Scale & rotation-invariant matching with curve chain
(English)In: IET Computer Vision, ISSN 1751-9632, E-ISSN 1751-9640Article in journal (Refereed) Submitted
This paper presents a new methodology that matches image geometry using a curve chain. A curve chain is defined as a 1-dimensional arrangement of curves. The idea is to match images without using local descriptors and apply this concept into applications. This paper have two contributions. First, we present a novel curve feature which is scale & rotation – invariant. Secondly, we present an efficient scale & rotational-invariant matching method which matches curve chains in the scene. The efficacy is benefited by three factors. Firstly, matching a 1-dimensional curve chain can achieve quadratic operations when dynamic programming is used. Secondly, curves are salient features that naturally reduce the dimensionality compared with scanning all possible locations. Thirdly, curves provide stable relational cues between neighbouring curves. Such stable relational cues reduce the computation to linear operations by avoiding searching all combinations of curves in dynamic programming. The advantages of the method has good potential to benefit application including point correspondence matching, object detection, etc. In point correspondence experiments our method yields a good total matching score on various image transformations. At the same time, the proposed method shows good potential of matching non-rigid object such as faces with scale & rotation invariance.
curve feature, matching, object detection
Electrical Engineering, Electronic Engineering, Information Engineering
Research subject Signal Processing
IdentifiersURN: urn:nbn:se:umu:diva-111189OAI: oai:DiVA.org:umu-111189DiVA: diva2:867853