izpis_h1_title_alt

Selecting features for object detection using an AdaBoost-compatible evaluation function
Fürst, Luka (Avtor), Fidler, Sanja (Avtor), Leonardis, Aleš (Avtor)

URLURL - Predstavitvena datoteka, za dostop obiščite http://www.sciencedirect.com/science/journal/01678655 Novo okno

Izvleček
This paper addresses the problem of selecting features in a visual object detection setup where a detection algorithm is applied to an input image represented by a set of features. The set of features to be employed in the test stage is prepared in two training-stage steps. In the first step, a feature extraction algorithm produces a (possibly large) initial set of features. In the second step, on which this paper focuses, the initial set is reduced using a selection procedure. The proposed selection procedure is based on a novel evaluation function that measures the utility of individual features for a certain detection task. Owing to its design, the evaluation function can be seamlessly embedded into an AdaBoost selection framework. The developed selection procedure is integrated with state-of-the-art feature extraction and object detection methods. The presented system was tested on five challenging detection setups. In three of them, a fairly high detection accuracy was effected by as few as six features selected out of several hundred initial candidates.

Jezik:Angleški jezik
Ključne besede:razpoznavanje vzorcev, računalniški vid, izbira značilnic, algoritem AdaBoost, detekcija objektov
Vrsta gradiva:Delo ni kategorizirano (r6)
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:FRI - Fakulteta za računalništvo in informatiko
Leto izida:2008
Založnik:Elsevier Science Inc.
Št. strani:str. 1603-1612
Številčenje:Vol. 29, no. 11
UDK:004.93'1
ISSN pri članku:0167-8655
COBISS.SI-ID:6494804 Povezava se odpre v novem oknu
Število ogledov:641
Število prenosov:204
Metapodatki:XML RDF-CHPDL DC-XML DC-RDF
 
Skupna ocena:(0 glasov)
Vaša ocena:Ocenjevanje je dovoljeno samo prijavljenim uporabnikom.
:
Objavi na: Bookmark and Share

Gradivo je del revije

Naslov:Pattern recognition letters
Skrajšan naslov:Pattern recogn. lett.
Založnik:North-Holland
ISSN:0167-8655
COBISS.SI-ID:26103296 Novo okno

Sekundarni jezik

Jezik:Neznan jezik
Ključne besede:pattern recognition, computer vision, feature selection, AdaBoost algorithm, object detection

Podobna dela

Podobna dela v RUL:
Podobna dela v drugih slovenskih zbirkah:

Komentarji

Dodaj komentar

Za komentiranje se morate prijaviti.

Komentarji (0)
0 - 0 / 0
 
Ni komentarjev!

Nazaj