RUS  ENG
Full version
JOURNALS // Computer Optics // Archive

Computer Optics, 2016 Volume 40, Issue 6, Pages 887–894 (Mi co341)

This article is cited in 1 paper

IMAGE PROCESSING, PATTERN RECOGNITION

Analysis of conditions that influence the properties of the constructed 3D-image features

N. G. Fedotova, A. A. Syemovb, A. V. Moiseevc

a Penza State University, Penza, Russia
b LLC «KomHelf», Penza, Russia
c Penza State Technological University, Penza, Russia

Abstract: In this article, we discuss theoretical results obtained using a new geometric method for 3D image analysis and recognition (a hypertrace transform). A mathematical model of the proposed method is briefly described. The theory of 3D image hypertriplet features with analytical structure is further developed. The feature properties are studied while they are being formed using a newly developed mathematical tool – a hypertrace matrix. The feature properties depend on a specific formation process and processing results of the hypertrace matrix.

Keywords: image, hypertrace transform, hypertrace matrix, hypertriplet feature, support grid on the sphere, features analytical structure.

Received: 14.06.2016
Accepted: 24.10.2016

DOI: 10.18287/2412-6179-2016-40-6-887-894



© Steklov Math. Inst. of RAS, 2024