作者: Miguel Angel Garcia , Domènec Puig
DOI: 10.1007/978-3-540-45243-0_18
关键词:
摘要: This paper presents and evaluates a pixel-based texture classifier that integrates multiple feature extraction methods through new scheme based on the Kullback J-divergence. Experimental results show proposed technique yields qualitatively better image segmentations than well-known both supervised unsupervised classifiers specific families of methods. A practical application to fabric defect detection is presented.