Texture segmentation with a neural network

被引:2
|
作者
Jahn, H [1 ]
Halle, W [1 ]
机构
[1] German Aerosp Ctr, Inst Space Sensor Technol, Berlin, Germany
来源
NONLINEAR IMAGE PROCESSING X | 1999年 / 3646卷
关键词
segmentation; edge detection; edge preserving smoothing; neural networks; nonlinear dynamic systems; texture discrimination;
D O I
10.1117/12.341105
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A neural method for gray value segmentation now is applied to texture segmentation. The parallel-sequential algorithm is based on recursive nonlinear feature smoothing in a 4-neighborhood. The smoothed feature values then can be segmented using an adaptive adjacency criterion which defines a special graph structure, called the Feature Similarity Graph. The segments are the connected components of that graph. The combination of results from the different image features is done in a hierarchical process starting, like in the human visual system, with gray value segmentation. Besides segments with homogeneous gray value this process also provides texture elements which are the basis for the calculation of new image features. Then, first, the modulus of the gray value gradient is used as a new feature of the original image. The following segmentation basing on that feature provides regions which are homogeneous with respect to the mean gray value gradient. Furthermore, texel directions are calculated. That feature contains information on texture orientation of textured image regions. With these features the same neural segmentation method is able to separate not only regions with different mean gray values but also those with different textures.
引用
收藏
页码:92 / 99
页数:8
相关论文
共 50 条
  • [1] An assembly neural network for texture segmentation
    Goltsev, A
    [J]. NEURAL NETWORKS, 1996, 9 (04) : 643 - 653
  • [2] Road texture segmentation with a neural network
    Bonnet, W
    Fernandez-Maloigne, C
    Koudella, C
    [J]. ROAD VEHICLE AUTOMATION II: TOWARDS SYSTEMS INTEGRATION, 1997, : 392 - 399
  • [3] Texture Segmentation Based on Image Model and Neural Network
    Chen Zhenyu
    Sheng Wen
    Wang Guangjun
    Li Dehua(State Education Commission Laboratory for Image Processing and Intelligence Control
    [J]. Journal of Earth Science, 1999, (04) : 333 - 335
  • [4] Inhibitory connections in the assembly neural network for texture segmentation
    Goltsev, A
    Wunsch, DC
    [J]. NEURAL NETWORKS, 1998, 11 (05) : 951 - 962
  • [5] An approach in texture segmentation using multivalued neural network
    Stoiljkovic, LV
    Stojanovic, ND
    Milenovic, DR
    [J]. MELECON '98 - 9TH MEDITERRANEAN ELECTROTECHNICAL CONFERENCE, VOLS 1 AND 2, 1998, : 63 - 67
  • [6] Texture segmentation using a kernel modifying neural network
    Kameyama, K
    Mori, K
    Kosugi, Y
    [J]. IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, 1997, E80D (11) : 1092 - 1101
  • [7] Texture image segmentation based on improved wavelet neural network
    Feng, Deng-Chao
    Yang, Zhao-Xuan
    Qiao, Xiao-Jun
    [J]. ADVANCES IN NEURAL NETWORKS - ISNN 2007, PT 3, PROCEEDINGS, 2007, 4493 : 869 - +
  • [8] Texture image segmentation using structured artificial neural network
    Lee, AWH
    Tse, WF
    Cheng, LM
    Cheng, LL
    [J]. AUTOMATIC INSPECTION AND NOVEL INSTRUMENTATION, 1997, 3185 : 58 - 65
  • [9] Texture segmentation based on an adaptively fuzzy clustering neural network
    Wang, CB
    Wang, HB
    Mei, QB
    [J]. PROCEEDINGS OF THE 2004 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2004, : 1173 - 1176
  • [10] A Texture Integrated Deep Neural Network for Semantic Segmentation of Urban Meshes
    Yang, Yetao
    Tang, Rongkui
    Xia, Mengjiao
    Zhang, Chen
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2023, 16 : 4670 - 4684