In this study we propose a model-driven codebook generation method used to assign probability scores to pixels in order to represent underlying local shapes they reside in. In the first version of the symbol library we limited ourselves to photometric and similarity transformations applied on eight prototypical shapes of flat plateau, ramp, valley, ridge, circular and elliptic respectively pit and hill and used randomized decision forest as the statistical classifier to compute shape class ambiguity of each pixel. We achieved90% accuracy in identification of known objects from alternate views, however, we could not outperform texture, global and local shape methods, but only color-based method in recognition of unknown objects. We present a progress plan to be accomplished as a future work to improve the proposed approach further.

Symbolic feature detection for image understanding / S. Aslan, C.B. Akgul, B. Sankur (PROCEEDINGS OF SPIE, THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING). - In: Proceedings of SPIE / [a cura di] Niel Kurt S.. - [s.l] : The International Society for Optical Engineering (SPIE), 2014. - ISBN 9780819499417. - pp. 1-13 (( convegno Image Processing: Machine Vision Applications VII : 3 through 4 February tenutosi a San Francisco (CA, USA) nel 2014.

Symbolic feature detection for image understanding

S. Aslan
Primo
;
2014

Abstract

In this study we propose a model-driven codebook generation method used to assign probability scores to pixels in order to represent underlying local shapes they reside in. In the first version of the symbol library we limited ourselves to photometric and similarity transformations applied on eight prototypical shapes of flat plateau, ramp, valley, ridge, circular and elliptic respectively pit and hill and used randomized decision forest as the statistical classifier to compute shape class ambiguity of each pixel. We achieved90% accuracy in identification of known objects from alternate views, however, we could not outperform texture, global and local shape methods, but only color-based method in recognition of unknown objects. We present a progress plan to be accomplished as a future work to improve the proposed approach further.
local structure of images; model-driven dictionary construction; object recognition; pixel labelling;
Settore INFO-01/A - Informatica
2014
The Society for Imaging Science and Technology (IS and T)
The Society of Photo-Optical Instrumentation Engineers (SPIE)
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
aslan2014_SPIE.pdf

accesso riservato

Tipologia: Publisher's version/PDF
Dimensione 1.84 MB
Formato Adobe PDF
1.84 MB Adobe PDF   Visualizza/Apri   Richiedi una copia
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/1112436
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? 0
social impact