Speed up kernel discriminant analysis

Cai, Deng; He, Xiaofei; Han, Jiawei

doi:10.1007/s00778-010-0189-3

Cited by 195 publications

(137 citation statements)

References 34 publications

Supporting

Mentioning

136

Contrasting

Order By: Relevance

“…Kernel discriminant analysis is a non-linear technique of Linear Discriminant Analysis (LDA) (Cai et al, 2011;Fukunaga, 2013). In LDA, the projection vectors are acquired by decreasing the variation of the same class and at the same time, increasing the between class scatter.…”

Section: Kernel Discriminant Analysis With Spectral Regression (Sr-kdmentioning

confidence: 99%

“…It is shown in (Cai et al, 2011;Tahir et al, 2015) that the following two linear equations can be used to obtain the KDA projections…”

Section: Kernel Discriminant Analysis With Spectral Regression (Sr-kdmentioning

confidence: 99%

“…In this study, nearest centroid classifier (NCC) to get the final decision from each model of SR-KDA (Cai et al, 2011).…”

Section: Kernel Discriminant Analysis With Spectral Regression (Sr-kdmentioning

confidence: 99%

See 2 more Smart Citations

Robust off-line text independent writer identification using bagged discrete cosine transform features

Khan

Tahir

Khelifi

et al. 2017

Expert Systems with Applications

View full text Add to dashboard Cite

Northumbria University has developed Northumbria Research Link (NRL) to enable users to access the University's research output. Copyright © and moral rights for items on NRL are retained by the individual author(s) and/or other copyright owners. Single copies of full items can be reproduced, displayed or performed, and given to third parties in any format or medium for personal research or study, educational, or not-for-profit purposes without prior permission or charge, provided the authors, title and full bibliographic details are given, as well as a hyperlink and/or URL to the original metadata page. The content must not be changed in any way. Full items must not be sold commercially in any format or medium without formal permission of the copyright holder. The full policy is available online: http://nrl.northumbria.ac.uk/policies.html This document may differ from the final, published version of the research and has been made available online in accordance with publisher policies. To read and/or cite from the published version of the research, please visit the publisher's website (a subscription may be required.) AbstractEfficient writer identification systems identify the authorship of an unknown sample of text with high confidence. This has made automatic writer identification a very important topic of research for forensic document analysis. In this paper, we propose a robust system for offline text independent writer identification using bagged discrete cosine transform (BDCT) descriptors. Universal codebooks are first used to generate multiple predictor models. A final decision is then obtained by using the majority voting rule from these predictor models. The BDCT approach allows for DCT features to be effectively exploited for robust hand writer identification. The proposed system has first been assessed on the original version of hand written documents of various datasets and results have shown comparable performance with state-of-the-art systems. Next, blurry and noisy documents of two different datasets have been considered through intensive experiments where the system has been shown to perform significantly better than its competitors. To the best of our knowledge this is the first work that addresses the robustness aspect in automatic hand writer identification. This is particularly suitable in digital forensics as the documents acquired by the analyst may not be in ideal conditions.

show abstract

Section: Kernel Discriminant Analysis With Spectral Regression (Sr-kdmentioning

confidence: 99%

“…It is shown in (Cai et al, 2011;Tahir et al, 2015) that the following two linear equations can be used to obtain the KDA projections…”

Section: Kernel Discriminant Analysis With Spectral Regression (Sr-kdmentioning

confidence: 99%

See 1 more Smart Citation

Robust off-line text independent writer identification using bagged discrete cosine transform features

Khan

Tahir

Khelifi

et al. 2017

Expert Systems with Applications

View full text Add to dashboard Cite

show abstract

“…Inspired by the spectral regression kernel discriminant analysis (SRKDA) (Cai et al, 2011) having moderate computation effort, the SRKDA algorithm in combination with the optimal parameter selection is given as below.…”

Section: Feature Dimension Reductionmentioning

confidence: 99%

“…To solve the above regression problem, the least angel regression (LARS) (Efron and Tibshirani, 2004) is adopted, and the radial basis function (RBF) (Cai et al, 2011) is taken as the kernel function for the convenience of computation.…”

Section: Feature Dimension Reductionmentioning

confidence: 99%

In-situ crystal morphology identification using imaging analysis with application to the L-glutamic acid crystallization

Huo

Liu

et al. 2016

Chemical Engineering Science

View full text Add to dashboard Cite

Abstract:A synthetic image analysis strategy is proposed for in-situ crystal size measurement and shape identification for monitoring crystallization processes, based on using a real-time imaging system. The proposed method consists of image processing, feature analysis, particle sieving, crystal size measurement, and crystal shape identification. Fundamental image features of crystals are selected for efficient classification. In particular, a novel shape feature, referred to as inner distance descriptor, is introduced to quantitatively describe different crystal shapes, which is relatively independent of the crystal size and its geometric direction in an image captured for analysis. Moreover, a pixel equivalent calibration method based on subpixel edge detection and circle fitting is proposed to measure crystal sizes from the captured images. In addition, a kernel function based method is given to deal with nonlinear correlations between multiple features of crystals, facilitating computation efficiency for real-time shape identification.Case study and experimental results from the cooling crystallization of L-glutamic acid demonstrate that the proposed image analysis method can be effectively used for in-situ crystal size measurement and shape identification with good accuracy.

show abstract

Multi-modality Low-Rank Learning Fused First-Order and Second-Order Information for Computer-Aided Diagnosis of Schizophrenia

Zhu

Zhang

et al. 2019

Intelligence Science and Big Data Engineering. Big Data and Machine Learning

View full text Add to dashboard Cite

Speed up kernel discriminant analysis

Cited by 195 publications

References 34 publications

Robust off-line text independent writer identification using bagged discrete cosine transform features

Robust off-line text independent writer identification using bagged discrete cosine transform features

In-situ crystal morphology identification using imaging analysis with application to the L-glutamic acid crystallization

Multi-modality Low-Rank Learning Fused First-Order and Second-Order Information for Computer-Aided Diagnosis of Schizophrenia

Contact Info

Product

Resources

About