Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

Robust Planar Shape Recognition Using Spectrum Analyzer and Fuzzy ARTMAP

스펙트럼 분석기와 퍼지 ARTMAP 신경회로망을 이용한 Robust Planar Shape 인식

  • 한수환 (동의대학교 전자통신공학과)
  • Published : 1997.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper deals with the recognition of closed planar shape using a three dimensional spectral feature vector which is derived from the FFT(Fast Fourier Transform) spectrum of contour sequence and fuzzy ARTMAP neural network classifier. Contour sequences obtained from 2-D planar images represent the Euclidean distance between the centroid and all boundary pixels of the shape, and are related to the overall shape of the images. The Fourier transform of contour sequence and spectrum analyzer are used as a means of feature selection and data reduction. The three dimensional spectral feature vectors are extracted by spectrum analyzer from the FFT spectrum. These spectral feature vectors are invariant to shape translation, rotation and scale transformation. The fuzzy ARTMAP neural network which is combined with two fuzzy ART modules is trained and tested with these feature vectors. The experiments including 4 aircrafts and 4 industrial parts recognition process are presented to illustrate the high performance of this proposed method in the recognition problems of noisy shapes.

본 논문은 산업분야의 군사적으로 많이 사용되고 있는 planar shape의 인식을 스펙트럼 분석기를 이용하여 FFT 스펙트럼으로부터 추출된 3차원 특징 벡터와 신경회로망인 fuzzy ARTMAP을 이용하여 시도되었다. 외곽선 정보를 추출하여 이를 원점으로 이동시키고 각 경계점들과 원점들과의 유클리드 거리를 구하여 이를 다시 FFT스펙트럼과 스펙트럼 분석기를 통하여 3차원 특징 벡터를 추출하였다. 이 3차원 데이터는 이동, 회전, 크기에 무관한 값으로 fuzzy ARTMAP에 입력값으로 사용하였다. Fuzzy ARTMAP은 두개의 fuzzy ART 모듈을 가지고 있으며 위에서 구한 특징 벡터들에 의해 학습되고 실험되어 진다.본 논문에 포함된 실험은 4개의 비행기와 4개의 산업부품을 이용하여 잡음이 섞인 shape의 인식에 있엇 제시된 방법이 좋은 인식률을 기록함을 보여주고 있다.

Keywords

References

  1. Pattern Recognition v.21 no.3 Invariant Planar Shape Recognition Using Dynamic Alignment L.Gupta;M.D.Srinath
  2. Pattern Recognition v.21 no.6 Planar shape matching based on binary tree shape representayion J.G.Leu;I.N.Husang
  3. Ph.D. Thesis Rotation, translation and scale invariant 2-D object recognition using spectral analysis and a hybrid neural network B.H.Cho
  4. Pattern Recognition v.23 no.6 A neural network aproach to robust shape classification L.Gupta;M.R.Sayeh;R.Tammana
  5. Pattern Recognition v.25 no.9 Robust position, scale, and rotation invariant object recognition using higher-order neural network Lilly;M.B.Reid
  6. IEEE Trans. Neural networks v.3 no.5 Fuzzy ARTMAP:A neural network architecture for incremental supervised learning of analog multidimensional maps G.A.Carpenter;S.Grossberg;N.Markkuzon
  7. the 1993 INNS Annual Meeting (World Con-gress on Neural Networks) v.1 Quantitative Study of the QRS Complex Using Fuzzy ARTMAP and the MIT/BIH Arrhythmia Database F.M.Ham;Soowhan Han
  8. Journal of Fuzzy Logic and Intelligent Systems v.5 no.4 A New Approach For Off-line Signature Verification Using Fuzzy ARTMAP Soowhan Han
  9. IEEE Trans. Biomedical Eng. v.43 no.4 Classification of Cardiac Arrhymia Using Fuzzy ARTMAP F.M.Ham;Soowhan Han
  10. Digital Image Processing R.C.Gonzalez;R.E.Woods
  11. Digital Image Processing(2nd ed.) W.K.Pratt
  12. Digital Image Processing A.V.Oppenheim;R.W,Schafer
  13. Proc. 1971 Applications of Walsh Functions Symp. A power spectrum and related physical interpretation for the multidimensional BIFORE transform N.Ahmed;R.M.Bates
  14. IEEE trans. Inform. Theory v.IT-14 A generalized concept of freqency and some applications H.Harmuth
  15. Neural NetWorks v.4 Fuzzy ART-Fast stable learning and categorization of analog patterns by an Adaptive Reson ance System G.A.Carpenter;S.Grossberg;D.B.Rosn
  16. Proc. of IJCNN v.2 Fuzzy ART:An adaptive resonance algotithm for rapid, stable classification of analog patterns G.A.Carpenter;S.Grossberg;D.B.Rosen