A new approach to automated pollen analysis

Palynological data are used in a wide range of applications, but the tasks of classification and counting of pollen grains are highly skilled and labo rious. The development of an automated system for pollen identification and classification would be of great benefit. Previous attempts at computer cl assification have taken approaches that have been intrinsically difficult t o develop into fully automated systems that could operate largely independe ntly of a human operator. We describe a new approach to the problem based o n improving the quality of the image processing rather than the data collec ted using images collected with an optical microscope. Two sets of experime nts are described, demonstrating the ability of the system firstly, to diff erentiate between pollen and detritus, and secondly, to classify different pollen types correctly. The results of these tests, in which the pollen ima ges were acquired using an automated system, are encouraging and demonstrat e that even using relatively low spatial resolution we can reliably differe ntiate between three taxa of pollen grains. Based upon the experience that we have gained we describe the characteristics required of the next generat ion of automated pollen identification and classification systems. (C) 2000 Elsevier Science Ltd. All rights reserved.