Search

In the process of handwritten signature recognition, preprocessing is an important step before calculation its informative features. Signatures of any person always have some differences, in addition, they can be of different colors, sizes and orientations. After signature digitization, their images may contain some noise. The purpose of signature image preprocessing is to obtain the most invariant representation of the digital image of a person's signature, which will allow us to identify him or define that the signature is forged.This paper describes a sequence of transformations necessary to perform preprocessing of the signature image and form its representation of a single orientation and size. It is assumed that there are no graphic elements in the image that are not related to the signature and the background is relatively uniform. The transformations under consideration sequentially perform binarization of the signature image, its filtering, rotation, cropping of the circumscribed rectangle and scaling to a fixed size.The described preprocessing procedures were applied to a number of available digital signature image databases, such as CEDAR, BHSig260-Bengali, BHSig260-Hindi. Experiments on signature recognition confirm that the presented approach to the signature image preprocessing leads to increasing of the recognition accuracy.

The Earth remote sensing technologies (ERS) in exploration largely determine their effectiveness. Therefore, development of a new methodological support for the use of remote sensing data in predicting mining and geological conditions is a key priority area. The studies are based on the analysis of the assessment of information, social, and economic efficiency of remote sensing data application at mineral deposits. The role of application of new technologies (including remote ones) in the process of optimizing initial exploration stages is noted. The possibilities of using remote sensing data to assess general nature, direction, and extent of environmental changes due to mining activities are shown. A technique is proposed that can be used in the process of tracking changes in the topology of objects in the course of mining. The differences in the results obtained using the proposed technique for processing satellite images on rectangular and hexagonal grids (rasters) are considered. The advantages of using the hexagonal grid for tracking the boundaries of objects and formation of signs are shown. Practical examples - a number of open source satellite images processed using the proposed method - are presented. The study findings allow applying intelligent analysis of satellite imagery data with the subsequent identification of the earth's surface objects of interest. An example of using the obtained results together with specialized software tools (such as GIS INTEGRO geographic information system capable of solving geological problems, or the foreign ArcGIS system) for constructing contour maps of the territory and obtaining its description based on topological relations and metric information is shown.

Diabetic retinopathy is one of the most frequent complications of diabetes, which leads to severe consequences, including rapid and irreversible vision loss. The laser coagulation procedure to treat diabetic retinopathy consists in applying a series of microburns to the fundus to deal with macular edema. The existing hardware/software packages are primarily based on the use of a predetermined pattern for coagulate arrangement. However, due to the complex form of edema and vascular system, this approach leads to an uneven arrangement. To solve the problem, we propose a new approach based on the application of sphere packing algorithms (circle packing in two-dimensional images) in the specified area of interest. Since one of the main requirements for the laser coagulation procedure is that it should have the minimum duration, a problem of the computational complexity of the developed algorithms arises. This requirement is completely ignored by the existing approaches, therefore the development of new high-performance coagulate arrangement algorithms is highly relevant. In the paper, we propose seven new algorithms for coagulate arrangement and provide a detailed analysis of key characteristics of the algorithms. The characteristics considered have made it possible to extract information relating to the algorithm properties. Regularity is determined by the median, asymmetry and the kurtosis; determinism is determined by the variance and the mean.