| 基于形状和纹理的外观设计专利图像检索方法 |
| |
| 引用本文： | 蔡念,张国宏,楼朋旭,戴青云. 基于形状和纹理的外观设计专利图像检索方法[J]. 山东大学学报(工学版), 2011, 41(2): 1-4 |
| |
| 作者姓名： | 蔡念 张国宏 楼朋旭 戴青云 |
| |
| 作者单位： | 广东工业大学信息工程学院, 广东 广州 510006 |
| |
| 基金项目： | 国家自然科学基金，广东省产学研项目，广东省信息产业厅项目 |
| |
| 摘 要： | 提出一种多特征融合的外观设计专利图像检索方法。形状特征融合了几何结构特征与边界方向直方图特征来描述,通过整体结构和轮廓特征的融合全面表达了物体的形状;纹理特征融合了Gabor小波提取的特征和提出的分块统计特征;最后采用加权法融合形状特征和纹理特征,实现外观设计专利图像检索。
|
| 关 键 词： | 外观设计专利 图像检索 边界方向直方图 纹理特征 多特征融合 |
| 收稿时间： | 2010-12-01 |
Image retrieval for a design patent based on shape features and texture features |
| |
| CAI Nian,ZHANG Guo-hong,LOU Peng-xu,DAI Qing-yun. Image retrieval for a design patent based on shape features and texture features[J]. Journal of Shandong University of Technology, 2011, 41(2): 1-4 |
| |
| Authors: | CAI Nian ZHANG Guo-hong LOU Peng-xu DAI Qing-yun |
| |
| Affiliation: | Faculty of Information Engineering, Guangdong University of Technology, Guangzhou 510006, China |
| |
| Abstract: | An image retrieval method for a design patent was proposed by means of a multi feature fusion method. A structure and edge direction histogram described shape features of the design patent images. Texture features were obtained by Gabor wavelet and statistical characteristics of image blocks. Image retrieval for design patents was accomplished with shape features and texture features integrated with a weighted method. |
| |
| Keywords: | design patent image retrieval edge direction histogram Texture features multi feature fusion |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
| 点击此处可从《山东大学学报(工学版)》浏览原始摘要信息 |
|
点击此处可从《山东大学学报(工学版)》下载全文 |
