Research Status and Prospect of Automated Fossil Identification Technology

The traditional identification method of fossils has always been tedious, inefficient, time-consuming and la- borious. It cannot satisfy the needs of fast and further development of paleontological studies already. At present, there are three kinds of automation technologies used to identify fossils including expert system, multivariate statistical analysis and artificial neural network. With recent advancements in digital cameras and computer vision, multivariate statistical analysis and artificial neural network have become more and more popular and important. The combination of them will be an inevitable trend in the field of automated fossil identification systems in the future.

[1]  J. J. Charles.  Automatic recognition of complete palynomorphs in digital images , 2009, Machine Vision and Applications.

[2]  R. Thunell,et al.  Fourier shape analysis and planktonic foraminiferal evolution; the Neogloboquadrina-Pulleniatina lineages , 1984 .

[3]  C. D. Burke,et al.  Recognition of fossil fresh water ostracodes: Fourier shape analysis , 1987 .

[4]  J. A. Ware,et al.  Artificial neural networks as potential classification tools for dinoflagellate cyst images: A case using the self-organizing map clustering algorithm , 2006 .

[5]  W. R. Riedel,et al.  IDENTIFY: a Prolog program to help identify fossils , 1989 .

[6]  Jane Annabel Garratt.  Morphological data from coccolith images using Fourier power spectra , 1992 .

[7]  A.W.G. Duller,et al.  A new approach to automated pollen analysis , 2000 .

[8]  A.W.G. Duller,et al.  Software Aspects of Automated Recognition of Particles: The Example of Pollen , 2005 .

[9]  Monique Thonnat,et al.  An expert system for the automatic classification and description of zooplanktons from monocular images , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[10]  Richard J. Howarth,et al.  The application of expert systems to the identification and use of microfossils in the petroleum industry , 1994 .

[11]  Luc Beaufort,et al.  Automatic recognition of coccoliths by dynamical neural networks , 2004 .

[12]  Nancy Healy-Williams,et al.  Fourier shape analysis of Globorotalia truncatulinoides from late Quaternary sediments in the southern Indian Ocean , 1983 .

[13]  Jörg Bollmann,et al.  Techniques for quantitative analyses of calcareous marine phytoplankton , 2002 .

[14]  Ps Quinn,et al.  Automated particle analysis: calcareous microfossils , 2005 .

[15]  Nancy Healy-Williams,et al.  Quantitative image analysys: Application to planktonic foraminiferal paleoecology and evolution , 1984 .

[16]  M. Berthod,et al.  Automatic classification of planktonic foraminifera by a knowledge-based system , 1994, Proceedings of the Tenth Conference on Artificial Intelligence for Applications.

[17]  Peter Alan Swaby,et al.  Integrating Artificial Intelligence and Graphics in a Tool for Microfossil Identification for Use in the Petroleum Industry , 1990 .

[18]  Adam P. Harrison,et al.  Feasibility of computer-aided identification of foraminiferal tests , 2009 .

[19]  Lionel Tarassenko,et al.  Guide to Neural Computing Applications , 1998 .

[20]  P. A. Swaby,et al.  VIDES: an expert system for visually identifying microfossils , 1992, IEEE Expert.

[21]  D. Dollfus,et al.  Fat neural network for recognition of position-normalised objects , 1999, Neural Networks.

[22]  D. R. Brough,et al.  The Fossil expert system , 1986 .

[23]  M. Berthod,et al.  Feasibility study of automatic identification of planktic foraminifera by computer vision , 1996 .