- Home
- feature extraction
Author: Yu Jijiang
Abstract: Based on Bayesian methods,which can recognize road quickly and perfectly,the article proposes a road detection method.The bitmap image is divided into roads,sky,and trees with the use of color information;and the RGB values of each pixel are extracted in ...
Abstract: Based on Bayesian methods,which can recognize road quickly and perfectly,the article proposes a road detection method.The bitmap image is divided into roads,sky,and trees with the use of color information;and the RGB values of each pixel are extracted in ...
Author: Fu Dongmei Wang Wentao
Abstract: RANSAC is a robustness estimate algorithm,always used in visible light images matching.In this paper,it is used in infrared images matching,and as the infrared images have low definition and lack of texture information,a subarea RANSAC matching algorithm ...
Abstract: RANSAC is a robustness estimate algorithm,always used in visible light images matching.In this paper,it is used in infrared images matching,and as the infrared images have low definition and lack of texture information,a subarea RANSAC matching algorithm ...
Author: ZHANG Zhen-Sheng, ZHU Ming-Ri,
Abstract: Based on the characteristics of sucrose-crystallizing images in the sugar-boiling process,this paper uses a method called color space conversion which changes the images from RGB color space into HIS color space,and makes use of the relative independence ...
Abstract: Based on the characteristics of sucrose-crystallizing images in the sugar-boiling process,this paper uses a method called color space conversion which changes the images from RGB color space into HIS color space,and makes use of the relative independence ...
Author: CHEN Wen-hao , FANG Yu-chun ,
Abstract: In this paper, we propose a parallel computing technique for content-based image retrieval （CBIR） system. This technique is mainly used for single node with multi-core processor, which is different from those based on cluster or network computing architec...
Abstract: In this paper, we propose a parallel computing technique for content-based image retrieval （CBIR） system. This technique is mainly used for single node with multi-core processor, which is different from those based on cluster or network computing architec...
Author: WEI Li-guo , ZHANG Xiao-chao ,
Abstract: The birdsong research and analysis methods are important to develop ornithological study. The FFT analysis, spectrographic analysis, Mel-cepstrum and principal components analysis are introduced in the paper, together with explanations of the birdsong fea...
Abstract: The birdsong research and analysis methods are important to develop ornithological study. The FFT analysis, spectrographic analysis, Mel-cepstrum and principal components analysis are introduced in the paper, together with explanations of the birdsong fea...
Author: WANG Hong-yong,LIAO Hai-bin,DU
Abstract: In order to recognize face quickly and accurately,a weighted adaptive algorithm based on the conjunction of partial and entire features is proposed.Global features and local features of six key parts of face are extracted respectively by singular value to...
Abstract: In order to recognize face quickly and accurately,a weighted adaptive algorithm based on the conjunction of partial and entire features is proposed.Global features and local features of six key parts of face are extracted respectively by singular value to...
Author: XU Hua, WU Qiang, ZHANG Xiao-l
Abstract: The formation and visualization of underwater streamline can help to improve the efficiency of numerical simulation during post processing stage.In the paper,the aim of this study is to simulate the continuous streamline in the groundwater seepage field.T...
Abstract: The formation and visualization of underwater streamline can help to improve the efficiency of numerical simulation during post processing stage.In the paper,the aim of this study is to simulate the continuous streamline in the groundwater seepage field.T...
Author: HAN Long, GUO Li
Abstract: Video panorama was generated by moving camera. Because of the temporal redundancy in video and misregistration in the large angle rotation, many existing algorithms perform poorly. To solve these challenging situation, this paper proposed an parallel synt...
Abstract: Video panorama was generated by moving camera. Because of the temporal redundancy in video and misregistration in the large angle rotation, many existing algorithms perform poorly. To solve these challenging situation, this paper proposed an parallel synt...
Author: SHANG Li, CHENJie, ZHANG Yu
Abstract: Face automatic recognition technique still is the research focus at present. The face recognition process includes mainly face detection and orientation, face feature recognition and classification etc. It summarized the research history and status quo of...
Abstract: Face automatic recognition technique still is the research focus at present. The face recognition process includes mainly face detection and orientation, face feature recognition and classification etc. It summarized the research history and status quo of...
Author: GAO Xue-tie
Abstract: This paper researches the algorithm of handwriting identification based on the background of self-study examination of higher education. Firstly, multi-chaanel Gabor filter is used in the texture analysis to gain handwriting features. It uses the Euclidea...
Abstract: This paper researches the algorithm of handwriting identification based on the background of self-study examination of higher education. Firstly, multi-chaanel Gabor filter is used in the texture analysis to gain handwriting features. It uses the Euclidea...
Author: ZHANG Tong, XIAO Nan-feng
Abstract: This paper compares several methods to recognize various digits and designs a digit recognition system based on the Back Propagation neural network. Firstly, the digit image is processed in binary to construct the input vector matrix. Secondly, by choosin...
Abstract: This paper compares several methods to recognize various digits and designs a digit recognition system based on the Back Propagation neural network. Firstly, the digit image is processed in binary to construct the input vector matrix. Secondly, by choosin...
Author: LI Wen-wen, WANG Bao-guang, ZH
Abstract: A classifying method of ceramic tiles＇ color difference is proposed, the online detection system based on linear array color CCD sensors is designed. After the image of tile collected by CCD is transformed to the HIS color modal, a series of image process...
Abstract: A classifying method of ceramic tiles＇ color difference is proposed, the online detection system based on linear array color CCD sensors is designed. After the image of tile collected by CCD is transformed to the HIS color modal, a series of image process...
Author: ZHENG De-zhong,CUI Fa-yi
Abstract: Wavelet packet transform,which is generalized by wavelet transform,can be considered as a linear combination of general wavelet functions and has good time-frequency local performance and orthogonality.With decomposition level increases,wavelet packet dec...
Abstract: Wavelet packet transform,which is generalized by wavelet transform,can be considered as a linear combination of general wavelet functions and has good time-frequency local performance and orthogonality.With decomposition level increases,wavelet packet dec...
Author: XU Liang,ZHANG Xiao-Bo
Abstract: A kernel independent component analysis （KICA） was used for nonlinear feature extraction. A fault classification model based on LSSVM was proposed. The research showed that the performance of a classification model depended on different kernel functions. ...
Abstract: A kernel independent component analysis （KICA） was used for nonlinear feature extraction. A fault classification model based on LSSVM was proposed. The research showed that the performance of a classification model depended on different kernel functions. ...
Author: ZHANG Zhi-ping, ZHANG Mei-mei
Abstract: In order for the enterprise to choose rather interfirms to satisfy the customer＇s individuation need, this paper designed the procedure of partionary iuterfirms choice. Construct the interfirm＇s customer value evaluation model based on SVM, regard the mod...
Abstract: In order for the enterprise to choose rather interfirms to satisfy the customer＇s individuation need, this paper designed the procedure of partionary iuterfirms choice. Construct the interfirm＇s customer value evaluation model based on SVM, regard the mod...
Author: DUAN Chai-jie TIAN Zhen, LIANG
Abstract: Objective： Bladder cancer is the ninth cause of cancer deaths and has high recurrence rate after resection of the tumors. Cystoscopy is the current most accurate method for investigating the bladder abnormalities. However, it is expensive, uncomfortable a...
Abstract: Objective： Bladder cancer is the ninth cause of cancer deaths and has high recurrence rate after resection of the tumors. Cystoscopy is the current most accurate method for investigating the bladder abnormalities. However, it is expensive, uncomfortable a...
Author: XIANG Lin,CUI Rong-yi
Abstract: The Independent Component Analysis（ICA） algorithm is applied to the motion blurred image retrieval.Firstly,ICA is performed on the images in picture database to construct a subspace spanned by independent basis vectors,and the respective features of both ...
Abstract: The Independent Component Analysis（ICA） algorithm is applied to the motion blurred image retrieval.Firstly,ICA is performed on the images in picture database to construct a subspace spanned by independent basis vectors,and the respective features of both ...
Author: MA Qian-chi, YU Guo-xian, ZHON
Abstract: Curse of dimensionality often comes out when learning from high dimensional data.Locality Preserving Projection（LPP） can preserve the local geometry of the manifold of data and solves this problem well.However,the similarity utilized in LPP is sensitive t...
Abstract: Curse of dimensionality often comes out when learning from high dimensional data.Locality Preserving Projection（LPP） can preserve the local geometry of the manifold of data and solves this problem well.However,the similarity utilized in LPP is sensitive t...
Author: YANG Yong-sheng, ZHANG You-yun
Abstract: The research is aimed at identifications of rolling bearing faults, improving the classification accuracy effectively, bring forward a method of support vector machines ensemble intelligent diagnosis based on Adaboost algorithm. The method use the frequen...
Abstract: The research is aimed at identifications of rolling bearing faults, improving the classification accuracy effectively, bring forward a method of support vector machines ensemble intelligent diagnosis based on Adaboost algorithm. The method use the frequen...
Author: LIU Jian-wei, XU Xiang, LUO Xi
Abstract: By combining Orthogonal Locality Preserving Projection（OLPP） and Informative Vector Machine（IVM）, this paper proposes OLPP-IVM algorithm for face recognition. It uses OLPP to extract the feature of face image and reduces the dimension of data, and uses IV...
Abstract: By combining Orthogonal Locality Preserving Projection（OLPP） and Informative Vector Machine（IVM）, this paper proposes OLPP-IVM algorithm for face recognition. It uses OLPP to extract the feature of face image and reduces the dimension of data, and uses IV...
Author: LUAN Shao-wen, GONG Wei-guo
Abstract: Aiming at the problem that recognition rate is low when using Mel-Frequency Cepstral Coefficient（MFCC） to present the abnormal sounds, this paper proposes an improved feature extraction method to handle the issue, including the analysis of the characteris...
Abstract: Aiming at the problem that recognition rate is low when using Mel-Frequency Cepstral Coefficient（MFCC） to present the abnormal sounds, this paper proposes an improved feature extraction method to handle the issue, including the analysis of the characteris...
Author: Zhou Ping,Li Chuanfu,Fu Zhipen
Abstract: In this paper we propose and validate a method for feature extraction of brain CT images,which is a difficult problem in CAD technology for mass medical imaging information.Firstly,the preprocessed sub-images were divided into different layers to construc...
Abstract: In this paper we propose and validate a method for feature extraction of brain CT images,which is a difficult problem in CAD technology for mass medical imaging information.Firstly,the preprocessed sub-images were divided into different layers to construc...
Author: Zeng Li,Li Zongjian,Liu Changj
Abstract: Line feature is one of the important features in CT cubic data.It is an important basis in reverse design based on industrial computed tomography（ICT）.After analyzing the component and relation of Wedgelet in monoscale, a fast Wedgelet decomposition metho...
Abstract: Line feature is one of the important features in CT cubic data.It is an important basis in reverse design based on industrial computed tomography（ICT）.After analyzing the component and relation of Wedgelet in monoscale, a fast Wedgelet decomposition metho...
Author: TANG Baoping,JIANG Yonghua, ZH
Abstract: Due to the influence caused by random noises and local strong disturbances embedded in signal on empirical mode decomposition （EMD） results, a novel integrated singular value decomposition-morphology filter method is proposed to overcome this shortcoming....
Abstract: Due to the influence caused by random noises and local strong disturbances embedded in signal on empirical mode decomposition （EMD） results, a novel integrated singular value decomposition-morphology filter method is proposed to overcome this shortcoming....
Author: XU dian-min,LIU Qing-jiang,FU
Abstract: A method of improved feature extraction based on synonymous was proposed collected synonyms in the text as a set, adjustment the weights of synonyms in the set and based on TF-IDF,and combined synonyms through the similarity. The experimental results d ne...
Abstract: A method of improved feature extraction based on synonymous was proposed collected synonyms in the text as a set, adjustment the weights of synonyms in the set and based on TF-IDF,and combined synonyms through the similarity. The experimental results d ne...
Author: WANG Jin-song,CHEN Zhe,FENG Ji
Abstract: A syllable recognition approach based on semi-supervised learning is proposed. This approach has an advantege of obtaining effective recognition when training data set are incomplete Experiment results prove that semisupervised learning is more efficient ...
Abstract: A syllable recognition approach based on semi-supervised learning is proposed. This approach has an advantege of obtaining effective recognition when training data set are incomplete Experiment results prove that semisupervised learning is more efficient ...
Author: DUAN Xu,ZHANG Jiang-li
Abstract: To solve the small sample size problem efficiently,proposed a matrix transform on the basis of linear subspace theory,by which constructed a new linear symmetrical subspace of within-class scatter matrix.By the Fisher＇s discriminant crite-rion,derived two...
Abstract: To solve the small sample size problem efficiently,proposed a matrix transform on the basis of linear subspace theory,by which constructed a new linear symmetrical subspace of within-class scatter matrix.By the Fisher＇s discriminant crite-rion,derived two...
Author: YE Xiao-li, HE Ji-chun
Abstract: To improve the tracking performance with scene complicated backgrounds, a algorithm of object tracking based on spectral histogram and Kalman filter is proposed.To obtain the image＇s frequency characteristic, firstly convoluted with image, and then comput...
Abstract: To improve the tracking performance with scene complicated backgrounds, a algorithm of object tracking based on spectral histogram and Kalman filter is proposed.To obtain the image＇s frequency characteristic, firstly convoluted with image, and then comput...