基于多描述子分层特征学习的图像分类  

Image classification based on multi-descriptor hierarchical feature learning

作　　者：郭继昌[1] 王楠[1] 张帆[1] 

机构地区：[1]天津大学电子信息工程学院,天津300072

出　　处：《哈尔滨工业大学学报》2016年第11期83-89,共7页Journal of Harbin Institute of Technology

基　　金：国家重点基础研究计划(2014CB340400);天津市自然科学基金(15JCYBJC15500)

摘　　要：为解决图像分类任务中词袋(Bag-of-Words)模型分类算法单一局部描述子信息缺失、特征量化误差较大、图像特征表现力不足等问题,提出一种基于多描述子分层特征学习的图像分类方法.结合尺度不变特征变换(SIFT)与形状核描述子(KDES-S)进行局部特征提取,并构建分层特征学习结构来减少编码过程中的量化误差,最后将图像特征分层归一化后进行线性组合并利用线性支持向量机(SVM)进行训练和分类.在Caltech-101、Caltech-256、Scene-15数据库上进行实验,结果表明:相比其他图像分类方法,本文方法在分类准确率上具有显著提升.To address the problem that Bag-of-Words model still has several drawbacks such as the scarcity of information in single local descriptor,large quantization error and lack of representation upon image features in image classification tasks,an image classification method based on multi-descriptor hierarchical feature learning is proposed. Combing scale invariant feature transform（ SIFT） and kernel descriptors-shape（ KDES-S） features,a hierarchical structure is used to reduce quantization error in encoding process,which extracts local features. After that,image features in each layer are normalized respectively,the liner combination of which is the final feature representation for linear support vector machine（ SVM） classifier. Experiments are conducted on datasets Caltech-101,Caltech-256 and Scene-15, and experimental results show that the proposed method improves the classification accuracy significantly in comparison with other algorithms.

关 键 词：图像分类 分层特征学习 分层归一化 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]