A comparison of classification algorithms within the Classifynder pollen imaging system

We describe an investigation into how Massey University's Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University's pollen reference collection (2890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. In addition to the Classifynder's native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples. © 2013 AIP Publishing LLC.

Evaluation of the In Situ Ichthyoplankton Imaging System (ISIIS): comparison with the traditional (bongo net) sampler

Plankton and larval fish sampling programs often are limited by a balance between sampling frequency (for precision) and costs. Advancements in sampling techniques hold the potential to add considerable efficiency and, therefore, add sampling frequency to improve precision. We compare a newly developed plankton imaging system, In Situ Ichthyoplankton Imaging System (ISIIS), with a bongo sampler, which is a traditional plankton sampling gear developed in the 1960s. Comparative sampling was conducted along 2 transects ~30–40 km long. Over 2 days, we completed 36 ISIIS tow-yo undulations and 11 bongo oblique tows, each from the surface to within 10 m of the seafloor. Overall, the 2 gears detected comparable numbers of larval fishes, representing similar taxonomic compositions, although larvae captured with the bongo were capable of being identified to lower taxonomic levels, especially larvae in the small (<5 mm), preflexion stages. Size distributions of the sampled larval fishes differed considerably between these 2 sampling methods, with the size range and mean size of larval fishes larger with ISIIS than with the bongo sampler. The high frequency and fine spatial scale of ISIIS allow it to add considerable sampling precision (i.e., more vertical sections) to plankton surveys. Improvements in the ISIIS technology (including greater depth of field and image resolution) should also increase taxonomic resolution and decrease processing time. When coupled with appropriate net sampling (for the purpose of collecting and verifying the identification of biological samples), the use of ISIIS could improve overall survey design and simultaneously provide detailed, process-oriented information for fisheries scientists and oceanographers.

A method to introduce accommodation cues into 3D integral imaging system using Fresnel holograms

Conventional 3D Integral imaging suffers from limited image depth range due to the fixed distance between the display panel and the lens array, while digital Fresnel holography suffers from a narrow viewing angle due to the lack of a high resolution spatial light modulator. This paper proposes an original system which combines the advantages of these two techniques to provide an integral imaging system of a reasonable viewing angle with accommodation cues. © 2012 Copyright Society of Photo-Optical Instrumentation Engineers (SPIE).

Optimized sinusoidal phase mask to extend the depth of field of an incoherent imaging system

Wavefront coding is a powerful technique that can be used to extend the depth of field of an incoherent imaging system. By adding a suitable phase mask to the aperture plane, the optical transfer function of a conventional imaging system can be made defocus invariant. Since 1995, when a cubic phase mask was first suggested, many kinds of phase masks have been proposed to achieve the goal of depth extension. In this Letter, a phase mask based on sinusoidal function is designed to enrich the family of phase masks. Numerical evaluation demonstrates that the proposed mask is not only less sensitive to focus errors than cubic, exponential, and modified logarithmic masks are, but it also has a smaller point-spread-function shifting effect. (C) 2010 Optical Society of America