Abstract
In this paper, we address the challenge about insufficiency of training set and limited feedback information in each relevance feedback (RF) round during the process of content based image retrieval (CBIR). We propose a novel active learning scheme to utilize the labeled and unlabeled images to build the initial Support Vector Machine (SVM) classifier for image retrieving. In our framework, two main components, a pseudo-label strategy and an improved active learning selection method, are included. Moreover, a feature subspace partition algorithm is proposed to model the retrieval target from users by the analysis from relevance labeled images. Experimental results demonstrate the superiority of the proposed method on a range of databases with respect to the retrieval accuracy.
Similar content being viewed by others
References
Bezdek, J.C.: Convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-2(1), 1–8 (2009)
Cao, X., Zhang, C., Fu, H., Guo, X.J.: Saliency-aware nonparametric foreground annotation based on weakly labeled data. IEEE Trans. Neural Netw. Learn. Syst. 27(6), 1253–1265 (2016)
Demir, B., Bruzzone, L.: A novel active learning method in relevance feedback for content-based remote sensing image retrieval. IEEE Trans. Geosci. Remote Sens. 53(5), 2323–2334 (2015)
Elhamifar, E., Sapiro, G., Yang, A., Satry, S.S.: A convex optimization framework for active learning. In: IEEE International Conference on Computer Vision (ICCV). IEEE Computer Society, pp. 209– 216 (2013)
Feng, J., Wei, Y., Tao, L., Zhang, C., Sun, J.: Salient object detection by composition. In: Proc IEEE Int. Conf. Comput. Vis., pp. 1028–1035 (2011)
Gao, X., Xiao, B., Tao, D., Li, X.: Image categorization: Graph edit distance+edge direction histogram. Pattern Recogn. 41(10), 3179–3191 (2008)
Hoi, S. C.H., Jin, R., Zhu, J., Lyu, M. R.: Semi-supervised SVM Batch mode active learning with applications to image retrieval. Acm Trans. Inf. Syst. 27(3), 16–32 (2009)
Hu, R.Y., Zhu, X.F., Cheng, D.B., He, W., Yan, Y., Song, J.K., Zhang, S.C.: Graph self-representation method for unsupervised feature selection. Neurocomputing 220, 130–137 (2017)
Hu, M.Q., Yang, Y., Shen, F.M., Zhang, L.M., Shen, H.T., Li X.L.: Robust Web Image Annotation via Exploring Multi-facet and Structural Knowledge. IEEE Transactions on Image Processing 26(10), 4871–4884 (2017)
Hu, M.Q., Yang, Y., Shen, F., Xie, N., Shen, H.T.: Hashing with Angular Reconstructive Embeddings. IEEE Transactions on Image Processing 27(2), 545–555 (2018)
Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. Euro. Conf. Comput. Vis. 5302, 304–317 (2008)
Jones, S., Shao, L., Zhang, J., Liu, Y.: Relevance feedback for real-world human action retrieval. Pattern Recogn. Lett. 33(4), 446–452 (2012)
Kim, D.W., Lee, K.Y., Lee, D.: kernel-based subtractive clustering method. A Pattern. Recogn. Lett. 26(7), 879–891 (2005)
Krizhevsky, A.: Learning multiple layers of features from tiny images (2009)
Li, J., Wang, J.Z.: Automatic linguistic indexing of pictures by a statistical modeling approach. IEEE Trans. Pattern Anal. Mach. Intell. 25(9), 1075–1088 (2003)
Li, J., Allinson, N.M.: Relevance feedback in content-based image retrieval: a survey. In: Handbook on Neural Information Processing, Springer, Berlin, Heidelberg, pp. 433–469 (2013)
Lin, K., Yang, H.F., Hsiao, J.H., Chen, C.S.: Deep learning of binary hash codes for fast image retrieval, Computer Vision and Pattern Recognition Workshops (2015)
Liu, R.J., Wang, Y.H., Baba, T., Masumoto, D., Nagata, S.: SVM-Based active feedback in image retrieval using clustering and unlabeled Data. Pattern Recogn. 41(8), 2645–2655 (2008)
Liu, H., Wang, R., Shan, S., Chen, X.: Deep supervised hashing for fast image retrieval. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), IEEE, pp. 2064–2072 (2016)
Luo, Y.D., Yang, Y., Shen, F.M., Huang, Z., Zhou, P., Shen, H.T.: Robust discrete code modeling for supervised hashing. Pattern Recognition 75, 128–135 (2018)
Manjunath, B.S., Ma, W.Y.: Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Mach. Intell. 18, 837–842 (1996)
Markus, S., Markus, O.: Similarity of color images, SPIE Storage and Retrieval for Image and Video Databases (1995)
Min, R., Cheng, H.D.: Effective image retrieval using dominant color descriptor and fuzzy support machine. Pattern Recogn. 4(12), 147–157 (2009)
Niblack, W., Barber, R., Equitz, W., Fickner, M., Glasman, E., Petkovic, D., Yanker, P.: The QBIC project: Querying images by content using color, texture and shape. In: Proceedings of the SPIE Conference on GeometricMethods in Computer Vision II, San Diego, California, USA (1993)
Niu, B., Cheng, J., Bai, X., Lu, H.Q.: Asymmetric propagation based batch mode active learning for image retrieval. Signal Process. 93(6), 1639–1650 (2013)
Qin, T., Zhang, X.D., Liu, T.Y., Wang, D.S., Ma, W.Y., Zhang, H. J.: An active feedback framework for image retrieval. Pattern Recogn. Lett. 29(5), 637–646 (2008)
Rahman, M.M., Antani, S.K., Thoma, G.R.: A learning-based similarity fusion and filtering approach for biomedical image retrieval Using SVM classication and relevance feedback. IEEE Trans. Inf. Technol. Biomed. 15(4), 640–646 (2011)
Rocchio, J.: Relevance feedback in information retrieval, Computer Science (2000)
Russell, B., Torralba, A., Liu, C., Fergus, R., Freeman, W.T.: Object recognition by scene alignment. In: Proc. Adv. Neural Inf. Process. Syst. (NIPS), pp. 1241–1248 (2007)
Samadi, A., Lillicrap, T.P., Tweed, D.B.: Deep learning with dynamic spiking neurons and fixed feedback weights. Neural Comput. 29(3), 578 (2017)
Schmid, C.: Weakly supervised learning of visual models and its application to content-based retrieval. Int. J. Comput. Vis. 56(1), 7–16 (2004)
Schohn, G., Cohn, D.: Less is more: active learning with Support Vector Machines. In: Proc 17th International Conf. Mach. Learn., Stanford, CA, USA, pp. 839–846 (2000)
Scott, G., Klaric, M., Davis, C., Shyu, C.R.: Entropy-balanced bitmap tree for shape-based object retrieval from large-scale satellite imagery databases. IEEE Trans. Geosci. Remote Sens. 49(5), 1603–1616 (2011)
Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298–2304 (2017)
Tao, D.C., Tang, X.O., Li, X.L., Wu, X.D.: Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval. IEEE Trans. Pattern Anal. Mach. Intell. 28(7), 1088–1099 (2006)
Tong, S., Chang, E.: Support vector machine active learning for image retrieval. In: Proceedings of the ACM Multimedia, pp. 107–118 (2001)
Wan, J., Wang, D., Hoi, S.C.H., Wu, P., Zhu, J., Zhang, Y.D., Li, J.T.: Deep learning for content-based image retrieval: a comprehensive study. In: ACM International Conference on Multimedia. ACM, pp. 157–166 (2014)
Wang, X.Y., Chen, J.W., Yang, H.Y.: A new integrated SVM classers for relevance feedback content-based image retrieval using EM parameter estimation. Appl. Soft Comput. 4(11), 2787–2804 (2011)
Wang, X., Zhang, B., Yang, H.: Active SVM-based relevance feedback using multiple classifiers ensemble and features re-weighting. Eng. Appl. Artif. Intell. 26, 368–381 (2013)
Wang, X.Y., Li, Y.W., Yang, H.Y., Chen, J.W.: An image retrieval scheme with relevance feedback using feature reconstruction and SVM reclassication. Neurocomputing 127, 214–230 (2014)
Wang, X.Y., Liang, L.L., Li, W.Y., Li, D.M., Yang, H.Y.: A new SVM-based relevance feedback image retrieval using probabilistic feature and weighted kernel function. J. Vis. Commun. Image Represent. 38, 256–275 (2016)
Weir, J.P.: Quantifying test-retest reliability using the intraclass correlation coefficient and the SEM. J. Strength Cond. Res. 19(1), 231 (2005)
Wu, K., Yap, K.H.: Fuzzy SVM for content-based image retrieval. IEEE Comput. Intell. Mag. 1(2), 10–16 (2005)
Xia, R., Pan, Y., Lai, H., Liu, C., Yan, S.: Supervised hashing for image retrieval via image representation learning. In: Proceedings of the Twenty-Eighth AAAI Conf. on Artificial Intelligence, vol. 3, pp. 2156–2162 (2014)
Yang, Y., Shen, F.M., Shen, H.T, Li, H.X, Li, X.L: Robust discrete spectral hashing for large-scale image semantic indexing. IEEE Transactions on Big Data 1(4), 162–171 (2015)
Yang, Y., Ma, Z.G., Yang, Y., Nie, F.P., Shen, H.T.: Multitask spectral clustering by exploring intertask correlation. 45(5), 1083–1094 (2015)
Yang, Y., Shen, F.M., Huang, Z., Shen, H.T., Li, X.L.: Discrete nonnegative spectral clustering. IEEE Transactions on Knowledge and Data Engineering 29(9), 1834–1845 (2017)
Zhang, Z., Ji, R.R., Yao, H.X., Xu, P.F., Wang, J.C.: Random sampling SVM based soft query expansion for image retrieval. In: IEEE International Conference on Image and Graphics, Chengdu, Sichuan, China, pp. 805–809 (2007)
Zhu, X.F., Zhang, L., Huang, Z.: A sparse embedding and least variance encoding approach to hashing. IEEE transactions on image processing 23(9), 3737–3750 (2014)
Zhu, X.F., Li, X.L., Zhang, S.C.: Block-row sparse multiview multilabel learning for image classification. IEEE transactions on cybernetics 46(2), 450–461 (2016)
Zhu, X.F., Li, X.L., Zhang, S.C., Ju, C.H., Wu, X.D.: Robust joint graph sparse coding for unsupervised spectral feature selection. 27(2), 545–555 (2018)
Acknowledgments
This work was supported by the Fundamental Research Funds for the Central Universities of China(No.A03013023001050,No.ZYGX2016J095).the National Natural Science Foundation of Sichuan(No.2017JY0229).
Author information
Authors and Affiliations
Corresponding author
Additional information
This article belongs to the Topical Collection: Special Issue on Deep Mining Big Social Data
Guest Editors: Xiaofeng Zhu, Gerard Sanroma, Jilian Zhang, and Brent C. Munsell
Rights and permissions
About this article
Cite this article
Rao, Y., Liu, W., Fan, B. et al. A novel relevance feedback method for CBIR. World Wide Web 21, 1505–1522 (2018). https://doi.org/10.1007/s11280-017-0523-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11280-017-0523-4