2 results for Allen, Gary

  • Automatic Recognition of Light Microscope Pollen Images

    Allen, Gary; Hodgson, Bob; Marsland, Stephen; Arnold, Greg; Flemmer, Rory; Flenley, John; Fountain, David (2006)

    Journal article
    Massey University

    This paper is a progress report on a project aimed at the realization of a low-cost, automatic, trainable system "AutoStage" for recognition and counting of pollen. Previous work on image feature selection and classification has been extended by design and integration of an XY stage to allow slides to be scanned, an auto focus system, and segmentation software. The results of a series of classification tests are reported, and verified by comparison with classification performance by expert palynologists. A number of technical issues are addressed, including pollen slide preparation and slide sampling protocols.

    View record details
  • An automated pollen recognition system : a thesis submitted to Massey University, Turitea, Palmerston North, New Zealand in fulfilment of the requirements for the degree of Master of Engineering

    Allen, Gary (2008-04-15T04:49:33Z)

    Masters thesis
    Massey University

    A system was developed with the aim of demonstrating that the tedious tasks of classifying and counting pollen on slides could be performed automatically to a standard comparable with that of human experts. Automation of pollen classification and counting will advance the science and range of applications of palynology. The system developed is a completely functioning prototype. After initial set up and training it is automatic in operation. System tests have demonstrated that the concept is viable and that the prototype developed is at a stage that it is of practical use to palynologists. There are opportunities for improvements and added functionality. Now that the system is developed and characterised, it provides a benchmark for gauging the efficacy of future improvements and adaptations. The system is presently adaptable to many different classification problems within palynology and would be adaptable for other automated microscopic classification or imaging tasks.

    View record details