DOIONLINE

DOIONLINE NO - IJAECS-IRAJ-DOIONLINE-1801

Publish In
International Journal of Advances in Electronics and Computer Science-IJAECS
Journal Home
Volume Issue
Issue
Volume-2, Issue-3  ( Mar, 2015 )
Paper Title
Fabric Defect Detection Based On Set Of Geometric Features For Neural Network
Author Name
Sharda P. Jadhav, M.S.Biradar
Affilition
ME IInd Year Student, Siddhant College of Engg, Sudumbre, Pune HOD Department of Electronics, Siddhant College of Engg, Sudumbre, Pune
Pages
36-40
Abstract
In this paper we proposed a method for automatic fabric defect detection based on neural network. Neural network is widely used to extract features from images for texture segmentation. Feature vector for every pixel is extracted from gray level arrangement of neighboring pixels, and this change is used to segment the defects. The feature vector for every pixel is extracted from gray level arrangement of neighboring pixel. Till now more work is carried out on defect detection but not on defect classification. The proposed scheme involves two challenging problem .i.e. defect detection and defect classification. Scene analysis and feature selection play an important role in classification process. an appropriate set of geometric features is taken into account in order to address the problem of neural network-based textile defect classification. Statistical approach is used to extract the features. Keywords- Fabric Defect, Defect Detection, Neural network, Feature Extraction.
  View Paper