In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the d...In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the data is mapped into a higher-dimensional space with kernel principal component analysis to make the data linearly separable. Then a two-layer KPCANet is built to obtain the principal components of the image. Finally, the principal components are classified with a linear classifier. Experimental results showthat the proposed KPCANet is effective in face recognition, object recognition and handwritten digit recognition. It also outperforms principal component analysis network（ PCANet） generally. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.展开更多
Human adenoviruses (HAdVs), especially HAdV-B3, -E4 and -B7, are associated with Acute Respiratory Disease in Chinese children, and occasionally in adults. In order to establish and document the profiles of the respir...Human adenoviruses (HAdVs), especially HAdV-B3, -E4 and -B7, are associated with Acute Respiratory Disease in Chinese children, and occasionally in adults. In order to establish and document the profiles of the respiratory adenovirus pathogen among children in Guangzhou, Southern China, a rapid, simple and practical method for identification and typing of respiratory adenoviruses was developed and evaluated. One pair of universal PCR primers was designed according to the conserved region of the hexon gene, which can detect not only HAdV-B3, -E4 and -B7, but also HAdV-B14, -F40 and -F41, with a specific 300bp PCR product. Three pairs of type-specific PCR primers were also designed according to the hypervariable regions of the hexon gene to type HAdV-B3, -E4 and -B7 by three independent PCR reactions, making it easy to optimize the PCR conditions. By using this method, one hundred throat swab specimens collected during Oct 2010 to Dec 2011 and suspected of being positive for adenoviral infection were identified and typed for adenoviruses. Of these samples, fifty-five were adenovirus-positive. The most common HAdV type was HAdV-B3, identified in 92.7% of samples, which is not only consistent with the data reported in 2004-2006, but also consistent with the recent report in Hangzhou, eastern China, indicating that HAdV-B3 has been circulating in Guangzhou, and maybe in eastern China, for many years. The method for the respiratory adenovirus identification and typing we developed is rapid, simple and practical, which has a potential in the real-time surveillance of circulating adenovirus strains and also to provide etiological evidence for the adenovirus-relative disease control and prevention in China.展开更多
Several languages use the Arabic alphabets and Arabic scripts present challenges because the letter shape is context sensitive. For the past three decades, there has been a mounting interest among researchers in this ...Several languages use the Arabic alphabets and Arabic scripts present challenges because the letter shape is context sensitive. For the past three decades, there has been a mounting interest among researchers in this problem. In this paper we present an Arabic Character Recognition system and review the theory behind the Arabic recognition system, the characteristics of Arabic writing, the sequence steps of recognizing Arabic text. These steps are separately discussed, and previous research work on each step is reviewed. Also in this paper we give some samples of Arabic fonts.展开更多
In this work,a system for recognition of newspaper printed in Gurumukhi script is presented.Four feature extraction techniques,namely,zoning features,diagonal features,parabola curve fitting based features,and power c...In this work,a system for recognition of newspaper printed in Gurumukhi script is presented.Four feature extraction techniques,namely,zoning features,diagonal features,parabola curve fitting based features,and power curve fitting based features are considered for extracting the statistical properties of the characters printed in the newspaper.Different combinations of these features are also applied to improve the recognition accuracy.For recognition,four classification techniques,namely,k-NN,linear-SVM,decision tree,and random forest are used.A database for the experiments is collected from three major Gurumukhi script newspapers which are Ajit,Jagbani and Punjabi Tribune.Using 5-fold cross validation and random forest classifier,a recognition accuracy of 96.19%with a combination of zoning features,diagonal features and parabola curve fitting based features has been reported.A recognition accuracy of 95.21%with a partitioning strategy of data set(70%data as training data and remaining 30%data as testing data)has been achieved.展开更多
Moment invariants firstly introduced by M. K Hu in 1962, has some shortcomings. After counting a large number of statistical distribution information of Chinese characters,the authors put forward the concept of inform...Moment invariants firstly introduced by M. K Hu in 1962, has some shortcomings. After counting a large number of statistical distribution information of Chinese characters,the authors put forward the concept of information moments and demonstrate its invariance to translation,rotation and scaling.Also they perform the experiment in which information moments compared with moment invaiants for the effects of similar Chinese characters and font recognition.At last they show the recognition rate of 88% by information moments,with 70% by moment inariants.展开更多
基金The National Natural Science Foundation of China(No.6120134461271312+7 种基金6140108511301074)the Research Fund for the Doctoral Program of Higher Education(No.20120092120036)the Program for Special Talents in Six Fields of Jiangsu Province(No.DZXX-031)Industry-University-Research Cooperation Project of Jiangsu Province(No.BY2014127-11)"333"Project(No.BRA2015288)High-End Foreign Experts Recruitment Program(No.GDT20153200043)Open Fund of Jiangsu Engineering Center of Network Monitoring(No.KJR1404)
文摘In order to classify nonlinear features with a linear classifier and improve the classification accuracy, a deep learning network named kernel principal component analysis network（ KPCANet） is proposed. First, the data is mapped into a higher-dimensional space with kernel principal component analysis to make the data linearly separable. Then a two-layer KPCANet is built to obtain the principal components of the image. Finally, the principal components are classified with a linear classifier. Experimental results showthat the proposed KPCANet is effective in face recognition, object recognition and handwritten digit recognition. It also outperforms principal component analysis network（ PCANet） generally. Besides, KPCANet is invariant to illumination and stable to occlusion and slight deformation.
基金supported by National Natural Science Foundation of China (31100133)Natural Science Foundation of Guangdong Province (S2012010009261)+2 种基金Guangdong College Students' Innovative Experimental Project(1212111023)Extracurricular Research Activities of Southern Medical University (2010kw076)School of Public Health and Tropical Medicine (GWXS20110102)
文摘Human adenoviruses (HAdVs), especially HAdV-B3, -E4 and -B7, are associated with Acute Respiratory Disease in Chinese children, and occasionally in adults. In order to establish and document the profiles of the respiratory adenovirus pathogen among children in Guangzhou, Southern China, a rapid, simple and practical method for identification and typing of respiratory adenoviruses was developed and evaluated. One pair of universal PCR primers was designed according to the conserved region of the hexon gene, which can detect not only HAdV-B3, -E4 and -B7, but also HAdV-B14, -F40 and -F41, with a specific 300bp PCR product. Three pairs of type-specific PCR primers were also designed according to the hypervariable regions of the hexon gene to type HAdV-B3, -E4 and -B7 by three independent PCR reactions, making it easy to optimize the PCR conditions. By using this method, one hundred throat swab specimens collected during Oct 2010 to Dec 2011 and suspected of being positive for adenoviral infection were identified and typed for adenoviruses. Of these samples, fifty-five were adenovirus-positive. The most common HAdV type was HAdV-B3, identified in 92.7% of samples, which is not only consistent with the data reported in 2004-2006, but also consistent with the recent report in Hangzhou, eastern China, indicating that HAdV-B3 has been circulating in Guangzhou, and maybe in eastern China, for many years. The method for the respiratory adenovirus identification and typing we developed is rapid, simple and practical, which has a potential in the real-time surveillance of circulating adenovirus strains and also to provide etiological evidence for the adenovirus-relative disease control and prevention in China.
文摘Several languages use the Arabic alphabets and Arabic scripts present challenges because the letter shape is context sensitive. For the past three decades, there has been a mounting interest among researchers in this problem. In this paper we present an Arabic Character Recognition system and review the theory behind the Arabic recognition system, the characteristics of Arabic writing, the sequence steps of recognizing Arabic text. These steps are separately discussed, and previous research work on each step is reviewed. Also in this paper we give some samples of Arabic fonts.
文摘In this work,a system for recognition of newspaper printed in Gurumukhi script is presented.Four feature extraction techniques,namely,zoning features,diagonal features,parabola curve fitting based features,and power curve fitting based features are considered for extracting the statistical properties of the characters printed in the newspaper.Different combinations of these features are also applied to improve the recognition accuracy.For recognition,four classification techniques,namely,k-NN,linear-SVM,decision tree,and random forest are used.A database for the experiments is collected from three major Gurumukhi script newspapers which are Ajit,Jagbani and Punjabi Tribune.Using 5-fold cross validation and random forest classifier,a recognition accuracy of 96.19%with a combination of zoning features,diagonal features and parabola curve fitting based features has been reported.A recognition accuracy of 95.21%with a partitioning strategy of data set(70%data as training data and remaining 30%data as testing data)has been achieved.
基金supported by the Specical Fund of Taishan Scholar of Shandong Province
文摘Moment invariants firstly introduced by M. K Hu in 1962, has some shortcomings. After counting a large number of statistical distribution information of Chinese characters,the authors put forward the concept of information moments and demonstrate its invariance to translation,rotation and scaling.Also they perform the experiment in which information moments compared with moment invaiants for the effects of similar Chinese characters and font recognition.At last they show the recognition rate of 88% by information moments,with 70% by moment inariants.
