Distance interior ratio: A new shape signature for 2D shape retrieval

被引:31
|
作者
Kaothanthong, Natsuda [1 ]
Chun, Jinhee [2 ]
Tokuyama, Takeshi [2 ]
机构
[1] Thammasat Univ, Dept Comp Sci, Fac Sci & Technol, 99 Klongluang, Pathum Thani 12120, Thailand
[2] Tohoku Univ, Grad Sch Informat Sci, Aramaki Aza Aoba 6-3-09, Sendai, Miyagi 9808579, Japan
关键词
Shape signature; Shape retrieval; Homometric pair; RECOGNITION;
D O I
10.1016/j.patrec.2016.03.029
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this work, we propose a shape signature named Distance Interior Ratio (DIR) that utilizes intersection pattern of the distribution of line segments with the shape. To improve the efficiency of the histogram-based shape signature, we present a histogram alignment method for adjusting the interval of the histogram according to the distance distribution. The experimental result shows a 3.25% improvement using the proposed histogram alignment. When compared to other shape signatures, our experimental result gives a 77.69% retrieval rate using MPEG7 Part B dataset [Latecki, et al. (2000)[14]]. (C) 2016 Elsevier B.V. All rights reserved.
引用
收藏
页码:14 / 21
页数:8
相关论文
共 50 条
  • [1] Interior Distance Ratio to a Regular Shape for Fast Shape Recognition
    Li, Zekun
    Guo, Baolong
    Li, Cheng
    SYMMETRY-BASEL, 2022, 14 (10):
  • [2] 2D Shape Classification and Retrieval
    McNeill, Graham
    Vijayakumar, Sethu
    19TH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE (IJCAI-05), 2005, : 1483 - 1488
  • [3] Shape Retrieval Based on Centroid Distance Ratio and Shape Context
    Zhang, Shujun
    Li, Longzhuo
    2014 INTERNATIONAL CONFERENCE ON VIRTUAL REALITY AND VISUALIZATION (ICVRV2014), 2014, : 439 - 443
  • [4] A NEW SHAPE DESCRIPTOR 2D FOR CONTENT BASED IMAGE RETRIEVAL
    Silkan, Hassan
    Tmiri, Amal
    Ouatik, Said El Alaoui
    Lachkar, Abdelmounaime
    2014 SECOND WORLD CONFERENCE ON COMPLEX SYSTEMS (WCCS), 2014, : 670 - 674
  • [5] A combined distance measure for 2D shape matching
    Ramachandran, Geetha
    INTERNATIONAL CONFERENCE ON COMPUTER VISION AND IMAGE ANALYSIS APPLICATIONS, 2015,
  • [6] 2D SHAPE SIGNATURE BASED ON FRACTAL MEASUREMENTS MEASUREMENTS
    TAYLOR, RI
    LEWIS, PH
    IEE PROCEEDINGS-VISION IMAGE AND SIGNAL PROCESSING, 1994, 141 (06): : 422 - 430
  • [7] 2D shape recognition using maximum weighted distance
    Fac. Automat., Comp. and Electronics, University of Craiova, 13 Al. I. Cuza Street, RO-1100 Craiova, Romania
    Adv. Intell. Syst. Comput. Sci., (69-72):
  • [8] 2D shape segmentation: A new approach
    Wu, KN
    Levine, MD
    PATTERN RECOGNITION LETTERS, 1996, 17 (02) : 133 - 140
  • [10] ShapeLab A unified framework for 2D & 3D shape retrieval
    Pu, Jiantao
    Ramani, Karthik
    THIRD INTERNATIONAL SYMPOSIUM ON 3D DATA PROCESSING, VISUALIZATION, AND TRANSMISSION, PROCEEDINGS, 2007, : 1072 - 1079