考虑视觉显著性的部分相似图像检索

计算机与现代化 ›› 2015, Vol. 0 ›› Issue (4): 82-85,89.

考虑视觉显著性的部分相似图像检索

南京理工大学计算机科学与工程学院，江苏南京210094

收稿日期:2014-12-19 出版日期:2015-04-27 发布日期:2015-04-29
作者简介: 陈秋平(1988-)，男，江苏丹阳人，南京理工大学计算机科学与工程学院硕士研究生，研究方向：图像处理，图像检索。

Partial-duplicate Image Retrieval via Exploiting Visual Saliency

School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China

Received:2014-12-19 Online:2015-04-27 Published:2015-04-29

摘要/Abstract

摘要：

当前流行的图像检索系统普遍采用词袋（Bag-of-Words）模型表示图像视觉内容。由于传统的视觉词袋模型忽略了局部特征间的几何关系，考虑几何约束的后处理方法明显地提高了检索准

确率。这些方法认为每个局部特征点是平等的，然而在实际情况中，图像中的局部特征点对于部分相似图像检索任务的重要性是不同的，比如位于相似图像区域上的特征点要比位于背景图像区域的特征

点重要。鉴于此，提出考虑图像特征点重要性的部分相似图像检索算法。首先用视觉显著性算法来计算图像每个像素点的显著性（即重要性），然后在几何验证计算图像间匹配分数中考虑匹配局部特征

点的重要性，最后在广泛使用的相似图像检索数据集上对提出的算法进行验证。实验结果表明了本方法的优越性。

关键词: , 图像检索, 相似图像, 视觉相似性, 几何验证

Abstract:

Bag-of-Word (BoW) model is widely used to represent the visual content of images in state-of-the-art image retrieval systems. Since traditional BoW models

discard geometric relationships among local features, exploiting geometric constraints as post-processing steps has been demonstrated to significantly improve the performance.

Each local feature is treated equally in these methods. In practice, the importance of local features for image retrieval is different. For example, the local features in the

duplicate image regions are more important that ones in the background image regions. Towards this end, a new partial-duplicate image retrieval method is proposed by leveraging

the importance of local features. First, visual saliency method is introduced to calculate the importance of each pixel, and then the importance is used to weight the similarity

of matched points. To verify the performance of the proposed method, extensive experiments are conducted on the widely-used datasets and experimental results show the

outperformance of the propose method.

Key words: image retrieval, duplicate image, visual saliency, geometry verification

陈秋平. 考虑视觉显著性的部分相似图像检索[J]. 计算机与现代化, 2015, 0(4): 82-85,89.

CHEN Qiu-ping. Partial-duplicate Image Retrieval via Exploiting Visual Saliency[J]. Computer and Modernization, 2015, 0(4): 82-85,89.

参考文献

［1］ Perdoch M, Chum O, Matas J. Efficient representation of local geometry for large scale object retrieval［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2009:

9-16.
［2］ Jegou H, Douze M, Schmid C. Hamming embedding and weak geometric consistency for large scale image search［C］// The 10th European Conference on Computer Vision. 2008:

304-317.
［3］ Li Zechao, Liu Jing, Zhu Xiaobin, et al. Image annotation using multi-correlation probabilistic matrix factorization［C］// ACM International Conference on Multimedia.

2010:1187-1190.
［4］ Jegou H, Douze M, Schmid C. Improving bag-of-features for large scale image search［J］. International Journal of Computer Vision, 2010,87(3):316-336.
［5］ Nister D, Stewenius H. Scalable recognition with a vocabulary tree［C］// IEEE Conference on Computer Vision and Pattern Recognition. 2006:1063-2168.
［6］ Sivic J, Zisserman A. Efficient visual search of videos cast as text retrieval［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009,31(4):591-606.
［7］ Philbin J, Chum O, Isard M, et al. Object retrieval with large vocabularies and fast spatial matching［C］// IEEE Conference on Computer Vision and Pattern Recognition.

2007:1-8.

［8］ Chum O, Matas J, Obdrzalek S. Enhancing RANSAC by generalized model optimization［C］// Asian Conference on Computer Vision. 2004:812-817.
［9］ Zhao Wanlei, Wu Xiao, Ngo Chong-Wah. On the annotation of Web videos by efficient near-duplicate search［J］. IEEE Transactions on Multimedia, 2010,12(5):448-461.
［10］Wang Junqiang, Tang Jinhui, Jiang Yugang. Strong geometry consistency for large scale partial-duplicate image search ［C］// ACM International Conference on Multimedia.

2013:633-636.
［11］Xie Hongtao, Gao Ke, Zhang Yongdong, et al. Local geometry consistency constraint for image retrieval［C］// IEEE International Conference on Image Processing. 2011:101

-104.
［12］Stas Goferman, Lihi Zelnik-Manor, Ayellet Tal. Contextaware saliency detection［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012,34(10):1915-

1926.
［13］Lowe D. Distinctive image features from scale-invariant key points［J］. International Journal of Computer Vision, 2004,60(2):91-110.
［14］Technion. Saliency［ED/OL］. http://webee.technion.ac.il/cgm/Computer-Graphics-Multimedia/Software/Saliency/Saliency.zip, 2014-12-19.

[1]	赵晨阳, 薛涛, 刘俊华. 基于改进Stable Diffusion的时尚服饰图案生成[J]. 计算机与现代化, 2024, 0(12): 15-23.
[2]	万兵1, 2, 3, 赵文涛4, 潘多涛1, 赵峥韬2, 3, 孙朝阳2, 3, 俞建成2, 3. 无人帆船半物理仿真测试系统设计[J]. 计算机与现代化, 2024, 0(12): 91-99.
[3]	陈宇航1, 杨勇1, 帕力旦·吐尔逊1, 樊小超1, 任鸽1, 刁宇峰2. 融合句法特征与语义特征的作文自动评分方法[J]. 计算机与现代化, 2024, 0(11): 64-69.
[4]	黄文栋, 王怡凡. 基于模态类别的多模态信息处理与融合综述[J]. 计算机与现代化, 2024, 0(07): 47-62.
[5]	郭泽昕, 钟国韵, 何剑锋, 张军. 基于深度学习的超市果蔬检索方法[J]. 计算机与现代化, 2024, 0(04): 60-65.
[6]	王欣怡, 尹四清, 洪军. 融合注意力机制的非对称深度监督哈希[J]. 计算机与现代化, 2023, 0(05): 26-31.
[7]	李静元, 张珂, 杨东裕. 基于雾计算的工业互联网安全数据访问方法[J]. 计算机与现代化, 2022, 0(12): 118-122.
[8]	陈春燕, 刘梦赤. 基于粒子群遗传算法的智能组卷策略[J]. 计算机与现代化, 2021, 0(08): 16-23.
[9]	宋鑫, 樊志强, . 基于Laguerre 前向神经网络的信息服务性能建模方法 [J]. 计算机与现代化, 2021, 0(03): 1-6.
[10]	魏健, 赵红涛, 刘敦楠, 加鹤萍 . 基于集成模型的超短时负荷预测方法[J]. 计算机与现代化, 2021, 0(03): 12-17.
[11]	段桂芹1，邹臣嵩2，刘锋2. 基于优化初始聚类中心的K中心点算法[J]. 计算机与现代化, 2019, 0(04): 1-.
[12]	李富星，蒙祖强 . 一种改进的类别区分词特征选择算法[J]. 计算机与现代化, 2019, 0(03): 73-.
[13]	白晓波1，邵景峰1，和征1，田建刚2. 基于学习的核偏最小二乘法优化扩展卡尔曼滤波[J]. 计算机与现代化, 2018, 0(09): 110-.
[14]	郑亚鹏，樊璐. 基于LSTM的临床血液需求预测方法[J]. 计算机与现代化, 2018, 0(05): 41-.
[15]	刘德春1，张秀国2，姜微2. 基于马尔科夫链的大学生自主学习能力预测方法[J]. 计算机与现代化, 2018, 0(05): 106-.