Coboost learning of visual categories with 1st and 2nd order features from Google images

ABSTRACT

Conventional object recognition techniques rely heavily on manually annotated image datasets to achieve good performances. However, collecting high quality datasets is really laborious. In this paper, we propose a semi-supervised framework for learning visual categories from Google Images. The 1st and 2nd order features, which define bag of words representation and spatial relationship between local features respectively, make up an independent and redundant feature split. We then integrate a cotraining algorithm CoBoost with these two features. We create two boosting classifiers based on the 1st and 2nd order features respectively in the training, during which one classifier provides labels for the other. Besides, the 2nd order features are generated dynamically rather than extracted exhaustively to avoid high computation. An active learning technique is also introduced to further improve the performance. We evaluate our method on the benchmark datasets, showing results competitive with the state-of-the-art unsupervised approaches and some supervised techniques.

REFERENCES

• 1: T. L. Berg and D. A. Forsyth. Animals on the web. In CVPR,2006.
• 2: M. Collins and Y. Singer. Unsupervised models for named entity classification. In EMNLP/VLC, 1999.
• 3: R. Fergus, Feifei Li, P. Perona, and A. Zisserman. Learning object categories from google's image search. In ICCV, 2005.
• 4: Li-Jia Li, Gang Wang, and Feifei Li. OPTIMOL: automatic object picture collection via incremental model learning. In CVPR, 2007.
• 5: D. Liu, G. Hua, P. Viola, and T. Chen. Integrated Feature Selection and Higher-order Spatial Feature Extraction for Object Categorization. In CVPR, 2008.
• 6: A. Opelt, A. Fussenegger, and P. Auer. Weak Hypotheses and Boosting for Generic Object Detection and Recognition. In ECCV, 2004.
• 7: S. Savarese, A. Criminisi, and J. Winn. Discriminative Object Class Models of Appearance and Shape by Correlatons. In CVPR, 2006.
• 8: F. Schroff, A. Criminisi, and A. Zisserman. Harvesting image databases from the web. In ICCV, 2007.
• 9: J. Sivic, et al. Discovering Object Categories in Image Collections. In ICCV, 2005.
• 10: J. Zhang, et al. Local Features and Kernels for Classification of Texture and Object Categories: A Comprehensive Study. IJCV, 73(2):213--238, 2007.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.4 IMAGE PROCESSING AND COMPUTER VISION
      I.4.8 Scene Analysis
          Subjects: Object recognition

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval
          Subjects: Information filtering

General Terms:
Algorithms, Experimentation, Performance

Keywords:
1st and 2nd order features, co-training, coboost, learn categories