KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Settings

Author: search.filters.author.Suwansukho, KajpanyaSubject: search.filters.subject.Fluorescent imaging

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Single-wavelength based thai jasmine rice identification with polynomial fitting function and neural network analysis
    (2013-09-18)
    Suwansukho, Kajpanya
    ;
    Sumriddetchkajorn, Sarun
    ;
    Buranasiri, Prathan
    We previously showed that a combination of image thresholding, chain coding, elliptic Fourier descriptors, and artificial neural network analysis provided a low false acceptance rate (FAR) and a false rejection rate (FRR) of 11.0% and 19.0%, respectively, in identify Thai jasmine rice from three unwanted rice varieties. In this work, we highlight that only a polynomial function fitting on the determined chain code and the neural network analysis are highly sufficient in obtaining a very low FAR of < 3.0% and a very low 0.3% FRR for the separation of Thai jasmine rice from Chainat 1 (CNT1), Prathumtani 1 (PTT1), and Hom-Pitsanulok (HPSL) rice varieties. With this proposed approach, the analytical time is tremendously suppressed from 4,250 seconds down to 2 seconds, implying extremely high potential in practical deployment. © 2013 SPIE.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Improvement of single wavelength-based Thai jasmine rice identification with elliptic Fourier descriptor and neural network analysis
    (2012-12-01)
    Suwansukho, Kajpanya
    ;
    Sumriddetchkajorn, Sarun
    ;
    Buranasiri, Prathan
    Instead of considering only the amount of fluorescent signal spatially distributed on the image of milled rice grains this paper shows how our single-wavelength spectral-imaging-based Thai jasmine (KDML105) rice identification system can be improved by analyzing the shape and size of the image of each milled rice variety especially during the image threshold operation. The image of each milled rice variety is expressed as chain codes and elliptic Fourier coefficients. After that, a feed-forward back-propagation neural network model is applied, resulting in an improved average FAR of 11.0% and FRR of 19.0% in identifying KDML105 milled rice from the unwanted four milled rice varieties. © Copyright SPIE.