A SEMANTICS BASED SEGMENTATION ALGORITHM FOR SCENE IMAGES

被引：0
|
作者：
Wang, Xiaoru [1 ]
Du, Junping [1 ]
Liu, Jie [1 ]
机构：
[1] Beijing Univ Posts & Telecommun, Beijing Key Lab Intelligent Telecommun Software &, Sch Comp Sci, Beijing, Peoples R China
来源：
2011 IEEE INTERNATIONAL CONFERENCE ON CLOUD COMPUTING AND INTELLIGENCE SYSTEMS | 2011年
基金：
中国国家自然科学基金;
关键词：
scene image segmentation; image semantics; region growth; region merging;
D O I：
10.1109/ICMTMA.2011.24
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
This paper proposes and evaluates a new semantics based segmentation algorithm for scene images. This algorithm has two phases: the initial segmentation based on color -spatial information and region merging based semantics information. The initial segmentation uses an automatic region growth method without the need of seeds. It avoids the loss of detailed color information of the scene images by using non -quantized colors in region growth. This paper also innovatively includes the underlying semantics of the scene images during the region merging. The experiments show the new segmentation algorithm is very efficient and effective and could get a very accurate segmentation for scene images. The main regions also match well to people's visual perception.
引用
收藏
页码：70 / 74
页数：5
相关论文
共 50 条
  • [21] A Benchmark for Endoluminal Scene Segmentation of Colonoscopy Images
    Vazquez, David
    Bernal, Jorge
    Javier Sanchez, F.
    Fernandez-Esparrach, Gloria
    Lopez, Antonio M.
    Romero, Adriana
    Drozdzal, Michal
    Courville, Aaron
    JOURNAL OF HEALTHCARE ENGINEERING, 2017, 2017
  • [22] CT Images Segmentation Algorithm Based on Graph Cuts
    Privalov, Maksim
    Kazantsev, Maksim
    2018 INTERNATIONAL SCIENTIFIC MULTI-CONFERENCE ON INDUSTRIAL ENGINEERING AND MODERN TECHNOLOGIES (FAREASTCON), 2018,
  • [23] Improving Gray World Algorithm Guided by Scene Semantics
    Xie M.
    Sun P.
    Lang Y.
    Wei Q.
    Shan D.
    Jisuanji Fuzhu Sheji Yu Tuxingxue Xuebao/Journal of Computer-Aided Design and Computer Graphics, 2022, 34 (01): : 152 - 162
  • [24] Normal region segmentation of road scene based on spatial context algorithm
    Chen X.-Y.
    Yao Q.
    Ding Q.-C.
    Bei X.-Y.
    Huang X.-Q.
    Jin X.
    Zhejiang Daxue Xuebao (Gongxue Ban)/Journal of Zhejiang University (Engineering Science), 2021, 55 (11): : 2013 - 2021
  • [25] Indoor scene segmentation algorithm based on full convolutional neural network
    Zijiang Zhu
    Deming Li
    Yi Hu
    Junshan Li
    Dong Liu
    Jianjun Li
    Neural Computing and Applications, 2021, 33 : 8261 - 8273
  • [26] Indoor scene segmentation algorithm based on full convolutional neural network
    Zhu, Zijiang
    Li, Deming
    Hu, Yi
    Li, Junshan
    Liu, Dong
    Li, Jianjun
    NEURAL COMPUTING & APPLICATIONS, 2021, 33 (14): : 8261 - 8273
  • [27] Detection and segmentation text from natural scene images based on graph model
    1600, World Scientific and Engineering Academy and Society, Ag. Ioannou Theologou 17-23, Zographou, Athens, 15773, Greece (10):
  • [28] Encoder-Decoder based Segmentation Model for UAV Street Scene Images
    Kumar, Satyawant
    Kumar, Abhishek
    Hong, Hye-Seong
    Lee, Dong-Gyu
    2023 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, ICCE, 2023,
  • [29] Fractal based texture segmentation and artifact object separation in natural scene images
    Yang, B
    Xu, GY
    Zhu, ZG
    INTERNATIONAL SYMPOSIUM ON MULTISPECTRAL IMAGE PROCESSING, 1998, 3545 : 450 - 453
  • [30] Image semantics segmentation using watershed algorithm
    Miao Chengliang
    Xie Shengli
    Yu Weiyu
    2006 IEEE INTERNATIONAL CONFERENCE ON SERVICE OPERATIONS AND LOGISTICS, AND INFORMATICS (SOLI 2006), PROCEEDINGS, 2006, : 925 - +
12345