DOI QR코드

DOI QR Code

Extraction of Basic Insect Footprint Segments Using ART2 of Automatic Threshold Setting

자동 임계값 설정 ART2를 이용한 곤충 발자국의 인식 대상 영역 추출

  • 신복숙 (부산대학교 전자계산과) ;
  • 차의영 (부산대학교 전자계산과) ;
  • 우영운 (동의대학교 멀티미디어공학과)
  • Published : 2007.08.31

Abstract

In a process of insect footprint recognition, basic footprint segments should be extracted from a whole insect footprint image in order to find out appropriate features for classification. In this paper, we used a clustering method as a preprocessing stage for extraction of basic insect footprint segments. In general, sizes and strides of footprints may be different according to type and sire of an insect for recognition. Therefore we proposed an improved ART2 algorithm for extraction or basic insect footprint segments regardless of size and stride or footprint pattern. In the proposed ART2 algorithm, threshold value for clustering is determined automatically using contour shape of the graph created by accumulating distances between all the spots of footprint pattern. In the experimental results applying the proposed method to two kinds of insect footprint patterns, we could see that all the clustering results were accomplished correctly.

곤충의 발자국 패턴을 이용하여 곤충을 인식하고자 할 때에는 특징을 추출하기 위한 기본 단위의 영역을 추출할 필요가 있다. 이 논문에서는 기본 단위 영역의 추출을 위한 전 단계 처리 과정으로서 군집화 기법을 사용하였다. 인식의 대상이 되는 곤충들의 크기와 종류에 따라 남겨지는 발자국 패턴의 크기 및 간격이 다르게 나타난다. 따라서 이 논문에서는 패턴의 크기와 간격에 관계없이 인식의 기본 단위가 되는 영역을 추출할 수 있도록 하는 개선된 ART2 알고리즘을 제안하였다. 제안한 ART2 알고리즘에서는 군집화를 위한 임계값이 군집화의 대상이 되는 모든 패턴들의 거리를 축적한 그래프의 형태에 따라 자동으로 설정되도록 하였다. 제안한 기법으로 2 가지 종류의 곤충 발자국 패턴에 대하여 군집화를 실험한 결과 모두 바르게 군집화가 이루어짐을 알 수 있었다.

Keywords

References

  1. Connovation - equipment instructions, http://www.connovation.co.nz
  2. Desley A. Whisson, Richard M. Engeman and Kellie Collins, 'Developing relative abundance techniques (RATs) for monitoring rodent population,' Wildlife Research, Vol.32, pp.239-244, 2005 https://doi.org/10.1071/WR03128
  3. J. Russel, 'A recent survey of methods for closed populations of small mammals,' unpublished dissertation to STATS776 Animal Abundance Course (A), 2003
  4. Lea Deng, Daniel J. Bertinshaw, Reinhard Klette, Gisela Klette and Darryl Jeffries, 'Footprint identification of weta and other insects,' Technical Report in CITR, The University of Auckland, pp.191-196, 2004
  5. J. Gray, Animal Locomotion, Weidenfeld & Nicolson, London, 1968
  6. M. Sezgin and B. Sankur, 'Survey over image thresholding techniques and quantitative performance evaluation,' Journal of Electronic Imaging Vol.13, pp.146-165, 2004 https://doi.org/10.1117/1.1631315
  7. A. Rosenfeld and P. De la Torre, 'Histogram concavity analysis as an aid in threshold selection,' IEEE Trans. on System, Man and Cybernetics, Vol.13, pp.231-235, 1983
  8. Young W. Woo, 'Performance Evaluation of Binarizations of Scanned Insect Footprints,' LNCS 3322, Springer-Verlag, pp.669-678, 2004
  9. A.S. Abutaleb, 'Automatic thresholding of gray-level pictures using two-dimensional entropy,' Computer Vision Graphics Image Processing, Vol.47, pp.22-32, 1989 https://doi.org/10.1016/0734-189X(89)90051-0
  10. Nils Hasler, Reinhard Klette, Bodo Rosenhahn and Warren Agnew, 'Footprint recognition of rodents and insects,' Technical Report in CITR, The University of Auckland, 2004
  11. Simon Haykin, Neural Networks: A Comprehensive Foundation, McMillan, 1994
  12. Gail A Carpenter and Stephen Grossberg, 'The ART of Adaptive Pattern Recognition by a Self-Organizing Neural Network,' Journal of IEEE Computer, Vol.21, No.3, pp.77-88, 1988 https://doi.org/10.1109/2.33
  13. Gail A Carpenter and Stephen Grossberg, 'ART2: Self-Organization of Stable Category Recognition Codes for Analog Input patterns,' Applied Optics, Vol.26, No.23, pp.4919-4930, 1987 https://doi.org/10.1364/AO.26.004919