卷 26, 编号 4 (2016)

We consider a problem of risk estimation for large-margin multi-class classifiers. We propose a novel risk bound for the multi-class classification problem. The bound involves the marginal distribution of the classifier and the Rademacher complexity of the hypothesis class. We prove that our bound is tight in the number of classes. Finally, we compare our bound with the related ones and provide a simplified version of the bound for the multi-class classification with kernel based hypotheses.

Recognition of human actions is a very important, task in many applications such as Human Computer Interaction, Content based video retrieval and indexing, Intelligent video surveillance, Gesture Recognition, Robot learning and control, etc. An efficient action recognition system using Difference Intensity Distance Group Pattern (DIDGP) method and recognition using Support Vector Machines (SVM) classifier is presented. Initially, Region of Interest (ROI) is extracted from the difference frame, where it represents the motion information. The extracted ROI is divided into two blocks B1 and B2. The proposed DIDGP feature is applied on the maximum intensity block of the ROI to discriminate the each action from video sequences. The feature vectors obtained from the DIDGP are recognized using SVM with polynomial and RBF kernel. The proposed work has been evaluated on KTH action dataset which consists of actions like walking, running, jogging, hand waving, clapping and boxing. The proposed method has been experimentally tested on KTH dataset and an overall accuracy of 94.67% for RBF kernel.

Nowadays, with the increased use of digital images, almost all of which are in color format. Conventional methods process color images by converting them into gray scale, which is definitely not effective in representing and which may lose some significant color information. Recently, a novel method of the Color Angular Radial Transform (CART) is presented. This transform combines the information by considering the shape information inherent in the color. However, ART is adapted on the MPEG-7 standard is only limited to binary images and gray-scale images has many properties: invariant to rotation, Translation and scaling, ability to describe complex objects, so it cannot handle color images directly. To solve this problem we proposed in this article to generalize ART from complex domain to hypercomplex domain using quaternion algebras to achieve the Quaternion Angular Radial Transform (QART) to describe finally two dimensional color images and to insure these properties robustness to all possible rotations and translation and scaling. The performance of QART is then evaluated with large database of color image as an example. We first provide a general formula of ART from which we derive a set of quaternion-valued QART properties transformations by eliminating the influence of transformation parameters. The experimental results show that the QART performs better than the commonly used Quaternion form Zernike Moment (QZM) in terms of image representation capability and numerical stability.

Local binary patterns was used to distinguish the Photorealistic Computer Graphics and Photographic Images, however the dimension of the extracted features is too high. Accordingly, the Local Ternary Count based on the Local Ternary Patterns and the Local Binary Count was developed in this study. Furthermore, a novel algorithm is presented based on the Local Ternary Count to classify photorealistic Computer Graphics and Photographic images. The experiment results show that the proposed algorithm effectively reduces the dimension of the classification features and maintains a good classification performance.

This paper discusses the problems associated with the development of the specialized database management system (DBMS) GIS Terra Plus for storage, processing, and analysis of spatially distributed data (SDD). Description models and the presentation structure of the SDD, the scheme of databases of the GIS Terra Plus DBMS, the query system, and operating conditions are considered.

The classification of fractured of a patient plays an important role in orthopaedic evaluation and diagnosis. It not only aids in assessing the severity of the disease or injury but also serves as a basis of treatment or surgical correction. This paper proposes a novel approach to automated classification of long-bone fractures based on the analysis of an input X-ray image. The method consists of four major steps: (i) extraction of the bone-contour from a given X-ray image, (ii) identification of fracture-points or cracks, (iii) determination of an equivalent set of geometric features in tune with the Müller-AO clinical classification of fractures, and (iv) identification and detailed assessment of the fracture-type. The decision procedure makes use of certain geometric properties of digital curves such as relaxed digital straight line segments (RDSS), arcs, discrete curvature, and concavity index. The proposed method for the analysis of fractures is applied on different types of bone-images and is observed to have produced correct classification in most of the test-cases.

This paper discusses the main aspects of geomagnetic data processing using the wavelet transform. The wavelet transform is shown to be efficient for automatic extraction of unperturbed level of the horizontal component of the Earth’s magnetic field. As a result, it becomes possible to significantly reduce the errors arising during automatic calculations of the local geomagnetic activity index (local K-index) in comparison with adaptive smoothing (KAsm is Adaptative Smoothing method) recommended by INTERMAGNET. It has been found that prior to magnetic storms, we can observe a weak rise of geomagnetic activity in different frequency bands connected with the development of an approaching storm.

The article presents the algorithm that allows one to carry out automatic detection of local anomalies of magnetometric data based on image analysis principles. The algorithm was tested on the available data of the magnetometric survey in areas of planned archaeological excavations.

This paper considers the problem of metric classification of early Parkinsonism in the feature space of multi-channel signals of electroencephalography (EEG). The electroencephalography feature space includes both spectral characteristics and features of rhythmic disorganization. A model of logistic regression for the classification of early Parkinsonism is studied. The model was trained on the data obtained from the experimental EEG studies in a group of patients in the 1st stage of Parkinson’s disease and a control group of subjects. Analysis of the classification logistic model was carried out using the data from 38 subjects, including 22 subjects from the control group and 16 patients in the first stage of Parkinson’s disease. Dependencies of the recall on the functional value for the control group and the patients and classification accuracies are calculated.

The key problem in increasing efficiency of radiotherapy of malignant tumors in brain and other dangerous neoplasms is the problem of increasing the quality of 3D positioning of a patient before radiotherapy. We consider the principles of development of fast parallel iterative algorithms based on graphic accelerators and the OpenGL library. The proposed approaches provide simultaneous residual minimization for the sought solution and total variation of the reconstructed 3D image. In this case, the number of required initial data, i.e., conic X-ray projections, can be reduced several times, and therefore, the radiation load on the patient can also be accordingly reduced with preservation of the necessary contrast and spatial resolution of the 3D image of the patient. The new heuristic iterative algorithm can be used as an alternative to the known 3D Feldkamp algorithm.

There are 2 errors in the paper of A.E.Levashov “An algorithm for recognizing linear objects in aerial photos of the author automatically” (PRIA, volume 26, Issue 2, page 385). The corrected version are as follows:

(1) The affiliation of the author is “The Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences (Moscow, Russian Federation).

(2) Тhe Acknowledgements

The paper was partly supported by the Russian Foundation for Basic Research (project 1401-00881).