Fabric defect detection using local homogeneity and morphological image processing

In this paper, a new fabric detect detection algorithm based on local homogeneity and mathematical morphology is presented. In a first step, the local homogeneity of each pixel is computed to construct a new homogeneity image denoted as (H-image). Then a classical histogram is computed for the H-ima...

Full description

Saved in:
Bibliographic Details
Published in2016 International Image Processing, Applications and Systems (IPAS) pp. 1 - 5
Main Authors Rebhi, A., Abid, S., Fnaiech, F.
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.11.2016
Subjects
Fabric defect detection
Fabrics
Histograms
Inspection
local homogeneity (H-image)
Morphological operations
Morphology
Shape
Online AccessGet full text

Cover

More Information
Summary:In this paper, a new fabric detect detection algorithm based on local homogeneity and mathematical morphology is presented. In a first step, the local homogeneity of each pixel is computed to construct a new homogeneity image denoted as (H-image). Then a classical histogram is computed for the H-image to choose an optimal thresholding value to produce a corresponding binary image, which will be used to extract the optimal size and the shape of the Structuring Element (SE) for mathematical morphology. In a second step, the image is subjected to a series of morphological operations with this SE to detect the possible existing fabric defect. Simulation results exhibit accurate defect detection with low false alarms.
DOI:10.1109/IPAS.2016.7880062