earticle

논문검색

Object Detection Using Hausdorff Distance and Multiclass Discriminative Field

초록

영어

In this paper, we present a novel object detection scheme using only local contour fragments. A sample fragment extraction method decomposes a whole contour into several parts. Then, the candidate locations of corresponding fragments in test images are detected by a modified Hausdorff distance with punishment on clutter edge regions. The most probable locations are selected by Multiclass Discriminative Field (MDF). Finally, contours of the objects can be drawn with these locations and sample fragments. Our major contributions are simplifying the MDF by an undirected graph constructed by the candidate locations and directly selecting the fragment locations by this MDF. The results on our postmark database and the ETHZ database from internet show that the proposed scheme is practicable.

목차

Abstract
 1. Introduction
 2. Local Fragment Detection
  2.1. Sample Fragment Extraction
  2.2. Candidate Location Detection
 3. Fragment Selection by MDF
  3.1. MDF Introduction
  3.2. Parameter Estimation
  3.3. Model Inference
 4. Experiments
 5. Conclusion
 Acknowledgements
 References

저자정보

  • Xiaofeng Zhang School of Computer Science and Technology, Nantong University
  • Hong Ding School of Computer Science and Technology, Nantong University
  • Rengui Cheng Department of Mathematics and Computer Science, Wuyi University

참고문헌

자료제공 : 네이버학술정보

    함께 이용한 논문

      ※ 원문제공기관과의 협약기간이 종료되어 열람이 제한될 수 있습니다.

      0개의 논문이 장바구니에 담겼습니다.