Partial-duplicate Image Retrieval via Exploiting Visual Saliency

Abstract

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

CHEN Qiu-ping. Partial-duplicate Image Retrieval via Exploiting Visual Saliency[J]. Computer and Modernization.

References

［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]	WANG Xin-yi, YIN Si-qing, HONG Jun. Asymmetric Deep Supervised Hashing with Attention Mechanism [J]. Computer and Modernization, 2023, 0(05): 26-31.
[2]	HAN Dan-dan, HAN Li-xin. Image Retrieval Based on Tensor Locality Preserving Projection [J]. Computer and Modernization, 2017, 0(1): 71-74.
[3]	CHEN Meng-ting1, CHEN Si-xi2. New Object Bank Method for Scene Classification Based on GBVS [J]. Computer and Modernization, 2017, 0(1): 61-64+70.
[4]	GUO Hai-feng1,2, CHEN Yue-xia1, SUN Zhou-bao2. Application of Improved ISOMAP Algorithm for Face Recognition [J]. Computer and Modernization, 2015, 0(9): 25-29.
[5]	ZHU Ling-yun1, ZHU Zheng-yu1,2, QI Xin-yong1. An Image Retrieval Algorithm Combining Multi-content Features [J]. Computer and Modernization, 2015, 0(9): 17-21.
[6]	WANG Meng-lei. A Relevance Feedback Method Based on Interest Region Detection in Image Retrieval System#br# [J]. Computer and Modernization, 2015, 0(1): 75-80.
[7]	GUAN Yong-hong. Rotation-invariant Texture Image Retrieval Based on Nonsubsampled Contourlet Transform and Matrix F-norm [J]. Computer and Modernization, 2013, 1(9): 95-97,1.
[8]	HE Wen-bin;LIANG Li-jiao. Image Retrieval Based on Modified Gabor Function [J]. Computer and Modernization, 2013, 1(7): 138-141.
[9]	TAO Chen;XU Dan;ZHANG Hai-yu;DENG Jian. Prohibition Road Sign Detection Algorithm Based on Visual Saliency and Symmetry Projection [J]. Computer and Modernization, 2013, 1(2): 35-37+4.
[10]	GUO Hai-feng, LI Guang-shui, QIU Bin-ren . Method of Social Website Image Retrieval Based on Multi-feature Fusion [J]. Computer and Modernization, 2013, 12(12): 159-163.
[11]	QIANG Zhen-ping;CHEN Xu;LIN Hong. An Image Retrieval Method Based on Radius and Angle Histograms Shape Descriptor [J]. Computer and Modernization, 2012, 1(201): 35-38.
[12]	JIANG Shao-feng;YANG Shu-qin. Application of Joint Relevance Feedback in Medical Image Retrieval [J]. Computer and Modernization, 2012, 208(12): 55-59.
[13]	WANG Han;WANG Bing;LI Yue;TANG Jin. Image Retrieval Based on Rtree [J]. Computer and Modernization, 2011, 1(1): 103-3.
[14]	ZHANG Shu-juan;WANG Qing-min. Research on Image Retrieval Based on Multi-features [J]. Computer and Modernization, 2010, 1(01): 124-127.
[15]	CHEN Ze-bin;HUANG Xiao-hua. Research on Image Retrieval Arithmetic Based on Edge Direction Histogram [J]. Computer and Modernization, 2009, 8(8): 144-146.