Abstract

A new method has been developed for representing the key points of images by vectors in attribute space. The method is based on an algorithm for the adaptive construction of new attributes on the basis of descriptions obtained ahead of time by using the “speeded-up robust features” method for a series of images recorded indoors from different aspects. Experimental studies of the model thus developed on various series of images shows that this method can be used in practice to solve the image-correlation problem, provided that a preliminary training stage of the given model is carried out.

© 2010 Optical Society of America

Image scale determination for optimal texture classification using coordinated clusters representation

Evguenii V. Kurmyshev, Marian Poterasu, and Jose T. Guillen-Bonilla
Appl. Opt. 46(9) 1467-1476 (2007)

Effect on null spaces of list-mode imaging systems due to increasing the size of attribute space

Eric Clarkson and Meredith Kupinski
J. Opt. Soc. Am. A 38(3) 387-394 (2021)

Intraclass and between-class training-image registration for correlation-filter synthesis

Abhijt Mahalanobis, B. V. K. Vijaya Kumar, and Robert T. Frankot
Appl. Opt. 39(17) 2918-2924 (2000)

Optimization of a three-dimensional digital image correlation system for deformation measurements in extreme environments

Bing Pan, Dafang Wu, and Liping Yu
Appl. Opt. 51(19) 4409-4419 (2012)

Independent spectral representations of images for recognition

Xiuwen Liu and Lei Cheng
J. Opt. Soc. Am. A 20(7) 1271-1282 (2003)