Open AccessRapid region analysis for classification
Author(s) -
Rasche Christoph
Publication year - 2020
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2019.0273
Subject(s) - computer science , mnist database , artificial intelligence , pattern recognition (psychology) , pixel , ridge , maxima and minima , identification (biology) , contextual image classification , computer vision , image (mathematics) , deep learning , mathematics , cartography , geography , mathematical analysis , botany , biology
The authors describe and evaluate a method that detects ridges (symmetric axes) in an Euclidean distance map. The method detects ridge‐pixels with a local‐maxima search using only relational operations and has therefore minimal complexity. The resulting ridges exhibit a height profile that is suitable for region abstraction by means of simple parameterisation. The method is firstly evaluated on artificial stimuli with systematic shape variations using spatial jitter and contour fragmentation. Then it is mentioned, how the method can be used for developing region abstractions. Such abstractions have been already exploited in two tasks, hand‐written digit identification (MNIST database) and image classification (satellite images and images of urban/natural landscapes); the classification results of those systems are competitive.