KMITL

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

Browse

Settings

Subject: search.filters.subject.GLCM

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Surface roughness classification of mangosteen with gray level co-occurrence matrix based texture analysis
    (2018-07-02)
    Acharya, Anjali
    ;
    Phothisonothai, Montri
    ;
    Tantisatirapong, Suchada
    Mangosteen is one of the fruits that has an enormous export potential in Thailand. It is well-known as the queen of fruit. Mangosteen export generates large revenue; however, fruit is not defect free it contains many undesirable external as well as internal condition which results in the shipment rejection and decrease the reliability of the export. Therefore, this research investigates an approach for texture image analysis based surface roughness detection and classification into 3 classes: i.e., Glossy Surface, Mid Rough Surface and Extreme Rough Surface. In this study, for the first time, we propose the textural features extracted using Gray-Level Co-occurrence Matrix (GLCM) for surface roughness classification of mangosteen.
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Defect detection on air bearing surface with gray level co-occurrence matrix
    (2014-01-01)
    Kunakornvong, Pichate
    ;
    Tangkongkiet, Chiewchan
    ;
    Sooraksa, Pitikhate
    Air bearing surface (ABS) is the part of magnetic read/write head flying height controller. It is very important part in magnetic disk (hard disk drive), defected on ABS lead to crash between read/write head and disk surface, therefore its verifying is necessary. The best way to verify defect on ABS is machine vision. Main problem of machine vision in real world is variation of luminance intensity that affects image acquisition. This research proposes method for detecting defect on ABS which has variance luminance intensity, the Co-Occurrence Matrix is used to avoid the variance intensity of ABS image then feature parameter is defined by four identification features and defected detect by threshold that selected from Euclidean distance of each identification. The experimental results show very low error of defect detection on ABS by Co-Occurrence matrix and their identification feature. © 2014 IEEE.