This paper considers a method of image recognition, which is produced by the transformation of the object into a set of functions representing the area of intersection of the figure and its copy at its shift in one direction. The object of this research is image shapes of individual objects in the visual picture. The efficiency of different methods of optical image recognition has been conducted depending on the scale and rotation angle.

This article describes basic methods that are required to build a system of machine vision which based on parallel shift technology. The methods are based on the implementation of one operation (definition function of the area of intersection of the real image and its copy which parallel shifted) and analysis of its basic characteristics. Analysis of time intervals obtained characteristics improves the performance of image recognition. The methods are based on simple mathematical operations and can be used in the processing of both raster and non-raster images.

No abstract

Image processing is one of the important tasks of creating artificial intelligence. The methods for digital images processing are widely used by developers at this time. The parallel shift technology makes it possible to create alternative ways of describing and processing images. It involves the transformation of images not into a set of pixels, but into a set of functions that are organized in a certain way. The completeness of the system is determined by the ability to perform some basic tasks. Image processing includes image pre-processing, video data storage, various image manipulations, images restoration. This chapter discusses a mathematical model for the recovery of flat convex binary images. Images are restored on the basis of data generated by an image processing system based on parallel shift technology. Two methods are provided for determining the imaging area.

There are tasks of automatic identification of the moving stock of the railway, one of which is the automatic identification of rail cars cars by their number plates. Different organizational, legal, moral and ethical, technical, and programmatic methods of automated identification are used to solve this problem. At present little attention is paid to the development of means of automatic identification of moving objects, which would be possible regardless of the orientation and shape of the figure, especially if it concerns the recognition of freely oriented images of number plates. Therefore, many new methods for recognizing of number plates are developing. In the chapter, the system of identification of objects by their number plates in real time is considered. On moving objects (moving stock of a railway), an identifier image is drawn, which is an ordered set of characters. As a rule, these are numbers. But there may be other characters. The work also discusses the method of identification images of number plates with a high percentage of noise.