationship, the model decides pairing of input components and recommends a suitable layout. With use of component features, by machine-learning algorithms, the types of components are identified, which are the leaf nodes of the output layout hierarchy. The experiments on 3362 interface instances from 800 open source apps proved that the accuracy of the proposed approach, on average, exceeds 90%.
为了方便用户界面的生成,提出了一种基于配对模型的用户界面布局推荐方法。将接口的绝对布局数据,包括组件的类型、文本、位置和大小,输入到模型中生成布局。Paring Model通过机器学习算法对从UI图库中提取的特征进行训练。该模型在功能关系和空间关系两个层面决定输入组件的配对,并给出合适的布局建议。通过使用组件特征,通过机器学习算法,识别组件的类型,这些类型是输出布局层次结构的叶节点。在800个开源应用的3362个接口实例上的实验证明,该方法的平均准确率超过90%。
{"title":"User Interface Layout Recommendation Based on Pairing Model","authors":"Xiaohong Shi, Shuyi Huang, Yongsheng Rao, Xiangping Chen","doi":"10.1109/ICDH.2018.00041","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00041","url":null,"abstract":"In order to facilitate the generation of user interfaces from mockups, an approach was proposed to recommend User Interface (UI) layout based on Pairing Model. The absolute layout data of interfaces, including types, text, positions and sizes of components, are input into the model to generate layout. Paring Model is trained by machine-learning algorithms with features extracted from UI galleries. On the levels of functional and spatial relationship, the model decides pairing of input components and recommends a suitable layout. With use of component features, by machine-learning algorithms, the types of components are identified, which are the leaf nodes of the output layout hierarchy. The experiments on 3362 interface instances from 800 open source apps proved that the accuracy of the proposed approach, on average, exceeds 90%.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"2013 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128010454","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
Simulation and Circuit Realization of a Novel Symmetry Grid Multi-wing Chaotic System 一种新型对称网格多翼混沌系统的仿真与电路实现
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00031
This research paper introduces a novel symmetry grid multi-wing chaotic system, whose dynamics support periodic and chaotic as certain parameters vary. By introducing a mirror symmetry conversion-based approach in a multi-wing chaotic system, various mirror symmetry grid multi-wing chaotic attractors can be simulated. Furthermore, the improved module-based circuit designs of multi-wing chaotic attractors and mirror symmetry grid multi-wing chaotic attractors are further presented. The proposed novel mirror symmetry multi-wing chaotic attractors are very useful for deliberate generation of chaos in applications.
本文介绍了一种新的对称网格多翼混沌系统,该系统的动力学支持周期性和随参数变化的混沌特性。通过在多翼混沌系统中引入基于镜像对称转换的方法,可以模拟各种镜像对称网格多翼混沌吸引子。进一步提出了基于改进模块的多翼混沌吸引子电路设计和镜面对称网格多翼混沌吸引子电路设计。所提出的新型镜像对称多翼混沌吸引子对于在实际应用中有意产生混沌非常有用。
{"title":"Simulation and Circuit Realization of a Novel Symmetry Grid Multi-wing Chaotic System","authors":"Chaoxia Zhang, Jinxin Ruan, Qiang Chen","doi":"10.1109/ICDH.2018.00031","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00031","url":null,"abstract":"This research paper introduces a novel symmetry grid multi-wing chaotic system, whose dynamics support periodic and chaotic as certain parameters vary. By introducing a mirror symmetry conversion-based approach in a multi-wing chaotic system, various mirror symmetry grid multi-wing chaotic attractors can be simulated. Furthermore, the improved module-based circuit designs of multi-wing chaotic attractors and mirror symmetry grid multi-wing chaotic attractors are further presented. The proposed novel mirror symmetry multi-wing chaotic attractors are very useful for deliberate generation of chaos in applications.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121154409","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
Multi-parameter Estimation and Its Cramer-Rao Lower Bound for Underwater Acoustic Signal 水声信号的多参数估计及其Cramer-Rao下界
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00026
In past decades, there has been a growing interest in the research of underwater acoustic communication. Due to attenuation, low propagation speed of the sound and multipath of underwater acoustic channel, signal parameter estimation becomes challenging and significant. In this paper, a multi-parameter estimation method of underwater acoustic signal was proposed. This method can estimate the channel gain, Doppler shift and phase compensation for single carrier signal. Meanwhile, the Cramer-Rao lower bound for this estimation method was also derived.
在过去的几十年里,人们对水声通信的研究越来越感兴趣。由于声的衰减、低传播速度和水声信道的多径特性,使得信号参数估计变得具有挑战性和重要性。提出了一种水声信号的多参数估计方法。该方法可以估计单载波信号的信道增益、多普勒频移和相位补偿。同时,给出了该估计方法的Cramer-Rao下界。
{"title":"Multi-parameter Estimation and Its Cramer-Rao Lower Bound for Underwater Acoustic Signal","authors":"Liying Xie, Jinxin Ruan, Yilin Wu, Qiang Chen","doi":"10.1109/ICDH.2018.00026","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00026","url":null,"abstract":"In past decades, there has been a growing interest in the research of underwater acoustic communication. Due to attenuation, low propagation speed of the sound and multipath of underwater acoustic channel, signal parameter estimation becomes challenging and significant. In this paper, a multi-parameter estimation method of underwater acoustic signal was proposed. This method can estimate the channel gain, Doppler shift and phase compensation for single carrier signal. Meanwhile, the Cramer-Rao lower bound for this estimation method was also derived.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"427 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123404710","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
An Efficient Expansion Word Extraction Algorithm for Educational Video 一种有效的教育视频扩展词提取算法
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00032
In recent years, watching educational videos online has become an important method of learning. The research purpose of this paper is to provide an efficient method to improve learning efficiency for users watching online educational videos. It is an effective way to help users understand video content by extracting key words of concern in the video, which is also a hot issue in video analysis. This paper proposes a solution to extract the expansion words from the video to help users understand and learn terminologies. The extracted expansion words help us quickly obtain the meaning of new words by knowledge base association, and further expand the depth and breadth of video content while learning the content in video. An improved keyword extraction algorithm is proposed in this paper, which redistributes the weights of extracted keywords to improve the recall of low frequency new words or terminologies. The experimental results show that the video expansion word extraction method proposed in this paper can effectively extract the proper nouns and terminologies in the video.
近年来,在线观看教育视频已成为一种重要的学习方法。本文的研究目的是为观看在线教育视频的用户提供一种提高学习效率的有效方法。提取视频中关注的关键词是帮助用户理解视频内容的有效途径,也是视频分析中的热点问题。本文提出了一种从视频中提取扩展词的解决方案,以帮助用户理解和学习术语。提取的扩展词帮助我们通过知识库关联快速获取新词的含义,在学习视频内容的同时进一步拓展视频内容的深度和广度。本文提出了一种改进的关键词提取算法,该算法通过重新分配提取的关键词的权重来提高低频新词或术语的查全率。实验结果表明,本文提出的视频扩展词提取方法可以有效地提取视频中的专有名词和术语。
{"title":"An Efficient Expansion Word Extraction Algorithm for Educational Video","authors":"Lijie Shao, Fuwei Zhang, Ruomei Wang, Fan Zhou, Shujin Lin","doi":"10.1109/ICDH.2018.00032","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00032","url":null,"abstract":"In recent years, watching educational videos online has become an important method of learning. The research purpose of this paper is to provide an efficient method to improve learning efficiency for users watching online educational videos. It is an effective way to help users understand video content by extracting key words of concern in the video, which is also a hot issue in video analysis. This paper proposes a solution to extract the expansion words from the video to help users understand and learn terminologies. The extracted expansion words help us quickly obtain the meaning of new words by knowledge base association, and further expand the depth and breadth of video content while learning the content in video. An improved keyword extraction algorithm is proposed in this paper, which redistributes the weights of extracted keywords to improve the recall of low frequency new words or terminologies. The experimental results show that the video expansion word extraction method proposed in this paper can effectively extract the proper nouns and terminologies in the video.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127002312","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
Research and Implementation of Path Recommendation Algorithm Based on Exercise Record 基于运动记录的路径推荐算法研究与实现
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00049
The recommended algorithm is widely used in the path recommendation. In this paper, the exercise path recommendation algorithm is reported. The main factors considering in the exercise path recommendation include the frequency of path selection, starting point and ending point of exercise and the moving object. Compared with other algorithms, our path recommendation algorithm is low computation cost, and some personal factors are considered in the recommendation algorithm, the recommended path is most suitable for the individual requirement.
推荐算法在路径推荐中应用广泛。本文提出了一种运动路径推荐算法。运动路径推荐中主要考虑的因素包括运动路径选择频率、运动起点和终点以及运动对象。与其他算法相比,我们的路径推荐算法计算成本低,并且在推荐算法中考虑了一些个人因素,所推荐的路径最适合个人需求。
{"title":"Research and Implementation of Path Recommendation Algorithm Based on Exercise Record","authors":"Qiuyuan Luo, Linfa Lu, Guifeng Zheng, Jinlu Xue","doi":"10.1109/ICDH.2018.00049","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00049","url":null,"abstract":"The recommended algorithm is widely used in the path recommendation. In this paper, the exercise path recommendation algorithm is reported. The main factors considering in the exercise path recommendation include the frequency of path selection, starting point and ending point of exercise and the moving object. Compared with other algorithms, our path recommendation algorithm is low computation cost, and some personal factors are considered in the recommendation algorithm, the recommended path is most suitable for the individual requirement.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126575129","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
A Benchmark for Action Recognition of Large Animals 大型动物动作识别的基准
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00020
The action recognition of large animals plays an important role in the intelligent and modern farming. People often use the actions as the key factors to achieve scientific feeding and improve the animal welfare, and then the quality and productivity of animals are greatly promoted. However, most present action recognition methods focus on the actions of human (as pedestrian, athletes) or man-made objects (as cars, bikes). This paper proposes a benchmark to recognize and evaluate the actions of a kind of large animals namely the cows. First, we construct a dataset including 60 videos to describe the popular actions existing in the daily life of cows, and manually denote the target regions of cows on every frame in the dataset. Second, six famous trackers are evaluated on this dataset to compute the trajectory of cows which is the basis of actions recognition. Third, we define the method to recognize the actions of cows via the trajectories and validate the proposed method on our dataset. Many experiments demonstrate that our method of action recognition performs favorable in detecting the actions of cows, and the proposed dataset basically satisfies the action evaluations for farmers. The work in this paper provides an automatic and scientific method for famers to design a scheme to promote the quality and productivity of cows.
大型动物的动作识别在智能化、现代化的农业生产中起着重要的作用。人们往往把行动作为实现科学饲养和提高动物福利的关键因素,从而大大提高动物的质量和生产力。然而,目前大多数的动作识别方法都集中在人类(如行人、运动员)或人造物体(如汽车、自行车)的动作上。本文提出了一种识别和评价大型动物——奶牛行为的基准。首先,我们构建了一个包含60个视频的数据集来描述奶牛日常生活中存在的流行动作,并在数据集的每一帧上手动标记奶牛的目标区域。其次,在此数据集上评估6个著名的跟踪器,计算奶牛的运动轨迹,这是动作识别的基础。第三,我们定义了通过轨迹识别奶牛动作的方法,并在我们的数据集上验证了所提出的方法。大量实验表明,我们的动作识别方法在检测奶牛的动作方面表现良好,所提出的数据集基本满足了对农民的动作评价。本文的工作为农民设计提高奶牛质量和生产力的方案提供了一种自动化、科学的方法。
{"title":"A Benchmark for Action Recognition of Large Animals","authors":"Yun Liang, Fuyou Xue, Xiaoming Chen, Zexin Wu, Xiang Chen","doi":"10.1109/ICDH.2018.00020","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00020","url":null,"abstract":"The action recognition of large animals plays an important role in the intelligent and modern farming. People often use the actions as the key factors to achieve scientific feeding and improve the animal welfare, and then the quality and productivity of animals are greatly promoted. However, most present action recognition methods focus on the actions of human (as pedestrian, athletes) or man-made objects (as cars, bikes). This paper proposes a benchmark to recognize and evaluate the actions of a kind of large animals namely the cows. First, we construct a dataset including 60 videos to describe the popular actions existing in the daily life of cows, and manually denote the target regions of cows on every frame in the dataset. Second, six famous trackers are evaluated on this dataset to compute the trajectory of cows which is the basis of actions recognition. Third, we define the method to recognize the actions of cows via the trajectories and validate the proposed method on our dataset. Many experiments demonstrate that our method of action recognition performs favorable in detecting the actions of cows, and the proposed dataset basically satisfies the action evaluations for farmers. The work in this paper provides an automatic and scientific method for famers to design a scheme to promote the quality and productivity of cows.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124482256","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
Single Image Super-Resolution via Laplacian Information Distillation Network 基于拉普拉斯信息蒸馏网络的单幅图像超分辨率
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00012
Recently, deep convolutional neural networks (CNNS) have been revealed significant progress on single image super-resolution (SISR). Nevertheless, as the depth and width of the networks increase, CNN-based super-resolution (SR) methods have been confronted with the challenges of computational complexity and memory consumption in practice. In order to solve the above issues, we combine the Laplacian Pyramid with the previous methods to propose a convolutional neural network, which is able to reconstruct the HR image from low resolution image step by step. Our Laplacian-Pyramid structure allows each layer to share common parameters with other layers as well as its inner structure; this kind of characteristic reduces the number of parameters dramatically while still extracts sufficient features at the same time. In experiment part, we compare our method with the state-of-art methods. The results demonstrate that the proposed method is superior to the previous methods, furthermore our x2 model also gains an ideal effect.
近年来,深度卷积神经网络(cnn)在单幅图像超分辨率(SISR)方面取得了重大进展。然而,随着网络深度和宽度的增加,基于cnn的超分辨率(SR)方法在实践中面临着计算复杂度和内存消耗的挑战。为了解决上述问题,我们将拉普拉斯金字塔与之前的方法相结合,提出了一种卷积神经网络,能够从低分辨率图像中逐步重建HR图像。我们的拉普拉斯金字塔结构允许每一层与其他层共享共同的参数以及它的内部结构;这种特征极大地减少了参数的数量,同时仍然提取了足够的特征。在实验部分,我们将本方法与目前的方法进行了比较。结果表明,该方法优于以往的方法,并且我们的x2模型也获得了理想的效果。
{"title":"Single Image Super-Resolution via Laplacian Information Distillation Network","authors":"M. Cheng, Zhan Shu, Jiapeng Hu, Y. Zhang, Zhuo Su","doi":"10.1109/ICDH.2018.00012","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00012","url":null,"abstract":"Recently, deep convolutional neural networks (CNNS) have been revealed significant progress on single image super-resolution (SISR). Nevertheless, as the depth and width of the networks increase, CNN-based super-resolution (SR) methods have been confronted with the challenges of computational complexity and memory consumption in practice. In order to solve the above issues, we combine the Laplacian Pyramid with the previous methods to propose a convolutional neural network, which is able to reconstruct the HR image from low resolution image step by step. Our Laplacian-Pyramid structure allows each layer to share common parameters with other layers as well as its inner structure; this kind of characteristic reduces the number of parameters dramatically while still extracts sufficient features at the same time. In experiment part, we compare our method with the state-of-art methods. The results demonstrate that the proposed method is superior to the previous methods, furthermore our x2 model also gains an ideal effect.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116143802","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
Sparse Representation-Based Face Object Generative via Deep Adversarial Network 基于深度对抗网络的稀疏表示人脸对象生成
Pub Date : 2018-11-01 DOI: 10.1109/ICDH.2018.00019
How to generate well quality faces objects of automated processes has always been the focus on researchers. Recently, due to the deep generative networks have achieved impressive successes in data generative fields, researchers have tried to introduce deep learning into the 3d objects generate field, such as text2scene, slice-based object generate. However, the generative ability in 3D object is limited by the size of the feature space, because of computational space limitations on hardware. In this paper, we address the problem by reducing amount of calculated on process of learning, and thus generative newly different objects. The problem is intractable, since first the limiting of compute space is so hard that object can't be process in deep network due to the process need to compute many matrix multiplications. To resolve the problem, we propose a sparse representation-based method of generating well-quality faces object. Our method consists of two parts: sparse reconstruction and object generative. First, we verified the possibility of using sparse representations of 3D data by reconstructing 3D object. Second, we design a network architecture of deep adversarial network of generating new sparse representation and combined with the previous reconstruction method of generating new face object. Experiments show that our method has the ability to generate very different and well quality faces objects that contain tens of thousands of points and meshes. Our findings show that sparse representation can be used in 3D object reconstruction and generate via deep generative adversarial model.
如何生成高质量的自动化过程人脸对象一直是研究人员关注的焦点。近年来,由于深度生成网络在数据生成领域取得了令人瞩目的成功,研究人员尝试将深度学习引入到3d对象生成领域,如text2scene、基于切片的对象生成等。然而,由于硬件计算空间的限制,三维对象的生成能力受到特征空间大小的限制。在本文中,我们通过减少学习过程的计算量来解决这个问题,从而生成新的不同的对象。由于计算空间的限制,在深度网络中由于需要计算大量的矩阵乘法而无法对对象进行处理,这是一个棘手的问题。为了解决这个问题,我们提出了一种基于稀疏表示的生成高质量人脸对象的方法。我们的方法包括两个部分:稀疏重建和目标生成。首先,我们通过重建三维物体验证了使用三维数据稀疏表示的可能性。其次,我们设计了一种生成新的稀疏表示的深度对抗网络网络架构,并结合之前生成新的人脸对象的重构方法。实验表明,我们的方法能够生成包含数万个点和网格的非常不同且质量良好的人脸。我们的研究结果表明,稀疏表示可以用于三维物体重建,并通过深度生成对抗模型生成。
{"title":"Sparse Representation-Based Face Object Generative via Deep Adversarial Network","authors":"Ye Yuan, Yong Zhang, Shaofan Wang, Baocai Yin","doi":"10.1109/ICDH.2018.00019","DOIUrl":"https://doi.org/10.1109/ICDH.2018.00019","url":null,"abstract":"How to generate well quality faces objects of automated processes has always been the focus on researchers. Recently, due to the deep generative networks have achieved impressive successes in data generative fields, researchers have tried to introduce deep learning into the 3d objects generate field, such as text2scene, slice-based object generate. However, the generative ability in 3D object is limited by the size of the feature space, because of computational space limitations on hardware. In this paper, we address the problem by reducing amount of calculated on process of learning, and thus generative newly different objects. The problem is intractable, since first the limiting of compute space is so hard that object can't be process in deep network due to the process need to compute many matrix multiplications. To resolve the problem, we propose a sparse representation-based method of generating well-quality faces object. Our method consists of two parts: sparse reconstruction and object generative. First, we verified the possibility of using sparse representations of 3D data by reconstructing 3D object. Second, we design a network architecture of deep adversarial network of generating new sparse representation and combined with the previous reconstruction method of generating new face object. Experiments show that our method has the ability to generate very different and well quality faces objects that contain tens of thousands of points and meshes. Our findings show that sparse representation can be used in 3D object reconstruction and generate via deep generative adversarial model.","PeriodicalId":117854,"journal":{"name":"2018 7th International Conference on Digital Home (ICDH)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127321837","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
期刊
2018 7th International Conference on Digital Home (ICDH)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1