KMITL

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

Browse

Settings

Author: search.filters.author.Treebupachatsakul, TreesukonSubject: search.filters.subject.Image processing

Search Results

Now showing 1 - 3 of 3
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Auto focusing ophthalmoscope for smartphone
    (2020-10-29)
    Navaitthiporn, Nitipon
    ;
    Rithcharung, Preeyarat
    ;
    Wongpa, Chuttima
    ;
    Treebupachatsakul, Treesukon
    ;
    Pechprasarn, Suejit
    Several retinal pathologies can cause severe damages and may lead to permanent vision loss. Early diagnosis is highly recommended to take a precautionary measure to reduce the risk of ocular diseases. Therefore, an eye test by an ophthalmologist plays a crucial role. This does, however, require paying visit to a hospital, which becomes a burden for elders and patients with physical disabilities. Consequently, these patients usually get a late diagnosis and treatment, which the symptoms may have progressed and developed. Here, we develop an optical toolkit with engineered software for smartphones enabling the smartphone to take images of human retina as a direct ophthalmoscope. Thanks to the modern smartphone specifications, which usually come with high resolution cameras and sufficient computing power for the software. The optical toolkit illuminates an eye with an appropriate wavelength and light intensity and it has been provisionally tested for health and safety based on the ISO-10942 and IEC 62471 standards. An image processing algorithm is embedded in the software providing an auto focusing capability.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Microorganism image recognition based on deep learning application
    (2020-01-01)
    Treebupachatsakul, Treesukon
    ;
    Poomrittigul, Suvit
    The application of Machine Learning for microorganism, especially bacteria and yeast, recognition becomes attractive because it can reduce the analyzing time of microorganism classification and eliminates human error compare to the classic biological techniques. Therefore, the recognition of microorganism based on Deep Learning increases the efficiency and accuracy of diagnostic process of infected patient. This research studies the possibility to use image classification and deep learning method to recognize bacteria and yeast with the comparison of cell image data-quality between our standard-resolution dataset and high-resolution dataset. We purpose this implementation method of microorganism recognition system using Python programming and the Keras API with Tensorflow Machine Learning framework. The experimental results have shown that bacteria and yeast cell images from microscope are able to be recognized. From the experimental results compare the deep learning methodology of different quality image dataset, our standard resolution dataset could be applied for obtaining more than 80% accuracy of prediction bacteria and yeast.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Bacteria Classification using Image Processing and Deep learning
    (2019-06-01)
    Treebupachatsakul, Treesukon
    ;
    Poomrittigul, Suvit
    An automizing process for bacteria recognition becomes attractive to reduce the analyzing time and increase the accuracy of diagnostic process. This research study possibility to use image classification and deep learning method for classify genera of bacteria. We propose the implementation method of bacteria recognition system using Python programing and the Keras API with TensorFlow Machine Learning framework. The implementation results have confirmed that bacteria images from microscope are able to recognize the genus of bacterium. The experimental results compare the deep learning methodology for accuracy in bacteria recognition standard resolution image use case. Proposed method can be applied the high-resolution datasets till standard resolution datasets for prediction bacteria type. However, this first study is limited to only two genera of bacteria.