Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지

Adaptive Scene Classification based on Semantic Concepts and Edge Detection

시멘틱개념과 에지탐지 기반의 적응형 이미지 분류기법

  • Jamil, Nuraini (Computer and Information Engineering, Inha University) ;
  • Ahmed, Shohel (Computer and Information Engineering, Inha University) ;
  • Kim, Kang-Seok (Computer and Information Engineering, Inha University) ;
  • Kang, Sang-Jil (Computer and Information Engineering, Inha University)
  • ;
  • ;
  • 김강석 (인하대학교 정보공학과) ;
  • 강상길 (인하대학교 정보공학과)
  • Received : 2009.03.05
  • Accepted : 2009.04.10
  • Published : 2009.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Scene classification and concept-based procedures have been the great interest for image categorization applications for large database. Knowing the category to which scene belongs, we can filter out uninterested images when we try to search a specific scene category such as beach, mountain, forest and field from database. In this paper, we propose an adaptive segmentation method for real-world natural scene classification based on a semantic modeling. Semantic modeling stands for the classification of sub-regions into semantic concepts such as grass, water and sky. Our adaptive segmentation method utilizes the edge detection to split an image into sub-regions. Frequency of occurrences of these semantic concepts represents the information of the image and classifies it to the scene categories. K-Nearest Neighbor (k-NN) algorithm is also applied as a classifier. The empirical results demonstrate that the proposed adaptive segmentation method outperforms the Vogel and Schiele's method in terms of accuracy.

개념 기반 이미지풍경 분류 기법은 데이터베이스에 있는 대량의 이미지 를 카테고리별로 구분하는 많이 적용되는 응용분야이다. 풍경이 속하는 카테고리를 알면 데이터베이스에서 해변, 산, 숲, 필드와 같은 필요한 풍경사진을 찾고자 할 때 불필요한 이미지를 필터링하여 신속하고 정확하게 찾을 수 있다. 본 논문에서는 이미지 분류를 위한 시멘틱 모델링 기반의 적응 세그멘테이션 기법을 제안 한다. 잔디, 물, 하늘과 같은 시멘틱 개념에 따른 이미지를 서브구역으로 나누어 세그멘테이션을 한다. 세그멘테이션은 에지탐색을 이용하고 또한 K-Nearest(K-NN)를 이용하여 세그멘테이션을 한다. 세그멘테이션 과정에서 이미지의 복잡도에 따라 적응적으로 서브구역으로 나눈다. 실험에서는 Vosel과 schiele가 제안한 방법과의 비교를 통해서 정확도면에서 제안된 연구의 우수성을 보여준다.

Keywords

References

  1. Barnard, K. and D. Forsyth, "Learning the Semantics of Words and Pictures", Proceeding of International Conference on Computer Vision, (2001), 408-415.
  2. Canny, J., "A Computational Approach To Edge Detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.8 (1986), 679-698.
  3. Duda R. O., P. E. Hart, D. G. Stork, Pattern Classification 2nd Edition, A Wiley-Interscience Publication, 2000.
  4. Embry, A., "An Adaptive Variable Block Size Transform Coding System with Lagrangian Cost Function Decision Criterion", Technical Report, EE 368B, Dept. of Computer Science, Stanford Univ., 2000.
  5. Fan, J., K. David, Y. Yau, K. Ahmed, and G. Walid, "Automatic Image Segmentation by Integrating Color-Edge Extraction and Seeded Region Growing", IEEE Transactions On Image Processing, Vol.10(2001), 1454-1466. https://doi.org/10.1109/83.951532
  6. Heath, M. D, S. Sarkar, T. Sanocki, and K. Bowyer, "A Robust Visual Method for Assessing the Relative Performance of Edge-Detection Algorithms", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.12(1997), 1338-1359.
  7. Huang, J., S. R. Kumar, and R. Zabih, "An Automatic Hierarchical Image Classification Scheme", Proceeding of 6th ACM Intenational Conference on Multimedia, 1998.
  8. Manjunath, B. S., P. Salembier, and T. Sikora, Introduction to MPEG-7 Multimedia Content Description Interface. John Wiley and Sons Ltd., England, 2002.
  9. Mojsilovic, A., J. Gomes, and B. Rogowitz, "Semantic-friendly indexing and querying of images based on the extraction of the objective semantic cues", International Journal of Computer Vision, Vol.56, No.1/2(2004), 79-107. https://doi.org/10.1023/B:VISI.0000004833.39906.33
  10. Murphy, K., A. Torralba, and W. Freeman, "Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes", Advances in Neural Information Processing Systems, Vol.16(2004).
  11. Oliva, A. and A. Torralba, "Modeling the shape of the scene: A holistic representation of the spatial envelope", International Journal of Computer Vision, Vol.42, No.3(2001), 145-175 https://doi.org/10.1023/A:1011139631724
  12. Pratt, W. K., Digital Image Processing. New York NY: Wiley, 1978.
  13. Smeulders, A., M. Worring, S. Santini, A. Gupta, and R. Jain, "Content-based image retrieval at the end of the early years", IEEE Transactions on Pattern Amalysis and Machine Interlligence, Vol.22, No.12(2000), 1349-1380. https://doi.org/10.1109/34.895972
  14. Szummer, M. and R. Picard, "Indoor-outdoor image classification", International Workshop on Content-based Access of Image and Video Databases, Bombay, India, 1998.
  15. Tamura, H., S. Mori, and T. Yamawaki, "Texture features corresponding to visual perception", IEEE Transactions System Man, and Cybernetics, Vol.8, No.6(1978).
  16. Vailaya, A., M. Figueiredo, A. Jain, and H. Zhang, "Image classification for content-based indexing", IEEE Transactions on Image Processing, Vol.10, No.1(2001), 117-130. https://doi.org/10.1109/83.892448
  17. Vogel, J. and B. Schiele, "Natural Scene Retrieval based on a Semantic Modeling Step", Conference on Image and Video Retrieval, Dublin, Ireland, 2004.
  18. Yan, R. MATLABArsenal; a library for k-nearest neighbor (2006) Software available at http://www.informedia.cs.cmu.edu/yanrong/MATLAMATLABAr/MATLABArsenal.htm.