MULTIPLE KEYWORDS ASSIGNMENT TO IMAGES USING SVM

摘要：

Use of semantic content is one of the important tasks in image analysis, which needs to be addressed for improving image retrieval effectiveness. We present a method to assign multiple keywords to image using SVMs. Images are divided into three-level regions called global image, semi-global images and sub-images. For each of them, color, texture and edge features are extracted. Then, the trained SVMs are employed and the results of classification are added based on the weight of the levels. The keywords are assigned according to the total of the results. Experiment results show the method is helpful to represent main contents of images.

关键词： Content-based image retrieval Support vector machines Classification

作者: YE JI YAN CHEN

作者单位: School of Economics & Management, Dalian Maritime University, Dalian 116023, China

会议类型: 国际会议

会议名称: 2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)

会议地点: 昆明

会议语种:英文

页码: 2569-2573

在线出版日期: 2008-07-12（万方平台首次上网日期，不代表论文的发表时间）