The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this work, a new training principle is introduced for unsupervised learning that makes the learned representations more efficient and useful. Using partially corrupted inputs instead, the denoising Auto encoder can obtain more robust and representative pattern of inputs than the traditional learning methods. Besides, this denoising Auto encoder can be stacked to form a deep network. The whole framework...
It is well known that extracting effective features from images is a crucial step for appearance-based face recognition methods. In this paper, an effective framework for extracting discriminant features, by so called Discriminant Class-dependence Feature Analysis (DCFA), which combines Linear Discriminant Analysis (LDA) and 1-D Class-dependence Feature Analysis (1D-CFA), is proposed. From one side,...
This paper presents a solution for video retrieval of frontal-view indoor moving pedestrians. A novel and effective system which contains two parts, feature extraction and key frame sets matching, is proposed. For the first part, a successful fusion strategy is proposed for effectively combining information from color and texture features. The experiment indicates that the retrieval accuracy based...
With the increase of the non-liner power loads and impact loads in power systems, the pollution of power quality is becoming more serious. It is important to put up multi-dimensional monitoring and construct monitoring network. In this paper the hardware and software scheme of a new power quality monitoring terminal based on configuration software is introduced in detail, which is applied to different...
Non-negative Matrix Factorization (NMF) is a recently developed method for dimensionality reduction, feature extraction and data mining, etc. Currently no NMF algorithm holds both satisfactory efficiency for applications and enough ease of use. To improve the applicability of NMF, this paper proposes a new monotonic, fixed-point algorithm coined FastNMF by implementing least squares error-based non-negative...
In this paper, a novel class-dependence feature analysis method based on Correlation Filter Bank (CFB) technique for effective multimodal biometrics fusion at the feature level is developed. In CFB, the unconstrained correlation filter trained for a specific modality is designed by optimizing the overall original correlation outputs. Therefore, the differences between modalities have been taken into...
In this paper, one of the problems of linear discriminant analysis (LDA), that is, it pays more attention on minimizing the within-class scatter than on maximizing the between-class scatter, is treated. Though the weighted maximum margin criterion (WMMC) with an appropriate weighted coefficient can solve this problem, how to select this coefficient automatically is still difficult as most of previous...
In this paper, a new method for extracting expression-independent face features based on HOSVD (higher-order singular value decomposition) is proposed and used for face recognition. In the new method, it is assumed that a facial expression could be represented by the facial expressions in the training set. In addition, the expression with higher similarity to the expression of test person has higher...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.