Selection of contour images based on alphabetical representation

V A Lomazov,D A Petrosov,O S Akupiyan,N I Korsunov,V I Lomazova

doi:10.1088/1742-6596/2032/1/012019

Abstract

The article is devoted to the actual problem of searching for contour images by given reference samples, due to the large amount of graphic scientific and technical information of the Contour type. Existing methods for image search do not allow taking into account the actual identity of images arising from affine transformations (stretching / compression, rotation) resulting from replication, which is important when analyzing graphic documentation. The paper proposes an alphabetical representation of contour images, which made it possible to construct a complex of affine-invariant equivalence relations. The relations built up served as the basis for the development of a set of selection procedures that can be considered as the initial stage of image search. The procedures included in the complex sequentially implement the reduction of the search scope up to a small set of contour images, allowing for the possibility of visual analysis. The complex is programmatically implemented in Python using the CUDA (NVIDIA GPU) software and hardware architecture for parallel computing.

Highlights

Automation of graphic data processing based on modern digital technologies is one of the important directions in improving existing methods and tools for analyzing information processing and managing complex systems, increasing the efficiency, reliability and quality of technical systems, which has led to great attention to this problem [1,2]
About 20% of the parts can be reused without modification, and about 18% can be reused with minor modifications.Таким образом, the purpose of this work is development of a selection procedure of contour images of machine parts, focused on the use of parallel computing technologies, which makes it possible to reduce the execution time of a search query, can be considered as relevant and practically significant
The developed alphabetical representation of contour images and the selection procedure built on its basis can significantly reduce the search area and makes possible search of the required images, either visually or based on more accurate methods of pattern recognition

Summary

Introduction

Automation of graphic data processing based on modern digital technologies is one of the important directions in improving existing methods and tools for analyzing information processing and managing complex systems, increasing the efficiency, reliability and quality of technical systems, which has led to great attention to this problem [1,2]. The task of finding digitized drawings and diagrams is especially acute, since the capabilities of existing systems for graphical retrieval of drawings and diagrams (using content-based retrieval [4,5], structure-oriented contour representation [6], sketch-based retrieval of drawings using spatial proximity [7], etc.) are still far from the desired (insufficient degree of compliance of the output with the user's requirements, little flexibility of the means of specifying queries, significant query execution time).

Objectives

Methods

Findings

Conclusion