朱杰,赵相坤,谢博鋆,吴树芳

• 1:中央司法警官学院信息管理系
• 2:首都医科大学生物医学工程学院
• 3:河北省机器学习与计算智能重点实验室
• 4:河北大学数学与信息科学学院

摘要(Abstract)：

卷积神经网络可以在图像检索中为图像内容提供有效的表示,基于该理论提出一种基于深度特征加权的图像表示方法,此方法通过对深度特征加权,突出图像表示中对象的内容,并降低背景信息的影响。首先,通过预训练卷积神经网络提取出图像的特征映射,然后根据不同特征映射的特点,计算出深度特征的位置重要性、区域重要性和通道重要性,并根据3种重要性对深度特征进行加权,最后通过池化与深度特征聚合的方式生成图像表示。实验结果表明,与其他图像表示方法相比,提出的方法在Holiday、Oxford和Paris图像库中取得了更好的检索效果。

关键词(KeyWords)： 卷积神经网络;图像检索;特征加权;池化

Abstract:

Keywords:

基金项目(Foundation): 河北省自然科学基金项目(F2018511002);; 河北大学高层次创新人才科研启动经费项目;; 河北省高等学校科学技术研究项目(QN2018251,QN2018084,Z2019037);; 中央司法警官学院项目(XYZ201602);; 河北省高等学校科学技术研究项目(Z2019037);; 首都医科大学基础-临床科研合作基金(17JL86)

作者(Author): 朱杰,赵相坤,谢博鋆,吴树芳

DOI: 10.13705/j.issn.1671-6841.2019164

参考文献(References)：

• [1]王杰,刘向晴.彩色图像分割的FCM预分类核极限学习机方法[J].郑州大学学报(理学版),2018,50(2):75-80.WANG J,LIU X Q. FCM pre-classification kernel extreme learning machine algorithm of color image segmentation[J]. Journal of Zhengzhou university(natural science edition),2018,50(2):75-80.
• [2]LOWE D G. Distinctive image features from scale-invariant keypoints[J]. International journal of computer vision,2004,60(2):91-110.
• [3]KARAKASIS E G,AMANATIADIS A,GASTERATOS A,et al. Image moment invariants as local features for content based image retrieval using the bag-of-visual-words model[J]. Pattern recognition letters,2015,55:22-27.
• [4]SU Y,JURIE F. Improving image classification using semantic attributes[J]. International journal of computer vision,2012,100(1):59-77.
• [5]KRIZHEVSKY A,SUTSKEVER I,HINTON G E. Image Net classification with deep convolutional neural networks[J]. Communications of the ACM,2017,60(6):84-90.
• [6]ZHANG M M,LI W,DU Q. Diverse region-based CNN for hyperspectral image classification[J]. IEEE transactions on image processing,2018,27(6):2623-2634.
• [7]ZHENG L,YANG Y,TIAN Q. SIFT meets CNN:a decade survey of instance retrieval[J]. IEEE transactions on pattern analysis and machine intelligence,2018,40(5):1224-1244.
• [8]BABENKO A,SLESAREV A,CHIGORIN A,et al. Neural codes for image retrieval[M].Switzerlaned:Springer International Publishing,2014:584-599.
• [9]RAZAVIAN A S,AZIZPOUR H,SULLIVAN J,et al. CNN features off-the-shelf:an astounding baseline for recognition[C]∥IEEE Conference on Computer Vision and Pattern Recognition Workshops. Columbus,2014:806-813.
• [10]TOLIAS G,SICRE R,JGOU H. Particular object retrieval with integral max-pooling of CNN activations[EB/OL].[2015-11-18]. https:∥arxiv.org/abs/1511. 05879.
• [11]YANDEX A B,LEMPITSKY V. Aggregating local deep features for image retrieval[C]∥IEEE International Conference on Computer Vision. Santiago,2015:1269-1277.
• [12]KALANTIDIS Y,MELLINA C,OSINDERO S. Cross-dimensional weighting for aggregated deep convolutional features[M].Switzerlaned:Springer International Publishing,2016:685-701.
• [13]NG J Y H,YANG F,DAVIS L S. Exploiting local features from deep networks for image retrieval[C]∥IEEE Conference on Computer Vision and Pattern Recognition Workshops. Boston,2015:53-61.
• [14]WEI X S,LUO J H,WU J X,et al. Selective convolutional descriptor aggregation for fine-grained image retrieval[J]. IEEE transactions on image processing,2017,26(6):2868-2881.
• [15]JEGOU H,DOUZE M,SCHMID C. Hamming embedding and weak geometric consistency for large scale image search[M].Berlin:Springer,2008:304-317.
• [16]PHILBIN J,CHUM O,ISARD M,et al. Object retrieval with large vocabularies and fast spatial matching[C]∥International Conference on Computer Vision and Pattern Recognition. Minneapolis,2007.
• [17]PHILBIN J,CHUM O,ISARD M,et al. Lost in quantization:improving particular object retrieval in large scale image databases[C]∥IEEE Conference on Computer Vision and Pattern Recognition:Anchorage,2008.
• [18]SIMONYAN K,ZISSERMAN A. SIMONYAN K,et al. Very deep convolutional networks for large-scale image recognition[EB/OL].[2014-09-04]. https:∥arxiv.org/abs/1409. 1556.
• [19]JEGOU H,ZISSERMAN A. Triangulation embedding and democratic aggregation for image search[C]∥IEEE Conference on Computer Vision and Pattern Recognition. Columbus,2014:3310-3317.
• [20]RAZAVIAN A S,SULLIVAN J,CARLSSON S,et al.Visual instance retrieval with deep convolutional networks[J]. ITE transactions on media technology and applications,2016,4(3):251-258.
• [21]YANG H F,LIN K,CHEN C S. Supervised learning of semantics-preserving hash via deep convolutional neural networks[J].IEEE transactions on pattern analysis and machine intelligence,2018,40(2):437-451.
• [22]HUSAIN S S,BOBER M. Improving large-scale image retrieval through robust aggregation of local descriptors[J]. IEEE transactions on pattern analysis and machine intelligence,2017,39(9):1783-1796.
• [23]RADENOVI'CF,TOLIAS G,CHUM O. Fine-tuning CNN image retrieval with No human annotation[J]. IEEE transactions on pattern analysis and machine intelligence,2019,41(7):1655-1668.