Logo
Logo

Goldsmiths - University of London

Medialness-based Shape Invariant Feature Transformation

Aparajeya, Prashant. 2016. Medialness-based Shape Invariant Feature Transformation. Doctoral thesis, Goldsmiths, University of London [Thesis]

No full text available
[img] Text (Medialness-based Shape Invariant Feature Transformation)
COM_thesis_AparajeyaP_2016.pdf - Accepted Version
Permissions: Administrator Access Only until 30 September 2019.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (123MB)

Abstract or Description

This research is about the perception-based medial point description of a natural form (2D static or in movement) as a generic framework for a part-based shape representation, which can then be efficiently used in biological species identification, as well as more general pattern matching and shape movement tasks. We consider recent studies and results in cognitive science that point in similar directions in emphasizing the likely importance of medialness as a core feature used by humans in perceiving shapes in static or dynamic situations. This leads us to define an algorithmic chain composed of the following main steps. The first step is one of fuzzy medialness measurements of 2D segmented objects from intensity images that emphasizes main shape information characteristic of an object's parts, e.g. concavities and folds along a contour. We distinguish interior from exterior shape description. Interior medialness is used to characterise deformations from straightness, corners and necks, while exterior medialness identifies the main concavities and inlands which are useful to verify parts extent and reason about articulation and movement. The second main step consists on defining a feature descriptor, we call ShIFT: Shape Invariant Feature Transform constructed from our proposed medialness­based discrete set, which permits efficient matching tasks when treating very large databases of images containing various types of 2D objects. Our defined shape descriptor ShIFT basically captures elementary shape cues and hence it is able to characterise any 2D shape. In summary, our shape descriptor is strongly footed in results from cognitive psychology while the algorithmic part is influenced by techniques from more traditional computer vision.

Item Type: Thesis (Doctoral)

Keywords:

Shape Psychophysics, 2D Shape Definition, Dominant Points, Medialness Representation, Feature Vector, Information Retrieval, Articulted Movement.

Departments, Centres and Research Units:

Computing

Date:

30 September 2016

Item ID:

19340

Date Deposited:

15 Dec 2016 09:32

Last Modified:

15 Dec 2016 09:43

URI: http://research.gold.ac.uk/id/eprint/19340

View statistics for this item...

Edit Record Edit Record (login required)