TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Low-energy graph fourier basis functions span salient objects

Tutkimustuotosvertaisarvioitu

Yksityiskohdat

AlkuperäiskieliEnglanti
Otsikko2018 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2018 - Proceedings
KustantajaInstitute of Electrical and Electronics Engineers Inc.
Sivut1548-1552
Sivumäärä5
Vuosikerta2018-April
ISBN (painettu)9781538646588
DOI - pysyväislinkit
TilaJulkaistu - 10 syyskuuta 2018
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaIEEE International Conference on Acoustics, Speech, and Signal Processing - Calgary, Kanada
Kesto: 15 huhtikuuta 201820 huhtikuuta 2018

Julkaisusarja

Nimi
ISSN (elektroninen)2379-190X

Conference

ConferenceIEEE International Conference on Acoustics, Speech, and Signal Processing
MaaKanada
KaupunkiCalgary
Ajanjakso15/04/1820/04/18

Tiivistelmä

There is an emerging interest aiming at defining principles for signals on general graphs, which are analogous to the basic principles in traditional signal processing. One example is the Graph Fourier Transform which aims at decomposing a graph signal into its components based on a set of basis functions with corresponding graph frequencies. It has been observed that most of the important information of a graph signal is contained inside the low frequency band, which leads to several applications such as denoising, compression, etc. In this paper, we show that the low frequency basis functions span the salient regions in an image, which can also be considered as important regions. Motivated by this, we present a novel simple and unsupervised method to utilize a number of low-energy basis functions and show that it improves the performance of seven state-of-the-art salient object detection methods in five datasets under four different evaluation criteria, with only minor exceptions.

Tutkimusalat

Julkaisufoorumi-taso