发布求助
文献互助 智能选刊 最新文献

2018 International Conference on Audio, Language and Image Processing (ICALIP)最新文献

筛选
英文 中文
A Novel Automatic Image Stitching Algorithm for Ceramic Microscopic Images 一种新的陶瓷显微图像自动拼接算法
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455766
Kaiyue Li, G. Ding
{"title":"A Novel Automatic Image Stitching Algorithm for Ceramic Microscopic Images","authors":"Kaiyue Li, G. Ding","doi":"10.1109/ICALIP.2018.8455766","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455766","url":null,"abstract":"The polyphase ceramic images taken by electron microscope contain rich material science information. However, in practical scientific engineering, the researchers can only obtain a small part material image by microscope. Therefore, it is necessary to apply image stitching technology to obtain full-size, information-rich images. To solve this problem, this paper proposes a novel automatic image stitching algorithm for ceramic microscopic images. Firstly, an algorithm for sorting out-ordered ceramic images into ordered sequences was proposed, which is based on local matching relationship and specific threshold. Next, an image stitching algorithm based on Principal Component Analysis (PCA) and Speeded Up Robust Feature (SURF) was proposed to get the complete image. The experimental result shows that the proposed method is more feasible and effective than traditional Scale Invariant Feature Transform (SIFT).","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115132366","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
Precision Landing System on H-Octocopter Drone Using Complementary Filter 基于互补滤波的八旋翼无人机精确着陆系统
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455553
Karisma Trinanda Putra, Rama Okta Wiyagi, Muhamad Yusvin Mustar
{"title":"Precision Landing System on H-Octocopter Drone Using Complementary Filter","authors":"Karisma Trinanda Putra, Rama Okta Wiyagi, Muhamad Yusvin Mustar","doi":"10.1109/ICALIP.2018.8455553","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455553","url":null,"abstract":"An automatic landing system is required on a long-range drone because the position of the vehicle cannot be reached visually by the pilot. The autopilot system must be able to correct the drone movement dynamically in accordance with its flying altitude. The current article describes autopilot system on an H-Octocopter drone using image processing and complementary filter. This paper proposes a new approach to reduce oscillations during the landing phase on a big drone. The drone flies above 10 meters to a provided coordinate using GPS data, to check for the existence of the landing area. This process is done visually using the camera. PID controller is used to correct the movement by calculate error distance detected by camera. The controller also includes altitude parameters on its calculations through a complementary filter. The controller output is the PWM signals which control the movement and altitude of the vehicle. The signal then transferred to Flight Controller through serial communication, so that, the drone able to correct its movement. From the experiments, the accuracy is around 0.56 meters and it can be done in 18 seconds.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123286115","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: 5
Square Root Based Activation Function in Neural Networks 神经网络中基于平方根的激活函数
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455590
Xiaoyu Yang, Yufei Chen, Haiquan Liang
{"title":"Square Root Based Activation Function in Neural Networks","authors":"Xiaoyu Yang, Yufei Chen, Haiquan Liang","doi":"10.1109/ICALIP.2018.8455590","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455590","url":null,"abstract":"Activation function plays an important role in the construction of a neural network. Existing methods such as S-type and Rectified-type activation function have many deficiencies in terms of robustness, which always leads to the problem of gradient diffusion and causes the collapse of the neural network. To address these drawbacks, a more robust approach is proposed that activates levels of the neural network by using square root function (SQRT) as the activation function. Utilizing its characteristics of broad safety margin, symmetrical output center and adaptive data range, the method reduces the risk of encountering gradient diffusion for neural networks in training and applications, and decreases the possibility of the neural network collapse. Experiments are carried out to demonstrate the effectiveness and efficiency of the proposed method. It can achieve average 99.6% accuracy in image classification, higher than 94.7% of Tanh function and 68.3% of Relu function under the same conditions. Moreover, our method has low requirements on initialization, fast convergence rate, better stability after convergence, and adaptive global optimal seeking so as to can get rid of the local optimal solution of the neural network.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125543520","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: 5
Friend Recommendation in Online Social Networks Combining Interest Similarity and Social Interaction 结合兴趣相似性和社会互动的在线社交网络好友推荐
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455483
Mingqing Huang, Bofeng Zhang, Guobing Zou, Shulin Cheng, Zhuocheng Zhou, Furong Chang
{"title":"Friend Recommendation in Online Social Networks Combining Interest Similarity and Social Interaction","authors":"Mingqing Huang, Bofeng Zhang, Guobing Zou, Shulin Cheng, Zhuocheng Zhou, Furong Chang","doi":"10.1109/ICALIP.2018.8455483","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455483","url":null,"abstract":"With the explosive popularity of online social networks (OSNs), the considerably large number of online users and their diverse activities have posed great challenges on social recommendation. However, most conventional methods for recommending friends in OSNs cannot simultaneously satisfy the requirements of accuracy and timeliness. By taking full advantage of latent Dirichlet allocation (LDA), in this study, we designed a friend recommendation approach combining interest-based features and interaction-based topologies with linear time complexity. The experimental results obtained using a real-world micro-blogging network demonstrated that the proposed hybrid scheme outperforms the other three state-of-the-art algorithms in terms of effectiveness and efficiency.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122366420","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
Pitch and Mode Recognition of Humming Melodies 哼唱旋律的音高和调式识别
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455558
Tiansheng Huang, Yibiao Yu
{"title":"Pitch and Mode Recognition of Humming Melodies","authors":"Tiansheng Huang, Yibiao Yu","doi":"10.1109/ICALIP.2018.8455558","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455558","url":null,"abstract":"The pitch and mode recognition of the humming melody is an important guarantee for humming music retrieval and automatic transcription. In view of the character that the pitches of humming melody are understandard and unstable, based on the pitch extraction in the cepstrum domain, this paper recognizes the humming pitches and gets the note sequence by detecting the stable ranges of the extracted fundamental frequencies above all. Then, the mode of the note sequence is recognized according to the features of the 24 tonalities and the result of the tonic detection. Experiments show that the method proposed in this paper can effectively achieve the pitch and mode recognition of the humming melody.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"18 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114069121","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
Named Entity Recognition Among Chinese MicroBlog Based on Cascaded CRF 基于级联CRF的中文微博命名实体识别
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455248
Yixue Xing, Yonghua Zhu, Ke Zhang, Shenkai Liu, Jin Zhou
{"title":"Named Entity Recognition Among Chinese MicroBlog Based on Cascaded CRF","authors":"Yixue Xing, Yonghua Zhu, Ke Zhang, Shenkai Liu, Jin Zhou","doi":"10.1109/ICALIP.2018.8455248","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455248","url":null,"abstract":"There are several features in the content of microblog, including brief, flexible, too colloquial, too much noise caused by informality terms (abbreviations, cyber words), etc. These features are new challenges for named entity recognition. In this paper, a modified method based on cascade conditional random field (CRF) is presented to address the challenge. First of all, we preprocessed the captured microblog text to basic corpus, then we manually built common name, toponym and organization database. A sliding window was set to extract the world feature, sentence feature and context feature of the text, then we established atomic templates and fabricated templates to train cascaded CRF model. Finally, an active learning algorithm based on minimum confidence was adopted to enhance the training effect of the model. This method has been verified in People's Daily labeled corpus and microblog corpus. Experimental data show that our method has achieved outstanding experiment effect compared with the traditional CRF method, the precision, recall and F-value are all improved.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130024525","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
Automatic Colorization of Images from Chinese Black and White Films Based on CNN 基于CNN的中国黑白胶片图像自动上色
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455654
Yu Chen, Y. Luo, Youdong Ding, Ting Yu
{"title":"Automatic Colorization of Images from Chinese Black and White Films Based on CNN","authors":"Yu Chen, Y. Luo, Youdong Ding, Ting Yu","doi":"10.1109/ICALIP.2018.8455654","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455654","url":null,"abstract":"The colorization of black and white films was a hot topic in the 1980s. Some black-and-white movies regained their luster through colorization. Although people are controversial about the artistic value of film colorization, it is no doubt that color images can enhance visual effects. Inspired by the recent colorization methods using deep learning, we propose a novel colorization model which combines two Convolutional Neural Networks and uses multi-scale convolution kernels to get better spatial consistency. Most of the current datasets used in the colorization networks are not applicable to colorizing images from Chinese black and white films. The main reason is that the objects in these films are very different from today's. To address this, we extract a large number of images from Chinese color films of the last century as a training dataset. Experiments demonstrate that our model can obtain pretty good results of colorizing images from Chinese black and white films.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130255377","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: 11
Domain Adaptation for Gaussian Process Classification 高斯过程分类的域自适应
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455721
Kai Yang, W. Wan, Jie Lu
{"title":"Domain Adaptation for Gaussian Process Classification","authors":"Kai Yang, W. Wan, Jie Lu","doi":"10.1109/ICALIP.2018.8455721","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455721","url":null,"abstract":"Traditional machining learning method aims at using the labeled data or unlabeled data to train a mathematic model then it can be used to predict the unlabeled data for Data mining problem, but it requires that the data which be trained should have same distribution with the predicting data. For the real world datasets, it is hard to get enough training datasets which has the same distribution. Thus, how to train a good mathematic model by using different distribution data is crucial problem, and the researchers using the probability view to solve transfer classification problem is relative less. In this paper, we propose a transfer classification algorithm based on the Gaussian Process model, which can be used to solve the homogeneous transfer classification problem. We use the probability theory to propose a novel classification transfer learning model based on the Gaussian Process (GP) model. We experiment on the synthetic and realworld datasets and compare to other method, the result has verified the effectiveness of our approach.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127374037","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
The Speed Improvement by Merging Batch Normalization into Previously Linear Layer in CNN 将批处理归一化合并到CNN前线性层的速度提高
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455587
Jie Duan, Ruixin Zhang, Jiahu Huang, Qiuyu Zhu
{"title":"The Speed Improvement by Merging Batch Normalization into Previously Linear Layer in CNN","authors":"Jie Duan, Ruixin Zhang, Jiahu Huang, Qiuyu Zhu","doi":"10.1109/ICALIP.2018.8455587","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455587","url":null,"abstract":"With the development of deep learning, the convolutional neural network is developing more deeply, which undoubtedly has considerable requirements for the calculative ability and storage capacity of the application environment. In order to get a better use of convolutional neural networks in mobile phones, embedded platforms and other platforms with limited calculative ability, this paper proposes to accelerate the neural network by integrating the Batch Normalization and previously Linear layers and analyzes the feasibility theoretically. The experimental results on the CPU, GPU and Raspberry Pi validate the effectiveness of this method. The experiments using Caffe framework show that the merging of Batch Normalization and previously linear layers can increase the speed of the neural network by 30% to 50%.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125597282","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: 8
Methods to Test Integrity of Train Components 列车部件完整性测试方法
2018 International Conference on Audio, Language and Image Processing (ICALIP) Pub Date : 2018-07-01 DOI: 10.1109/ICALIP.2018.8455408
Zhang Shao-yang, Xie Guan-Xing, Li Yue
{"title":"Methods to Test Integrity of Train Components","authors":"Zhang Shao-yang, Xie Guan-Xing, Li Yue","doi":"10.1109/ICALIP.2018.8455408","DOIUrl":"https://doi.org/10.1109/ICALIP.2018.8455408","url":null,"abstract":"To address concerns regarding component integrity and safety detection of trains, and the efficiency of this process, an automated system for train component integrity is proposed. First, the collected images are preprocessed to eliminate image noise. The component position is automatically matched to a pre-established part template. Then the component image is developed using the algorithm of multi-point automatic seed growth. Then, the abnormal region is judged based on the growth condition, where the difference region of the contour feature is analyzed to determine whether the component is intact. The experiment tested the integrity of thirty locations requiring detection in ten images. The detection accuracy for some types of components, such as the iron chain and the tail pipe, exceeded 95%.","PeriodicalId":241122,"journal":{"name":"2018 International Conference on Audio, Language and Image Processing (ICALIP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116716152","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
小红书