This paper describes a new selective attention based method which can be used effectively in wide range of target detection tasks without using any a-priori knowledge about the target. In our proposed system, several basic features are extracted directly from original input visual stimuli, and these features are integrated based on their local competitive relations and statistical information. ...

Feature extraction is a key technology in the process of the 3D model retrieval, and the retrieval result is determined by the quality of the features. This paper structures one function (θ, φ,H) which is used the spatial position (θ, φ) and the mean curvature (H) of the 3D model surface point. Through making harmonic analysis for the function, a group of partial features which have rotation in...

In this report, we present a preliminary evaluation of the feature extraction system for proxemic behavior analysis described in our previous work (Mead et al., 2011a).

In this work we propose a novel person re-identification approach. The solution, inspired by human gazing capabilities, wants to identify the salient regions of a given person. Such regions are used as a weighting tool in the image feature extraction process. Then, such novel representation is combined with a set of other visual features in a pairwise-based multiple metric learning framework. F...

A general feature extraction framework is proposed as an extension of conventional linear discriminant analysis. Two nonlinear feature extraction algorithms based on this framework are investigated. The 1rst is a kernel function feature extraction (KFFE) algorithm. A disturbance term is introduced to regularize the algorithm. Moreover, it is revealed that some existing nonlinear feature extract...

We present the Mind the Gap Model (MGM), an approach for interpretable feature extraction and selection. By placing interpretability criteria directly into the model, we allow for the model to both optimize parameters related to interpretability and to directly report a global set of distinguishable dimensions to assist with further data exploration and hypothesis generation. MGM extracts disti...

In this paper, we defined the viseme (visual speech element) and described about the method of extracting visual feature vector. We defined the 10 visemes based on vowel by analyzing of Korean utterance and proposed the method of extracting the 20-dimensional visual feature vector, combination of static features and dynamic features. Lastly, we took an experiment in recognizing words based on 3...

Due to the digitization of data and advances in technology, it has become extremely easy to obtain and store large quantities of data, particularly Multimedia data. Fields ranging from Commercial to Military need to analyze these data in an efficient and fast manner. Presently, tools for mining images are few and require human intervention. Feature selection and extraction is the pre-processing...