{"title":"Automatic inspection system for defects classification of stretch knitted fabrics","authors":"T. Su, Hua-Wei Chen, Gui-Bing Hong, Chih-Ming Ma","doi":"10.1109/ICWAPR.2010.5576302","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576302","url":null,"abstract":"Fabric defect detection and classification plays a very important role for the automatic detection in fabrics. This study refers to the four common seen defects of stretch knitted fabrics: laddering, end-out, hole, and oil spot. First of all, wavelet transfer is applied to obtain its wavelet energy to take them as defect features of this image, and then the back-propagation neural network (BPNN) was used to carry out the defects classification of the fabrics. In addition, by using the Taguchi method combined with BPNN had improved the deficiency of BPNN, which requires overly time consuming trial-and-error to find the learning parameters, and therefore could converge even faster, having an even smaller convergence error and better recognition rate. Experimental results have proven the final root-mean-square error convergence of the Taguchi-based BPNN was 0.000199, and the recognition rate can reach 96.5%.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128830490","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}
{"title":"Solution of wave-equation using multiresolution multiwavelet basis function","authors":"H. Sekino, Takumi Okamoto, S. Hamada","doi":"10.1109/ICWAPR.2010.5576390","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576390","url":null,"abstract":"Classical wave-equation is solved using Multiresolution Multiwavelet (MW) basis functions in one- and two-dimensional space. The time progression operator is represented using Cayley formalism in order to avoid instability of the solution. Stable solutions are obtained for different initial conditions.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115693780","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}
{"title":"Image match using distribution of colorful SIFT","authors":"Zeng-Shun Zhao, Qing-Ji Tian, Ji-Zhen Wang, Jian-Ming Zhou","doi":"10.1109/ICWAPR.2010.5576305","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576305","url":null,"abstract":"Finding reliable correspondence in two or more images remains a difficult and critical step in many computer vision tasks. The performance of descriptors determines the matching results directly. Compared with other descriptors, the Scale Invariant Feature Transform (SIFT) has been used widely for its superiority in invariant attributes, while it will fail in the case of locally visual aliasing. To reduce the perceptual alias of features easily confused, we propose an approach which combines a modified feature descriptor with a novel matching strategy. The feature descriptor is modified by augmenting traditional SIFT vector with dominant hue histogram. A novel matching strategy is developed to validate true matches by establishing geometrical relationships between candidate matching features. The proposed method is tested on many image pairs with viewpoint changes. Based on three instances of geometrical constraint metrics and color information, satisfactory results are attained.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"26-27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123648777","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}
{"title":"A hybrid diagnostic method based on wigner-ville distribution and wavelet packet transform","authors":"Wei Tian, Ruqiang Yan, R. Gao","doi":"10.1109/ICWAPR.2010.5576402","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576402","url":null,"abstract":"Effective machine health monitoring requires a time-frequency representation with high resolution. This paper presents a hybrid signal processing technique, based on Wavelet Packet Transform (WPT) and Wigner-Ville Distribution (WVD). It allows high resolution without introducing the cross-term interference as the original WVD method does. The suitability of applying this method is shown by both simulation and experiments.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121858049","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}
Zhihua Xie, Guodon Liu, Shi-Qian Wu, Zhijun Fang, Gan Yun
{"title":"A novel infrared face recognition method in DCT domain","authors":"Zhihua Xie, Guodon Liu, Shi-Qian Wu, Zhijun Fang, Gan Yun","doi":"10.1109/ICWAPR.2010.5576458","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576458","url":null,"abstract":"A novel infrared face recognition method using blood perfusion conversion and DCT is proposed in this paper. Firstly, the blood perfusion image instead of thermal image is used to get the stable biological features. Secondly, due to the low-resolution of the infrared images, the feature extraction method (Linear Discriminative Analysis in DCT domain) is chosen to get the principle features in the blood perfusion image, which is suitable for real-time application. A new feature selection algorithm in DCT domain is applied to lessen the small sample problem of LDA. The experiments illustrate that the feature selection algorithm in DCT domain is effective in getting the discriminant features and the proposed method has better performance compared with the traditional DCT and LDA method.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"340 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114506497","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}
{"title":"Ground deformation detection along Beijing-Tianjin intercity railway using advanced network multi-baseline DInSAR","authors":"Hong Zhang, L. Tao, Chao Wang, Yixian Tang","doi":"10.1109/ICWAPR.2010.5576333","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576333","url":null,"abstract":"Recent years, the application of multi-baseline DInSAR was primarily possible in the case of slow ground movements. In this paper, the application of Beijing-Tianjin intercity railway roadbed deformation monitoring based on multi-baselines DInSAR is present. To enable this, the advanced network algorithm is adapted for pixels linking. Our study is based on 15 ALOS PALSAR images during one-year period of 2008–2009. The results of current study indicate that the cumulate subsidence along most of the roadbed is about 0–10mm, which means the roadbed is relative stable during the first year running of the intercity railway.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116721213","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}
{"title":"Injector waveform analysis and engine fault diagnosis based on frequency space subdivision in wavelet transform","authors":"Shuxia Jiang, Yuanyuan Liu","doi":"10.1109/ICWAPR.2010.5576369","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576369","url":null,"abstract":"Although traditional waveform analysis in time domain plays an important role in realizing engine non-disintegration fault diagnosis, this method fails to make an accurate fault diagnosis when fault waveform and normal waveform are very close. To solve this problem, a new method based on frequency space subdivision (FSS) in wavelet transform (WT) is proposed and applied in this paper. Meanwhile, a processing approach of engine data stream is introduced, which makes further waveform analysis possible. This method is applied to an injector-pulse-width waveform analysis. As for the No. 12 fault analysis, firstly a biorthogonal wavelet base with good characteristics is selected, then three-layer wavelet decomposition is used to analyze injector-pulse-width in both time domain and frequency domain, and finally the accurate fault band is located through calculation of the sum of the difference between fault and normal wavelet coefficients. The result obtains that the fault comes from the oxygen sensor, which is completely coincident with the experimental fault hypothesis. Injector-pulse-width waveform of No.1, 8, 11 and 19 faults are also analyzed similarly. The results show that the proposed waveform analysis method improves the accuracy of the engine fault diagnosis. This method provides a supplement for the known non-disintegration engine fault diagnosis and supplies a good reference for fault diagnosis of the other large machines.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"200 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123005606","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}
{"title":"The reproducing kernel Hilbert space based on wavelet transform","authors":"Caixia Deng, Shuai Li, Zuoxian Fu","doi":"10.1109/ICWAPR.2010.5576389","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576389","url":null,"abstract":"In this paper, the explicit and analytic expression of the reproducing kernel function for the image space of the wavelet transform is obtained based on the fact that the image space of wavelet transform is a reproducing kernel Hilbert space. Here we describe in detail the reproducing kernel and structure of this space when the scale factor is fixed. This provides the theoretic basis for discussing the image space of general wavelet transform and broadens the scope of application of the reproducing kernel space theories.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131115308","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}
{"title":"Visualization of multi-cahnnel vital data at engine idling based on wavelet analysis","authors":"Toru Yamamoto, Seiichi Shin","doi":"10.1109/ICWAPR.2010.5576393","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576393","url":null,"abstract":"This paper presents an analysis and a visualization method of vital signals of a passenger, during engine idling. The idling signal is analyzed and suppressed in order to detect a pulse caused by heartbeats and make them visible by wavelet analysis. The measured vital signal is contaminated with an engine idling signal, and it is needed to be separated in a time-frequency band by using wavelet transformation. This paper also proposes a visualization method of 18 channel vital signals with wavelet analysis. An experiment result shows effectiveness of the proposing analysis and method.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121457102","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}
{"title":"Location of 2-Dim code in image by corner detection","authors":"Ping Wang, Jinyi Hou","doi":"10.1109/ICWAPR.2010.5576430","DOIUrl":"https://doi.org/10.1109/ICWAPR.2010.5576430","url":null,"abstract":"We report on the development and implementation of a robust algorithm for extracting 2-Dim code Area in video images. The algorithm concludes two main steps, firstly, convert the RGB images into gray-scale images and location the point of max local radio in the gray image. These points are so-called corner points. Secondly we used the points to clustering and the results of the clustering can be used to find one area that conform the shape of a 2-Dim code area. The experiment results shows that 2-Dim code area in the 2-Dim code images with rectangle or circle element, bad contrast in illumination or with adjacent noise in the image could be find correctly.","PeriodicalId":219884,"journal":{"name":"2010 International Conference on Wavelet Analysis and Pattern Recognition","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127563132","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}