Elaboration of structural representation of regions of scanned document images for MRC model

Abstract

<p class="abstract">The Mixed Raster Content (MRC) model is a common form of representation of a scanned document image. The further development of this model, which consists in the structural representation of homogeneous regions on each layer of the MRC image has been completed. The aim of such representation is to detect regions of interest in the image and identify it to solve the problem of segmentation of scanned document images.</p><p class="abstract">The layer containing graphic and photographic images was represented as a union of several regions using a piecewise constant function of the intensity of the image region. For this, the graphic and photographic images were represented in the form of a partition into segments containing pixels of uniform intensity. To determine these regions in order to separate the graphic from the photo images, the edges at the segment boundaries were considered.</p><p class="abstract">The layer containing the text was represented as an image of the regions of the structural texture on a uniform background. These regions contained fragments of normal text and heading with the same pixel intensity and differing in the shape and size of symbols, as well as the distance between them. Such a representation of the layer made it possible to take into account the spatial relationships between symbol image pixels and further to extract text from the background.</p>The proposed model for the representation of the scanned document image allows to extracting the image layers that contain homogeneous regions, and reducing the process of segmentation of the entire image to the segmentation of separate layers of the image. This allows increasing the performance speed while maintaining a high quality of image segmentation

Authors and Affiliations

Alesya Ishchenko, Marina Polyakova, Varvara Kuvaieva, Alexandr Nesteryuk

Keywords

Related Articles

Process of resources provision management of the enterprise's activity with consideration of gender factor

<p>The study of the process of resources provision management of enterprise activity taking into account the gender factor was conducted. It was determined that the present environment requires business entities to take...

Development of a mobile decision support system based on the smart method for android platform

<p>The work is devoted to the development of a mobile decision support system for solving the multiple criteria decision-making problems. To ensure the autonomous operation of the system, it was proposed to use a three-l...

Impoving energy characteristics of the welding power sources for TIG-AC welding

This paper proposes a circuit solution and a control algorithm for a welding power source for TIG-AC welding with improved energy characteristics. The source is made using a welding transformer and a low-voltage series a...

Comparative tests of contact elements at current collectors in order to comprehensively assess their operational performance

<p>We have studied the interaction between contact elements in the pantographs of electric transport under operation at the sections of railroads powered by direct and alternating current. In contrast to known techniques...

Revealing the effect of decreased energy intensity of grinding in a tumbling mill during self-excitation of auto-oscillations of the intrachamber fill

<p>We have investigated a possibility to perform comparative evaluation of the effectiveness of grinding process in a tumbling mill under conventional steady and self-excited auto-oscillatory flow modes of the intrachamb...

Download PDF file
  • EP ID EP528251
  • DOI 10.15587/1729-4061.2018.147671
  • Views 73
  • Downloads 0

How To Cite

Alesya Ishchenko, Marina Polyakova, Varvara Kuvaieva, Alexandr Nesteryuk (2018). Elaboration of structural representation of regions of scanned document images for MRC model. Восточно-Европейский журнал передовых технологий, 6(2), 32-38. https://europub.co.uk/articles/-A-528251