International Journal of Internet, Broadcasting and Communication

  • 제10권4호
  • /
  • Pages.50-64
  • /
  • 2018
  • /
  • 2288-4920(pISSN)
  • /
  • 2288-4939(eISSN)
한국인터넷방송통신학회 (The Institute of Internet, Broadcasting and Communication)
권호 표지
DOI QR코드

DOI QR Code

Performance Improvement of Classifier by Combining Disjunctive Normal Form features

  • 투고 : 2018.09.15
  • 심사 : 2018.09.30
  • 발행 : 2018.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This paper describes a visual object detection approach utilizing ensemble based machine learning. Object detection methods employing 1D features have the benefit of fast calculation speed. However, for real image with complex background, detection accuracy and performance are degraded. In this paper, we propose an ensemble learning algorithm that combines a 1D feature classifier and 2D DNF (Disjunctive Normal Form) classifier to improve the object detection performance in a single input image. Also, to improve the computing efficiency and accuracy, we propose a feature selecting method to reduce the computing time and ensemble algorithm by combining the 1D features and 2D DNF features. In the verification experiments, we selected the Haar-like feature as the 1D image descriptor, and demonstrated the performance of the algorithm on a few datasets such as face and vehicle.

키워드

참고문헌

  1. Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, and Deva Ramanan, "Object Detection with Discriminatively Trained Part-Based Models", In IEEE Trans. PAMI, vol. 32, no. 9, 2010.
  2. H. Grabner and H. Bischof, "On-line boosting and vision", In IEEE Conference on CVPR, vol. 1, pages 260-267, 2006.
  3. Dong-Wook Kim, Woo-Youl kim, Jisang Yoo and Young-Ho Seo, "A Fast and Accurate Face Tracking Scheme by using Depth Information in Addition to Texture Information", Journal of Electrical Engineering & Technology, vol. 9, no. 2, pages 707-720, 2014. https://doi.org/10.5370/JEET.2014.9.2.707
  4. Y. Bai and M. Tang, "Robust Tracking via Weakly Supervised Ranking SVM", In IEEE Conference on CVPR, pp1854-1861, 2013.
  5. Oscar Martinez Mozos, Cyrill Stachniss, and Wolfram Burgard "Supervised Learning of Places from Range Data using Adaboost," In IEEE Robotics and Automation, pp. 1730-1735, 2005.
  6. Rainer Lienhart and Jochen Maydt, "An Extended Set of Haar-like Features for Rapid Object Detection," In IEEE Proc. Conference on Image Processing, vol. 1, pp. I-900-I-903, 2002.
  7. Zhu Teng, and D.J. Kang, "Disjunctive Normal Form of Weak Classifier for Online Learning based Object Tracking," In Proc. Conference on VISAPP, pp. 138-146, 2013.
  8. Paul Viola and Michael Jones, "Rapid Object Detection using a Boosted Cascade of Simple Features," In IEEE Proc. Conference on CVPR, vol. 1, pp. I-511-I-518, 2001.
  9. Takeshi Mita, Toshimitsu Kaneko, and Osamu Hori, "Joint Haar-like Features for Face Detection", In IEEE Conference on ICCV, vo1. 2, pp 1619-1626, 2005.
  10. Rong Xiao, Huaiyi Zhu, He Sun, and Xiaoou Tang, "Dynamic Cascades for Face Detection", In IEEE Conference on ICCV, pp.1-8, 2007.
  11. Timo Ojala, Matti Pietikainen, and Topi Maenpaa, "Multiresolution Gray-Scale and Rotation Invariant Texture Classifiecation with Local Binary Patterns", In IEEE Trans. PAMI, vol. 24, no. 7, pp. 971-987, 2002. https://doi.org/10.1109/TPAMI.2002.1017623
  12. Kobi Levi and Yair Weiss, "Learning Object Detection from a Small Number of Examples: the Importance of Good Features", In IEEE Proc. Conference on CVPR, vol.2, pp. II-53-II-60, 2004.
  13. Vo Quang Nhat and Gueesang Lee, "Illumination Invariant Object Tracking with Adaptive Sparse Representation", International Journal of Control, Automation, and Systems, vol. 12, no. 1, pp.195-201, 2014. https://doi.org/10.1007/s12555-013-0077-x
  14. D. Wang, H. Lu, and M.-H. Yang, "Online Object Tracking with Sparse Prototypes", In IEEE Trans. Image Processing, vol. 22, no.1, pp.314-325, 2013. https://doi.org/10.1109/TIP.2012.2202677
  15. Robert T. Collins, Yanxi Liu, and Marius Leordeanu, "Online Selection of Discriminative Tracking Features", In IEEE Trans. PAMI , vol. 27, no. 10, pp.1631-1643, 2005. https://doi.org/10.1109/TPAMI.2005.205