文章基本信息

标题：A Novel Similarity Measure using a Normalized Hausdorff Distance for Trademarks Retrieval Based on Genetic Algorithm
本地全文：下载
作者：Marie Providence Umugwaneza ; Bei-ji Zou
期刊名称：International Journal of Computer Information Systems and Industrial Management Applications
印刷版ISSN：2150-7988
电子版ISSN：2150-7988
出版年度：2009
卷号：1
页码：312-320
出版社：Machine Intelligence Research Labs (MIR Labs)
摘要：In this paper we provide a novel measure based on direct Hausdorff distance (DHD). Most researchers have used the Euclidean distance (EUD) or DHD. We propose the use of normalized cosine distance (COSD) and EUD as finite set points instead of a set of image pixels. The proposed measure takes into account the integration of global and local features. For the performance assessment a genetic algorithm (GA) is applied to decide the best weight factors distribution. We have also used the retrieval efficiency equation in order to test the accuracy of the method. The obtained result showed that normalized Hausdorff distance (NHD) provides a significant improvement in retrieval accuracy and is robust against shape invariant transformations. Moreover, our shape retrieval algorithm proves to be efficient, promising and satisfies the human perception quite well.