Toward an Optimal Object-Oriented Image Classification Using SVM and MLLH Approaches

被引:0
作者
Malik, Ryad [1 ]
Kheddam, Radja [1 ]
Belhadj-Aissa, Aichouche [1 ]
机构
[1] USTHB, Image Proc & Radiat Lab, Algiers, Algeria
来源
2015 FIRST INTERNATIONAL CONFERENCE ON NEW TECHNOLOGIES OF INFORMATION AND COMMUNICATION (NTIC) | 2015年
关键词
Satellite image; Object-oriented classification; SVM; MLLH; Multi-scale segmentation; SUPPORT VECTOR MACHINES; SEGMENTATION; INTEGRATION; GIS;
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Support Vector Machines (SVM) and Maximum Likelihood (MLLH) are the most popular remote sensing image classification approaches. In the past, SVM and MLLH have been tested and evaluated only as pixel-based image classifiers. Moving from pixel-based analysis to object-based analysis, a fuzzy classification concept is used through eCognition software [1]. In this paper, SVM and MLLH are separately adopted and compared for multi-class object-oriented classification process where the input features vector contains primitive image objects produced by a multi-resolution segmentation algorithm. In this study, the determination of suitable object segmentation scale leading to an improved object-oriented classification result is also discussed and performed. Comparative analysis clearly revealed that higher overall classification accuracy (97%) was observed in the object-based classification using the optimal segmentation scale.
引用
收藏
页数:6
相关论文
共 28 条
  • [1] Al-Ahmadi F. S., 2009, Journal of King Abdulaziz University - Earth Sciences, V20, P167, DOI 10.4197/Ear.20-1.9
  • [2] Fine spatial resolution simulated satellite sensor imagery for land cover mapping in the United Kingdom
    Aplin, P
    Atkinson, PM
    Curran, PJ
    [J]. REMOTE SENSING OF ENVIRONMENT, 1999, 68 (03) : 206 - 216
  • [3] Baatz M., 2000, ANGEW GEOGRAPHISCHE, P12, DOI DOI 10.3390/RS5010183
  • [4] Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information
    Benz, UC
    Hofmann, P
    Willhauck, G
    Lingenfelder, I
    Heynen, M
    [J]. ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING, 2004, 58 (3-4) : 239 - 258
  • [5] Comparison of very high spatial resolution satellite image segmentations
    Carleer, A
    Debeir, O
    Wolff, E
    [J]. IMAGE AND SIGNAL PROCESSING FOR REMOTE SENSING IX, 2004, 5238 : 532 - 542
  • [6] SPLIT-AND-MERGE IMAGE SEGMENTATION BASED ON LOCALIZED FEATURE ANALYSIS AND STATISTICAL TESTS
    CHEN, SY
    LIN, WC
    CHEN, CT
    [J]. CVGIP-GRAPHICAL MODELS AND IMAGE PROCESSING, 1991, 53 (05): : 457 - 475
  • [7] De Kok R., 1999, International of Archives Photogrammetry and Remote Sensing, V32
  • [8] An evaluation of per-parcel land cover mapping using maximum likelihood class probabilities
    Dean, AM
    Smith, GM
    [J]. INTERNATIONAL JOURNAL OF REMOTE SENSING, 2003, 24 (14) : 2905 - 2920
  • [9] Definiens eCognition, 2009, DEF ECOGNITION DEV R
  • [10] Preliminary evaluation of eCognition object-based software for cut block delineation and feature extraction
    Flanders, D
    Hall-Beyer, M
    Pereverzoff, J
    [J]. CANADIAN JOURNAL OF REMOTE SENSING, 2003, 29 (04) : 441 - 452