Interactive image segmentation by matching attributed relational graphs

被引：32
作者：
Noma, Alexandre [1 ]
Graciano, Ana B. V. [1 ]
Cesar, Roberto M., Jr. [1 ]
Consularo, Luis A. [2 ]
Bloch, Isabelle [3 ]
机构：
[1] Univ Sao Paulo Rua Matao, Inst Math & Stat, BR-05508090 Sao Paulo, Brazil
[2] Tribunal Super Eleitoral, SAS, BR-70096900 Brasilia, DF, Brazil
[3] Telecom ParisTech, CNRS LTCI, F-75013 Paris, France
来源：
PATTERN RECOGNITION | 2012年 / 45卷 / 03期
基金：
巴西圣保罗研究基金会;
关键词：
Interactive image segmentation; Matching attributed relational graphs; Deformed graph; Spatial configuration; RECOGNITION;
D O I：
10.1016/j.patcog.2011.08.017
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
A model-based graph matching approach is proposed for interactive image segmentation. It starts from an over-segmentation of the input image, exploiting color and spatial information among regions to propagate the labels from the regions marked by the user-provided seeds to the entire image. The region merging procedure is performed by matching two graphs: the input graph, representing the entire image; and the model graph, representing only the marked regions. The optimization is based on discrete search using deformed graphs to efficiently evaluate the spatial information. Note that by using a model-based approach, different interactive segmentation problems can be tackled: binary and multi-label segmentation of single images as well as of multiple similar images. Successful results for all these cases are presented, in addition to a comparison between our binary segmentation results and those obtained with state-of-the-art approaches. An implementation is available at http://structuralsegm.sourceforge.net/. (C) 2011 Elsevier Ltd. All rights reserved.
引用
收藏
页码：1159 / 1179
页数：21
相关论文
共 35 条
  • [1] Adamek T., 2006, THESIS DUBLIN CITY U
  • [2] SEEDED REGION GROWING
    ADAMS, R
    BISCHOF, L
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 1994, 16 (06) : 641 - 647
  • [3] [Anonymous], 2001, Interactive Graph Cuts, DOI DOI 10.1109/ICCV.2001.937505
  • [4] [Anonymous], 2018, Mathematical Morphology in Image Processing, DOI DOI 10.1201/9781482277234-12/MORPHOLOGICAL-APPROACHSEGMENTATION-WATERSHED-TRANSFORMATION-BEUCHER-MEYER
  • [5] Bai X., 2007, P IEEE INT C COMP VI
  • [6] Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting
    Bai, Xue
    Sapiro, Guillermo
    [J]. INTERNATIONAL JOURNAL OF COMPUTER VISION, 2009, 82 (02) : 113 - 132
  • [7] Bal X., 2007, P INT C IM PROC
  • [8] Bunke H, 2000, INT C PATT RECOG, P117, DOI 10.1109/ICPR.2000.906030
  • [9] Inexact graph matching for model-based recognition:: Evaluation and comparison of optimization algorithms
    Cesar, RM
    Bengoetxea, E
    Bloch, I
    Larrañaga, P
    [J]. PATTERN RECOGNITION, 2005, 38 (11) : 2099 - 2113
  • [10] Consular L. A., 2007, P IEEE INT C IM PROC
1234