张霞,郑逢斌.基于多层次视觉语义特征融合的图像检索算法[J].包装工程,2018,39(19):223-232.
ZHANG Xia,ZHENG Feng-bin.The Image Retrieval Algorithm Based on Multi-level Visual Semantic Feature Fusion[J].Packaging Engineering,2018,39(19):223-232. |
| 基于多层次视觉语义特征融合的图像检索算法 |
| The Image Retrieval Algorithm Based on Multi-level Visual Semantic Feature Fusion |
| 投稿时间：2017-10-23 修订日期：2018-10-10 |
| DOI：10.19554/j.cnki.1001-3563.2018.19.038 |
| 中文关键词: 图像检索 深度卷积神经网络 Fisher向量 稀疏编码空间金字塔匹配 多层次视觉语义特征 半监督学习 |
| 英文关键词: image retrieval depth convolution neural network Fisher vector sparse coding spatial pyramid matching multi-level visual semantic features semi supervised learning |
| 基金项目:国家自然科学基金（41571417, 60973126）；河南省高等学校重点科研项目（15A520010） |
|
| 摘要点击次数: |
| 全文下载次数: |
| 中文摘要: |
| 目的 为了解决低层特征与中层语义属性间出现的语义鸿沟，以及在将低层特征转化为语义属性的过程中易丢失信息，从而会降低检索精度等问题，设计一种多层次视觉语义特征融合的图像检索算法。方法 首先分别提取图像的3种中层特征（深度卷积神经网络（DCNN）特征、Fisher向量、稀疏编码空间金字塔匹配特征（SCSPM））；其次，为了对3种特征进行有效融合，定义一种基于图的半监督学习模型，将提取的3个中层特征进行融合，形成一个多层次视觉语义特征，有效结合3种不同中层特征的互补信息，提高图像特征描述，从而降低检索算法中的语义鸿沟；最后，引入具有视觉特性与语义统一的距离函数，根据提取的多层次视觉语义特征来计算查询图像和训练图像的相似度量，完成图像检索任务。结果 实验结果表明，与当前检索方法对比，文中算法具有更高的检索精度与效率。结论 所提算法具有良好的检索准确度，在医疗、包装商标等领域具有一定的参考价值。 |
| 英文摘要: |
| The work aims to design an image retrieval scheme based on multi-level visual semantic feature fusion, for the purpose of solving such problems as the semantic gap between the low layer features and the middle semantic properties, and the reduced retrieval accuracy caused by the information easily lost in the process of converting low layer features into semantic properties. Firstly, three kinds of image features (deep convolutional neural network (DCNN), Fisher vector and sparse coding spatial pyramid matching (SCSPM) feature) were extracted from the middle level. Secondly, in order to effectively integrate the three kinds of features, a graph based semi supervised learning model was defined to integrate the extracted three middle features to form a multi-level visual semantic feature, so that it could improve the image feature description and thus reduce the semantic gap of the retrieval algorithm by effectively combining the complementary information of three different middle features. Finally, the distance function with visual and semantic unity was introduced and the similarity measure between the query image and the training image was calculated based on the extracted multi-layer visual semantic features to finish the image retrieval task. The ex-perimental results showed that the proposed algorithm had higher retrieval precision and efficiency compared with current popular retrieval methods. The proposed algorithm has good retrieval accuracy, and it has certain reference value in the fields of medical treatment and packaging trademark. |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
渝公网安备 50010702501716号