| 基于感兴趣区域和神经网络的图像检索 |
| |
| 引用本文： | 叶银兰. 基于感兴趣区域和神经网络的图像检索[J]. 河南师范大学学报(自然科学版), 2009, 37(1) |
| |
| 作者姓名： | 叶银兰 |
| |
| 作者单位： | 绍兴文理学院,上虞分院,浙江,绍兴,312300 |
| |
| 基金项目： | 国家高技术研究发展计划(863计划)，浙江省自然科学基金 |
| |
| 摘 要： | 提出一种感兴趣区域的图像检索方法,该方法首先采用遗传FCM算法对图像进行分割,然后提取分割后的区域特征进行检索;为了缩小低层特征和高层语义之间的语义鸿沟,最后提出一种基于神经网络的相关反馈方法,实验表明,该方法具有较好的检索性能,系统具有较高的查全率和查准率.
|
| 关 键 词： | 感兴趣区域(ROI) 图像分割 遗传算法 相关反馈 图像检索 |
Image Retrieval Based on Region of Interest and Neural Network |
| |
| YE Yin-lan. Image Retrieval Based on Region of Interest and Neural Network[J]. Journal of Henan Normal University(Natural Science), 2009, 37(1) |
| |
| Authors: | YE Yin-lan |
| |
| Affiliation: | Shangyu College;Journal of Shaoxing University;Shaoxing 312300;China |
| |
| Abstract: | An image retrieval method based on region of interest is proposed.First,genetic fuzzy c-means(FCM)is used for image segment,and then the feature of region of interest is extracted.In order to reduce the semantic gap between the low-level visual features and the high-level semantic content,a relevance feedback method based on neural network is proposed.Experimental results show that the proposed image retrieval algorithm has a better retrieval performance. |
| |
| Keywords: | region of interest image segmentation genetic algorithm relevance feedback image retrieval |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
