Skeleton Branch Distances for Shape Recognition

被引：0

作者：

Boluk, S. Arda ^{[1
]}

Demirci, M. Fatih ^{[1
]}

机构：

[1] TOBB Ekon & Teknol Univ, Bilgisayar Muhendisligi Bolumu, Ankara, Turkey

来源：

2015 23RD SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU) | 2015年

关键词：

Shape retrieval; shape matching; medial axis graph; Earth Mover's Distance; OBJECT RECOGNITION; IMAGE RETRIEVAL;

D O I：

暂无

中图分类号：

TM [电工技术]; TN [电子技术、通信技术];

学科分类号：

0808 ; 0809 ;

摘要：

In this paper, we presented a novel shape recognition framework based on medial axis graph. After extracting medial axis graph of a shape, we constructed a multi-dimensional distribution by calculating distances between each node and all of the branch nodes in the graph. Then similarity rates between these distributions is found by using a transportation-based distance function. At last, we compared our results with results of similar works conducted in the past.

引用

页码：552 / 555

页数：4

共 20 条

[1]

[Anonymous], 2013, ICCV

[2]

Ardizzone E., 1996, P 13 INT C PATT REC, VIII, P140

[3]

Aslan C, 2005, IEEE I CONF COMP VIS, P1339

[4] SHAPE DESCRIPTION USING WEIGHTED SYMMETRIC AXIS FEATURES [J].

BLUM, H ;

NAGEL, RN .

PATTERN RECOGNITION, 1978, 10 (03) :167-180

[5]

Blum H., 1967, A transformation for extracting descriptors of shape, P362

[6]

Boluk A., 2015, INT C COMP VIS THEOR

[7] Skeletal Shape Abstraction from Examples [J].

Demirci, M. Fatih ;

Shokoufandeh, Ali ;

Dickinson, Sven J. .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2009, 31 (05) :944-952

[8]

Eberly D., 1994, GEOMETRY DRIVEN DIFF, V1, P371

[9] The Amsterdam Library of Object Images [J].

Geusebroek, JM ;

Burghouts, GJ ;

Smeulders, AWM .

INTERNATIONAL JOURNAL OF COMPUTER VISION, 2005, 61 (01) :103-112

[10]

Lowe D.G., Object Recognition from Local SIF.pdf

← 1 2 →