Facial Pattern Recognition
Alongside the work on third order networks, a parallel experiment on face recognition was pursued using two-dimensional image moments and geneticallybred first-order backpropagation networks. Moments and functions of moments have been used as pattern features in many applications to achieve invariant recognition of two-dimensional image patterns [TEAG80]_[KHOT90]_[PERA92]_[REDD81]_[LO89]. Such features capture global information about the image and, unlike Fourier descriptors, do not require closed boundaries. Moment invariants were first proposed by Hu [HU62]_in 1961 using non-linear combinations of regular(geometric) moments which are invariant under scale, translation, and rotation image transformations.
KeywordsFace Recognition Facial Image Machine Intelligence Contrast Level Moment Invariant
Unable to display preview. Download preview PDF.
- [GALT88]Sir F. Galton, “Personal Identification and description-II”, Nature 173–177,21 June 1888.Google Scholar
- [GONZ92]R.C. Gonzalez, R.E. Woods, Digital Image Processing, Addison-Wesley, Reading, Mass., 1992.Google Scholar
- [HORN75]B. Horn,“Obtaining Shape from Shading”, The Psychology of Computer Vision, McGraw-Hill, 1975.Google Scholar
- [HU62]M. Hu, “Visual Pattern Recognition by Moment Invariants”, IRE Trans. on Information Theory, pp.l79-187, Feb.1962.Google Scholar
- [KRZY88]Krzyzak, S.Y. Leung, C.Y.Suen, “Reconstruction of two-dimensional patterns by Fourier descriptors”, Proceedings of the 9th ICPR, Rome, pp.555–558, Nov 1988.Google Scholar
- [LO89]C-H. Lo, H-S. Don, “3-D Moment Forms: Their Construction and Application to Object Identification and Positioning”, IEEE Trans. on Pattern Analysis and Machine Intelligence, Vol.11, No. 10, Oct 1989.Google Scholar
- [MHU62]M-K. Hu, “Visual Pattern Recognition by Moment Invariants”, IRE Trans. on Information Theory, pp. 179–187, Feb 1962.Google Scholar
- [PEAR24]K. Pearson, “Photographic Researches and Portrature”, Vol.2, Chapter XII, pp.283–333. Cambridge University Press, Cambridge (1924).Google Scholar
- [SU82]Y.N. Su, H.H. Arsenault, G. April, “Rotational Invariant Digital Pattern Recognition using Circular Harmonic Expansion”, Applied Optics, Vol.2l, pp.4012–4015, 1982.Google Scholar
- [UWEC94]O. Uwechue, P. Luebbers, “Numerical Optimization Techniques in Neural Networks and Robotics: a survey of Genetic Algorithms and Evolutionary Programming”, Proc. of IMACS Symposium, Lille(France), 1994.Google Scholar