We present an enhanced direct linear discriminant analysis (EDLDA) solution to effectively and efficiently extract discriminatory features from high dimensional data. The EDLDA integrates two types of class-wise weighting terms in estimating the average within-class and between-class scatter matrices in order to relate the resulting Fisher criterion more closely to the minimization of classific...

In this working note, we propose a set of features and a classification scheme for detecting automatically violent scenes in movies. The features are extracted from audio, video, and subtitles modalities of the movies. In violent scenes classification, we found the following features relevant: the short time audio energy, motion component, and shot words rate. We classified the shots into viole...

Recently deep learning has been successfully used in speech recognition, however it has not been carefully explored and widely accepted for speaker verification. To incorporate deep learning into speaker verification, this paper proposes novel approaches of extracting and using features from deep learning models for text-dependent speaker verification. In contrast to the traditional short-term ...

As for illumination variation, traditional feature extraction methods are not satisfactory for face recognition. A block discriminant analysis algorithm is proposed to solve the problem. Firstly, local contrast enhancement is used to compensate for uneven illumination; secondly, discrete cosine transform (DCT) is implemented for divided image blocks. According to data distribution of DCT matrix...

Human Activity Recognition (HAR) from time-sequential video images is an active research area in various applications such as video surveillance and smart homes nowadays. This paper presents a novel approach of automatic HAR based on Generalized Discriminant Analysis (GDA) on Enhanced Independent Component (EIC) features from binary silhouette information to be used with Hidden Markov Model (HM...

This paper proposes the AdaBoost Gabor Fisher Classifier (AGFC) for robust face recognition, in which a chain AdaBoost learning method based on Bootstrap re-sampling is proposed and applied to face recognition with impressive recognition performance. Gabor features have been recognized as one of the most successful face representations, but it is too high dimensional for fast extraction and acc...

The aim of this project is to classify the mammographic masses as benign or malignant using texture and shape features. A set of 73 mammograms is used for the analysis, out of which 41 are benign and 32 are malignant. Manually segmented masses are obtained from the DDSM, USF database [2]. Texture and shape features are extracted from the manually segmented masses. Stepwise linear discriminant a...

Automatic prostate segmentation in MR images plays an important role in prostate cancer diagnosis. However, there are two main challenges: (1) Large inter-subject prostate shape variations; (2) Inhomogeneous prostate appearance. To address these challenges, we propose a new hierarchical prostate MR segmentation method, with the main contributions lying in the following aspects: First, the most ...

A novel approach to feature selection is proposed for data space defined over continuous features. This approach can obtain a subset of features, such that the subset features can discriminate class labels of objects and the discriminant ability is prior or equivalent to that of the original features, so to effectively improve the learning performance and intelligibility of the classification m...

This paper reports on email filtering based on content features. We test the validity of a novel statistical feature extraction method, which relies on dimensionality reduction to retain the most informative and discriminative features from messages. The approach, named Biased Discriminant Analysis (BDA), aims at finding a feature space transformation that closely clusters positive examples whi...