Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521329
H. Omura, Teruya Minamoto
A new feature extraction method based on the wavelets and persistent homology for early esophageal cancer detection from an endoscopic image is proposed. In our proposed method, an input endoscopic image is converted to CIE L*a*b* color spaces, and a fusion image is made from the a* and b* components. Applying the two types of wavelets to the fusion image, the two types of frequency components are obtained. One is the low frequency component obtained by the dyadic wavelet transform (DYWT), and the other is the high frequency components obtained by the dual-tree complex discrete wavelet transform (DT-CDWT). Applying the dynamic threshold to each frequency component, binary images are obtained, and then each binary image is divided into small blocks. Utilizing the persistent homology to each block, the new features of the input image are acquired. The method to extract the feature is described in detail, and experimental results are presented to demonstrate that our method is useful for the development of early esophageal cancer detection from endoscopic image.
{"title":"Feature Extraction Based on the Wavelets and Persistent Homology for Early Esophageal Cancer Detection From Endoscopic Image","authors":"H. Omura, Teruya Minamoto","doi":"10.1109/ICWAPR.2018.8521329","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521329","url":null,"abstract":"A new feature extraction method based on the wavelets and persistent homology for early esophageal cancer detection from an endoscopic image is proposed. In our proposed method, an input endoscopic image is converted to CIE L*a*b* color spaces, and a fusion image is made from the a* and b* components. Applying the two types of wavelets to the fusion image, the two types of frequency components are obtained. One is the low frequency component obtained by the dyadic wavelet transform (DYWT), and the other is the high frequency components obtained by the dual-tree complex discrete wavelet transform (DT-CDWT). Applying the dynamic threshold to each frequency component, binary images are obtained, and then each binary image is divided into small blocks. Utilizing the persistent homology to each block, the new features of the input image are acquired. The method to extract the feature is described in detail, and experimental results are presented to demonstrate that our method is useful for the development of early esophageal cancer detection from endoscopic image.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"35 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":"125893173","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521279
Junyuli, Haoliang Yuan, L. L. Lai, Houqing Zheng, W. Qian, Xiaoming Zhou
It is common to perform feature selection for pattern recognition and image processing. However, most of conventional methods often convert the image matrix into a vector for feature selection, which fails to consider the spatial location of image. To address this issue, we propose a graph-based sparse matrix regression for feature selection on matrix. We incorporate a graph regularization term into the objective function of the sparse matrix regression model. The role of this graph structure is to make the matrix samples sharing the same labels keep close together in the transformed space. Extensive experimental results can demenstrate the effectiveness of our proposed method.
{"title":"Graph-Based Sparse Matrix Regression for 2D Feature Selection","authors":"Junyuli, Haoliang Yuan, L. L. Lai, Houqing Zheng, W. Qian, Xiaoming Zhou","doi":"10.1109/ICWAPR.2018.8521279","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521279","url":null,"abstract":"It is common to perform feature selection for pattern recognition and image processing. However, most of conventional methods often convert the image matrix into a vector for feature selection, which fails to consider the spatial location of image. To address this issue, we propose a graph-based sparse matrix regression for feature selection on matrix. We incorporate a graph regularization term into the objective function of the sparse matrix regression model. The role of this graph structure is to make the matrix samples sharing the same labels keep close together in the transformed space. Extensive experimental results can demenstrate the effectiveness of our proposed method.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","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":"124740552","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521274
Junjie Zheng, Haoliang Yuan, L. L. Lai, Houqing Zheng, Zhimin Wang, Fenghua Wang
Feature selection has obtained dramatic attentions in the recent years. In this paper, we propose a semi-supervised graph learning robust feature selection model (SGL-RFS). Our method can merge the procedures of sparse regression and graph construction as a whole to learn an optimal sparse regression matrix for feature selection. To solve our propose method, we also develop an effective alternating optimization algorithm. Experimental results on face and digit databases confirm the effectiveness of our proposed method.
{"title":"SGL-RFS: Semi-Supervised Graph Learning Robust Feature Selection","authors":"Junjie Zheng, Haoliang Yuan, L. L. Lai, Houqing Zheng, Zhimin Wang, Fenghua Wang","doi":"10.1109/ICWAPR.2018.8521274","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521274","url":null,"abstract":"Feature selection has obtained dramatic attentions in the recent years. In this paper, we propose a semi-supervised graph learning robust feature selection model (SGL-RFS). Our method can merge the procedures of sparse regression and graph construction as a whole to learn an optimal sparse regression matrix for feature selection. To solve our propose method, we also develop an effective alternating optimization algorithm. Experimental results on face and digit databases confirm the effectiveness of our proposed method.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"16 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":"123330489","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521325
Wing W. Y. Ng, Si-chao Lei, Xing Tian
Hashing-based approximated nearest neighbor (ANN) search techniques have been widely studied owing to its compact binary codes and efficient search scheme for large-scale image retrieval. For the most popular existing hashing methods, e.g. the Locality sensitivity Hashing and the Spectral Hashing, the key issue is to choose appropriate binary code length for similarity preserving and computational efficiency. Several extensions have been proposed to address the problem of balancing precision, recall rate and computation efficiency. However, most of existing hashing methods struggle for how to choose appropriate length of hash codes. A bad choice of code length may result in extremely poor performance of retrieval. In this paper, we propose a novel hashing scheme, called the Two-Layer Localized Sensitive Hashing with Adaptive Reranking (TL-LSHAR). This method utilizes a short hash code to generate the weights for a long hash code to further improve the retrieval performance. Moreover, the new scheme can be used by most of the existing hashing methods. The performance is evaluated on two large scale image databases which demonstrates the efficiency of our scheme.
{"title":"Two-Layer Localized Sensitive Hashing with Adaptive Re-Ranking","authors":"Wing W. Y. Ng, Si-chao Lei, Xing Tian","doi":"10.1109/ICWAPR.2018.8521325","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521325","url":null,"abstract":"Hashing-based approximated nearest neighbor (ANN) search techniques have been widely studied owing to its compact binary codes and efficient search scheme for large-scale image retrieval. For the most popular existing hashing methods, e.g. the Locality sensitivity Hashing and the Spectral Hashing, the key issue is to choose appropriate binary code length for similarity preserving and computational efficiency. Several extensions have been proposed to address the problem of balancing precision, recall rate and computation efficiency. However, most of existing hashing methods struggle for how to choose appropriate length of hash codes. A bad choice of code length may result in extremely poor performance of retrieval. In this paper, we propose a novel hashing scheme, called the Two-Layer Localized Sensitive Hashing with Adaptive Reranking (TL-LSHAR). This method utilizes a short hash code to generate the weights for a long hash code to further improve the retrieval performance. Moreover, the new scheme can be used by most of the existing hashing methods. The performance is evaluated on two large scale image databases which demonstrates the efficiency of our scheme.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","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":"125987266","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521394
M. Bahri, R. Ashino
The uncertainty principles can be regarded as generalization of the uncertainty principles on complex Hilbert space. By applying the linear operators, it is shown that the right-sided quaternion Fourier transform is a unitary operator. The duality property of the right-sided quaternion Fourier transform which enables us to express the alternative form of the Hausdorff-Young inequality associated with the right-sided quaternion Fourier transform is presented. AMS Subject Classification: 11R52, 42A38, 15A66
{"title":"Some Useful Results Associated with Right-Sided Quaternion Fourier Transform","authors":"M. Bahri, R. Ashino","doi":"10.1109/ICWAPR.2018.8521394","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521394","url":null,"abstract":"The uncertainty principles can be regarded as generalization of the uncertainty principles on complex Hilbert space. By applying the linear operators, it is shown that the right-sided quaternion Fourier transform is a unitary operator. The duality property of the right-sided quaternion Fourier transform which enables us to express the alternative form of the Hausdorff-Young inequality associated with the right-sided quaternion Fourier transform is presented. AMS Subject Classification: 11R52, 42A38, 15A66","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"81 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":"134389745","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521305
Weili Ding, Xinming Wang, Han Liu, Bo Hu
Shape recognition has been a popular application of machine learning, where each shape is defined as a class for training classifiers that recognize the shapes of new instances. Since training of classifiers is essentially achieved through learning from features, it is crucial to extract and select a set of relevant features that can effectively distinguish one class from other classes. However, different instances could present features which are highly dissimilar, even if these instances belong to the same class. The above difference in feature representation can also result in high diversity among classifiers trained by using different algorithms or data samples. In this paper, we investigate the impact of multi-classifier fusion on shape recognition by using six features extracted from a 2D shape data set. In particular, popular single learning algorithms, such as Decision Trees, Support Vector Machine and K Nearest Neighbours, are adopted to train base classifiers on features selected by using a wrapper approach. Furthermore, two popular ensemble learning algorithms (Random Forests and Gradient Boosted Trees) are adopted to train decision tree ensembles on the same feature sets. The outputs of the two ensemble classifiers are finally combined with the outputs of all the other base classifiers The experimental results show the effectiveness of the above setting of multi-classifier fusion for advancing the performance in comparison with using each single (non-ensemble) learning algorithm.
{"title":"An Empirical Study of Shape Recognition in Ensemble Learning Context","authors":"Weili Ding, Xinming Wang, Han Liu, Bo Hu","doi":"10.1109/ICWAPR.2018.8521305","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521305","url":null,"abstract":"Shape recognition has been a popular application of machine learning, where each shape is defined as a class for training classifiers that recognize the shapes of new instances. Since training of classifiers is essentially achieved through learning from features, it is crucial to extract and select a set of relevant features that can effectively distinguish one class from other classes. However, different instances could present features which are highly dissimilar, even if these instances belong to the same class. The above difference in feature representation can also result in high diversity among classifiers trained by using different algorithms or data samples. In this paper, we investigate the impact of multi-classifier fusion on shape recognition by using six features extracted from a 2D shape data set. In particular, popular single learning algorithms, such as Decision Trees, Support Vector Machine and K Nearest Neighbours, are adopted to train base classifiers on features selected by using a wrapper approach. Furthermore, two popular ensemble learning algorithms (Random Forests and Gradient Boosted Trees) are adopted to train decision tree ensembles on the same feature sets. The outputs of the two ensemble classifiers are finally combined with the outputs of all the other base classifiers The experimental results show the effectiveness of the above setting of multi-classifier fusion for advancing the performance in comparison with using each single (non-ensemble) learning algorithm.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"115 23","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131747489","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521257
H. Toda, Zhong Zhang
We have already proposed an orthonormal wavelet basis having an arbitrary real dilation. However, when its dilation is an irrational number, it is very difficult to calculate its transform and inverse transform because of its infinite number of wavelet shapes and its irrational distances between wavelets. In this paper, based on the decomposition and reconstruction algorithms, we propose a calculation method of its transform and inverse transform.
{"title":"Irrational-Dilation Orthonormal Wavelet Basis and its Calculation Method","authors":"H. Toda, Zhong Zhang","doi":"10.1109/ICWAPR.2018.8521257","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521257","url":null,"abstract":"We have already proposed an orthonormal wavelet basis having an arbitrary real dilation. However, when its dilation is an irrational number, it is very difficult to calculate its transform and inverse transform because of its infinite number of wavelet shapes and its irrational distances between wavelets. In this paper, based on the decomposition and reconstruction algorithms, we propose a calculation method of its transform and inverse transform.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"143 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":"133126790","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521271
Ting Shu, Bob Zhang, Yuanyan Tang
A Computer-assisted Non-invasive Diabetes Mellitus Detection System through facial key block analysis is designed and developed in this paper. There are four main steps in our system: facial image capture through a non-invasive device, automatic location of the key blocks based on the positions of the two pupils, key block texture feature extraction using Local Binary Pattern with cell-size 21, and classification with Support Vector Machines. In the first step of this system, a specially designed facial image capture device has been developed to capture the facial image of each patient in a standard designed environment. According to Traditional Chinese Medicine theory, various facial regions can reflect the health status of different inner organs. Based on this, four key blocks are located automatically using the positions of the two pupils and used in Diabetes Mellitus detection instead of employing the whole facial image. For the last two steps, an experiment which selects the best value of Local Binary Pattern cell-size and the better classifier of two traditional classifiers (k-Nearest Neighbors and Support Vector Machines) is implemented and its results are applied in this system. In order to test the system performance, the facial images of 200 volunteers consisting of 100 Diabetes Mellitus patients and 100 healthy persons are captured and analyzed through this system. Based on the test result, the Computer-assisted Non-invasive Diabetes Mellitus Detection System through facial key block analysis is proven to be effective and efficient at distinguishing Diabetes Mellitus from Healthy patients in real time.
{"title":"Computer-Assisted Non-Invasive Diabetes Mellitus Detection System via Facial Key Block Analysis","authors":"Ting Shu, Bob Zhang, Yuanyan Tang","doi":"10.1109/ICWAPR.2018.8521271","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521271","url":null,"abstract":"A Computer-assisted Non-invasive Diabetes Mellitus Detection System through facial key block analysis is designed and developed in this paper. There are four main steps in our system: facial image capture through a non-invasive device, automatic location of the key blocks based on the positions of the two pupils, key block texture feature extraction using Local Binary Pattern with cell-size 21, and classification with Support Vector Machines. In the first step of this system, a specially designed facial image capture device has been developed to capture the facial image of each patient in a standard designed environment. According to Traditional Chinese Medicine theory, various facial regions can reflect the health status of different inner organs. Based on this, four key blocks are located automatically using the positions of the two pupils and used in Diabetes Mellitus detection instead of employing the whole facial image. For the last two steps, an experiment which selects the best value of Local Binary Pattern cell-size and the better classifier of two traditional classifiers (k-Nearest Neighbors and Support Vector Machines) is implemented and its results are applied in this system. In order to test the system performance, the facial images of 200 volunteers consisting of 100 Diabetes Mellitus patients and 100 healthy persons are captured and analyzed through this system. Based on the test result, the Computer-assisted Non-invasive Diabetes Mellitus Detection System through facial key block analysis is proven to be effective and efficient at distinguishing Diabetes Mellitus from Healthy patients in real time.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"6 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":"123632392","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}
Pub Date : 2018-07-01DOI: 10.1109/ICWAPR.2018.8521284
Zhongwen Qian, Fenghua Wang, Wanli Wu, Jingzhou Cheng, Yue Wang, Fangyuan Xu, L. Lai
Causing Reason Locating (CRL) is a negative going decision making process. It provides specific individual causing reasons to events or abnormal variation so that decision maker can find out clear-cut points for updates or maintenance. Traditional CRL is usually implemented with self-correlation analysis on Value Comparable Data (VCD). Property Data (PD) is not covered in CRL for its nominal evaluations. This paper initiates a new scheme for PD data correlation analysis, including virtual data creation method and correlation balancing method for Kendall correlation computation. A numerical study is implemented for model support on equipment retire analysis.
{"title":"Self-Correlation Analysis Framework with Property Data in Master Data Management — A Case on Power Utility Equipment Retire Analysis","authors":"Zhongwen Qian, Fenghua Wang, Wanli Wu, Jingzhou Cheng, Yue Wang, Fangyuan Xu, L. Lai","doi":"10.1109/ICWAPR.2018.8521284","DOIUrl":"https://doi.org/10.1109/ICWAPR.2018.8521284","url":null,"abstract":"Causing Reason Locating (CRL) is a negative going decision making process. It provides specific individual causing reasons to events or abnormal variation so that decision maker can find out clear-cut points for updates or maintenance. Traditional CRL is usually implemented with self-correlation analysis on Value Comparable Data (VCD). Property Data (PD) is not covered in CRL for its nominal evaluations. This paper initiates a new scheme for PD data correlation analysis, including virtual data creation method and correlation balancing method for Kendall correlation computation. A numerical study is implemented for model support on equipment retire analysis.","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"49 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":"123641474","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}
Pub Date : 2018-07-01DOI: 10.1109/icwapr.2018.8521322
{"title":"Proceedings of 2018 International Conference on Wavelet Analysis and Pattern Recognition","authors":"","doi":"10.1109/icwapr.2018.8521322","DOIUrl":"https://doi.org/10.1109/icwapr.2018.8521322","url":null,"abstract":"","PeriodicalId":385478,"journal":{"name":"2018 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR)","volume":"104 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":"126372885","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：