Composition of SIFT features for robust image representation

Salvatore Gaglio, Ignazio Infantino, Salvatore Gaglio, Filippo Vella

Risultato della ricerca: Other

2 Citazioni (Scopus)

Abstract

In this paper we propose a novel feature based on SIFT (Scale Invariant Feature Transform) algorithm1 forthe robust representation of local visual contents. SIFT features have raised much interest for their power ofdescription of visual content characterizing punctual information against variation of luminance and change of viewpoint and they are very useful to capture local information. For a single image hundreds of key points are found and they are particularly suitable for tasks dealing with image registration or image matching. In this work we stretched the spatial coverage of descriptors creating a novel feature as composition of key points present in an image region while maintaining the invariance properties of SIFT descriptors. The number of descriptorsis reduced, limiting the computational weight, and at the same time a more abstract descriptor is achieved. The new feature is therefore suitable at describing objects and characteristic image regions.We tested the retrieval performance with a dataset used to test PCA SIFT2 and image matching capabilityamong images processed with affine transformations. Experimental results are reported.
Lingua originaleEnglish
Pagine754016-754016-7
Numero di pagine7
Stato di pubblicazionePublished - 2010

Fingerprint

Image Representation
Scale Invariant Feature Transform
Image matching
Mathematical transformations
Descriptors
Image Matching
Chemical analysis
Image registration
Invariance
Luminance
Image Registration
Affine transformation
Retrieval
Coverage
Limiting
luminance
Experimental Results
retrieval
invariance
Vision

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cita questo

Gaglio, S., Infantino, I., Gaglio, S., & Vella, F. (2010). Composition of SIFT features for robust image representation. 754016-754016-7.

Composition of SIFT features for robust image representation. / Gaglio, Salvatore; Infantino, Ignazio; Gaglio, Salvatore; Vella, Filippo.

2010. 754016-754016-7.

Risultato della ricerca: Other

Gaglio, S, Infantino, I, Gaglio, S & Vella, F 2010, 'Composition of SIFT features for robust image representation', pagg. 754016-754016-7.
Gaglio, Salvatore ; Infantino, Ignazio ; Gaglio, Salvatore ; Vella, Filippo. / Composition of SIFT features for robust image representation. 7 pag.
@conference{228da41df28b4dcfbe42a7c017e62d6f,
title = "Composition of SIFT features for robust image representation",
abstract = "In this paper we propose a novel feature based on SIFT (Scale Invariant Feature Transform) algorithm1 forthe robust representation of local visual contents. SIFT features have raised much interest for their power ofdescription of visual content characterizing punctual information against variation of luminance and change of viewpoint and they are very useful to capture local information. For a single image hundreds of key points are found and they are particularly suitable for tasks dealing with image registration or image matching. In this work we stretched the spatial coverage of descriptors creating a novel feature as composition of key points present in an image region while maintaining the invariance properties of SIFT descriptors. The number of descriptorsis reduced, limiting the computational weight, and at the same time a more abstract descriptor is achieved. The new feature is therefore suitable at describing objects and characteristic image regions.We tested the retrieval performance with a dataset used to test PCA SIFT2 and image matching capabilityamong images processed with affine transformations. Experimental results are reported.",
author = "Salvatore Gaglio and Ignazio Infantino and Salvatore Gaglio and Filippo Vella",
year = "2010",
language = "English",
pages = "754016--754016--7",

}

TY - CONF

T1 - Composition of SIFT features for robust image representation

AU - Gaglio, Salvatore

AU - Infantino, Ignazio

AU - Gaglio, Salvatore

AU - Vella, Filippo

PY - 2010

Y1 - 2010

N2 - In this paper we propose a novel feature based on SIFT (Scale Invariant Feature Transform) algorithm1 forthe robust representation of local visual contents. SIFT features have raised much interest for their power ofdescription of visual content characterizing punctual information against variation of luminance and change of viewpoint and they are very useful to capture local information. For a single image hundreds of key points are found and they are particularly suitable for tasks dealing with image registration or image matching. In this work we stretched the spatial coverage of descriptors creating a novel feature as composition of key points present in an image region while maintaining the invariance properties of SIFT descriptors. The number of descriptorsis reduced, limiting the computational weight, and at the same time a more abstract descriptor is achieved. The new feature is therefore suitable at describing objects and characteristic image regions.We tested the retrieval performance with a dataset used to test PCA SIFT2 and image matching capabilityamong images processed with affine transformations. Experimental results are reported.

AB - In this paper we propose a novel feature based on SIFT (Scale Invariant Feature Transform) algorithm1 forthe robust representation of local visual contents. SIFT features have raised much interest for their power ofdescription of visual content characterizing punctual information against variation of luminance and change of viewpoint and they are very useful to capture local information. For a single image hundreds of key points are found and they are particularly suitable for tasks dealing with image registration or image matching. In this work we stretched the spatial coverage of descriptors creating a novel feature as composition of key points present in an image region while maintaining the invariance properties of SIFT descriptors. The number of descriptorsis reduced, limiting the computational weight, and at the same time a more abstract descriptor is achieved. The new feature is therefore suitable at describing objects and characteristic image regions.We tested the retrieval performance with a dataset used to test PCA SIFT2 and image matching capabilityamong images processed with affine transformations. Experimental results are reported.

UR - http://hdl.handle.net/10447/103784

UR - http://spie.org/Publications/Proceedings/Paper/10.1117/12.843540

M3 - Other

SP - 754016-754016-7

ER -