We present an unsupervised anomaly detection method for hyperspectral imagery (HSI) based on data characteristics inherit in HSI. A locally adaptive technique of iteratively refining the well-known RX detector (LAIRX) is developed. The technique is motivated by the need for better firstand second-order statistic estimation via avoidance of anomaly presence. Overall, experiments show favorable R...

In image retrieval systems, the key point is the description of the set of images. In this paper we show that a representation using a cloud of points offers a flexible description but suffers from class overlap. We propose a novel approach for describing clouds of points based on the support vector data description (SVDD). We show that combining image descriptions using dissimilarities improve...

Support Vector Domain Description (SVDD) is inspired by the Support Vector Classifier. It obtains a sphere shaped decision boundary with minimal volume around a dataset. This data description can be used for novelty or outlier detection. Our approach is always to minimize the volume of the sphere describing the dataset, while at the same time maximize the separability between the spheres. To bu...

In this paper, we propose a feature coding method based on shared weights support vector data description (FCM-SWSVDD). The proposed process of FCM-SWSVDD is as follows. By considering the density information clusters and introducing weighting learning, an improved (SVDD), named (SWSVDD). SWSVDD can obtain cluster center radius more accurately. Incorporating triangle into same learning process,...

Object tracking is an important research topic in the applications of machine vision, and has made great progress in the past decades, among which the technique based on classification is a very efficient way to solve the tracking problem. The classifier classifies the objects and background into two different classes, where the tracking drift caused by noisy background can be effectively handl...