Pattern Recognition and Image Analysis

In this work the problem of synthesis of a learning algorithm of point classification in planar configurations is considered. A modification of the formulation of the problem, based on the use of metrics for comparing the neighborhoods and the ...

A method of prototype sample selection from a training set for a classifier of K nearest neighbors (KNN), based on minimization of the complete cross validation functional, is proposed. The optimization leads to reduction of the training set to the ...

The problem of searching all possible metrics in N -valued logic is considered. The cases of N = 1, 2, , 7 are considered, and a number of theorems valid for arbitrary N are formulated. The found metrics are assumed to be used for solving ...

In recognition theory a number of optimization problems appear. The search for the maximum solvable subsystem of the system of linear inequalities is one of these tasks. Its solution methods based on examining of the special set of subsystems are known. ...

The problem of noise-proof a posteriori (off-line) recognition is considered for a vector alphabet generating sequences that include quasi-periodically alternating vector-fragments coinciding with elements of this alphabet. One variant of this problem ...

We consider a problem of supervised statistical learning for a finite population and obtain PAC generalization bounds within the combinatorial PAC framework. Combinatorial counterparts of Langford shell bounds are obtained and are shown to be either the ...

It is shown that there are no kernel faces in a contracted disjunctive normal form of a complete Boolean function (in seven or more variables) with a small number of zeroes. In addition, a lower bound for the number of faces that go through the same ...

We investigate a direct geometric approach to the problem of reconstruction of the behavior of a sample of hidden dimensions. A method for an improved description of cluster sampling, based on the interpretation of nonlinearities in the empirical ...

The problem of selecting of prototypes is to select a subset in the learning sample for which the set of minimum cardinality would provide the optimum of a given learning quality functional. In this article the problem of classification is considered in ...

The problem of estimating the similarity of surfaces represented as point clouds is studied. An approach is suggested to the comparison of such surfaces based on the surface approximation by piecewise-linear functions of two variables in the Delaunay ...

Orthogonal moment is known as better moment functions compared to the non-orthogonal moment. Among all the orthogonal moments, Tchebichef Moment appear to be the most recent moment functions that still attract the interest among the computer vision ...

A two-dimensional principal component analysis (2D PCA) method directed at processing digital images is discussed. The method is based on representation of images as a set of rows and columns analyzing these sets. Two methods of realizing the 2D PCA ...

Algorithmic and software support of an interactive problem-solving system based on levelwise image transmission through the Internet and hierarchical video data representation structures is described.

Graph structure is crucial to graph based dimensionality reduction. A mixture graph based semi-supervised dimensionality reduction (MGSSDR) method with pairwise constraints is proposed. MGSSDR first constructs multiple diverse graphs on different random ...

The proximal isovelocity surface area measurement, also called as the "flow convergence" method, can be used in echocardiography to estimate the area of an orifice through which blood flows. It has a lot of applications, but this paper focuses only on ...

A new formal approach to recognition of halftone textures based on the apparatus of stochastic geometry and functional analysis is described. A key element of it is the application of a new class of structural features of recognition, i.e., trip flight ...

The problem of dividing noise and texture elements with regard to specific features of an ultrasonic image is studied. A mathematical model is developed that describes statistical and spectral properties of various elements of the image structure. Based ...

Three types of verified training algorithms (with a tutor) at the limited infinite sets (based on the theory of separability) are presented. On contrast to two first ones the mathematical motivation of the last one can be a basis of the new theory of ...

An algorithm for off-road routing of vehicles for land and water under off-road conditions or in the waters of the World Ocean is described. The proposed algorithm allows us to reduce significantly the memory sizes and computing time, which is important ...