KMITL

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

Browse

Settings

Author: search.filters.author.Ngernplubpla, JaturonSubject: search.filters.subject.Neuro-fuzzy clustering

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Variance training data in image enhancement
    (2019-07-01)
    Ngernplubpla, Jaturon
    ;
    Chitsobhuk, Orachat
    This paper presents a study of neuro-fuzzy behavior in clustering gradient profile spectral characteristics. Various types of image scene are chosen to evaluate neuro-fuzzy performance. The combinations of training data subsets are learned by ANFIS model to generate gradient profile priors, which are used as optimum weight selection criteria for image enhancement. The experimental results illustrate quantitative performance improvement and perceptual improvement in recovery of the high-resolution details in various images.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Neuro-fuzzy profile clustering in image enhancement
    (2019-03-01)
    Ngernplubpla, Jaturon
    ;
    Chitsobhuk, Orachat
    This paper proposes a technique for clustering features into profile groups to obtain optimum enhancement weights for reconstructing high resolution images. Neuro-fuzzy model, which combines the fuzzy reasoning behavior with the adaptive learning capability and connectionist structure of neural networks, is adopted to analyze and learn with gradient data and statistics and to generate gradient profile priors. In enhancement process, the optimum weights are appropriately chosen according to the gradient profile priors. From the experimental results, the proposed algorithm demonstrates quantitative performance improvement in classifying data and perceptual improvement in recovery of the high-resolution image.