Image transform bootstrapping and its applications to semantic scene classification

被引:15
|
作者
Luo, JB [1 ]
Boutell, M
Gray, RT
Brown, C
机构
[1] Eastman Kodak Co, Res & Dev Labs, Rochester, NY 14650 USA
[2] Univ Rochester, Dept Comp Sci, Rochester, NY 14627 USA
关键词
bootstrapping; exemplar-based learning; image transform; meta-classifier; semantic scene classification;
D O I
10.1109/TSMCB.2005.846677
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
The performance of an exemplar-based scene classification system depends largely on the size and quality of its set of training exemplars, which can be limited in practice. In addition, in nontrivial data sets, variations in scene content as well as distracting regions may exist in many testing images to prohibit good matches with the exemplars. Various boosting schemes have been proposed in machine learning, focusing on the feature space. We introduce the novel concept of image-transform bootstrapping using transforms in the image space to address such issues. In particular, three major schemes are described for exploiting this concept to augment training, testing, and both. We have successfully applied it to three applications of increasing difficulty: sunset detection, outdoor scene classification, and automatic image orientation detection. It is shown that appropriate transforms and meta-classification methods can be selected to boost performance according to the domain of the problem and the features/classifier used.
引用
收藏
页码:563 / 570
页数:8
相关论文
共 50 条
  • [1] Using image transform-based bootstrapping to improve scene classification
    Luo, JB
    Boutell, M
    Gray, RT
    Brown, C
    [J]. STORAGE AND RETRIEVAL METHODS AND APPLICATIONS FOR MULTIMEDIA 2004, 2004, 5307 : 200 - 211
  • [2] Research on the Classification of Image Semantic Scene
    Zhang Fang
    Guo Huiling
    Jia Lingshan
    [J]. PROCEEDINGS OF THE 2015 INTERNATIONAL INDUSTRIAL INFORMATICS AND COMPUTER ENGINEERING CONFERENCE, 2015, : 162 - 165
  • [3] Semantic Scene Classification for Image Annotation and Retrieval
    Cavus, Oezge
    Aksoy, Selim
    [J]. STRUCTURAL, SYNTACTIC, AND STATISTICAL PATTERN RECOGNITION, 2008, 5342 : 402 - 410
  • [4] Semantic-based Scene Image Classification
    Wang, Xiaoru
    Du, Junping
    Liu, Jie
    [J]. PROCEEDINGS OF 2011 INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENCE AND AWARENESS INTERNET, IET AIAI2011, 2011, : 150 - 153
  • [5] Semantic embedding: scene image classification using scene-specific objects
    Mohammad Javad Parseh
    Mohammad Rahmanimanesh
    Parviz Keshavarzi
    Zohreh Azimifar
    [J]. Multimedia Systems, 2023, 29 : 669 - 691
  • [6] Semantic embedding: scene image classification using scene-specific objects
    Parseh, Mohammad Javad
    Rahmanimanesh, Mohammad
    Keshavarzi, Parviz
    Azimifar, Zohreh
    [J]. MULTIMEDIA SYSTEMS, 2023, 29 (02) : 669 - 691
  • [7] Tag-Based Semantic Features for Scene Image Classification
    Sitaula, Chiranjibi
    Xiang, Yong
    Basnet, Anish
    Aryal, Sunil
    Lu, Xuequan
    [J]. NEURAL INFORMATION PROCESSING (ICONIP 2019), PT III, 2019, 11955 : 90 - 102
  • [8] VERY HIGH RESOLUTION IMAGE SCENE CLASSIFICATION WITH SEMANTIC FISHER VECTORS
    Chaib, Souleyman
    Gu, Yanfeng
    Yao, Hongxun
    Belkadi, Khaled
    [J]. IGARSS 2018 - 2018 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM, 2018, : 6844 - 6847
  • [9] Remote Sensing Image Scene Classification by Multiple Granularity Semantic Learning
    Guo, Weilong
    Li, Shengyang
    Yang, Jian
    Zhou, Zhuang
    Liu, Yunfei
    Lu, Junjie
    Kou, Longxuan
    Zhao, Manqi
    [J]. IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING, 2022, 15 : 2546 - 2562
  • [10] Image scene classification based on multi-scale and contextual semantic information
    Zhang, Rui-Jie
    Li, Bi-Cheng
    Wei, Fu-Shan
    [J]. Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2014, 42 (04): : 646 - 652