Defect Detection in Texture using Statistical Approach and Principal Component Analysis
Main Article Content
Abstract
In this paper a system to detect and locate the faults in the fabric texture is proposed. In the proposed method, the image is divided into
four non-overlapping samples and then locally invariant to similarity features are extracted from each of the sample using statistical analysis.
The image is further divided till the statistical features extracted are at least 75% same from all the samples. Principal component analysis (PCA)
is used to receive feature vector describing each samples. Fuzzy C-means clustering (FCM) is used to classify all the samples in to two clusters,
defective and non defective that are defined using threshold value selected empirically. The validity test on the developed algorithm has been
performed with some fabric defect images. Experimental results show that the proposed method can detect fabric defect correctly.
Â
Keywords: Industrial automation, Statistical feature extraction, principal component analysis, Histogram data interpretation, Fuzzy C-means
clustering
Downloads
Article Details
COPYRIGHT
Submission of a manuscript implies: that the work described has not been published before, that it is not under consideration for publication elsewhere; that if and when the manuscript is accepted for publication, the authors agree to automatic transfer of the copyright to the publisher.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work
- The journal allows the author(s) to retain publishing rights without restrictions.
- The journal allows the author(s) to hold the copyright without restrictions.