ABSTRACT
An efficient indexing method is essential for content-based image retrieval with the exponential growth in large-scale videos and photos. Recently, hash-based methods (e.g., locality sensitive hashing - LSH) have been shown efficient for similarity search. We extend such hash-based methods for retrieving images represented by bags of (high-dimensional) feature points. Though promising, the hash-based image object search suffers from low recall rates. To boost the hash-based search quality, we propose two novel expansion strategies - intra-expansion and inter-expansion. The former expands more target feature points similar to those in the query and the latter mines those feature points that shall co-occur with the search targets but not present in the query. We further exploit variations for the proposed methods. Experimenting in two consumer-photo benchmarks, we will show that the proposed expansion methods are complementary to each other and can collaboratively contribute up to 76.3% (average) relative improvement over the original hash-based method.
- E2LSH: http://www.mit.edu/~andoni/LSH/Google Scholar
- NIST TRECVID. http://www-nlpir.nist.gov/projects/trecvid/.Google Scholar
- A. Andoni et al. Efficient algorithms for substring near neighbor problem. ACM-SIAM SODA, 2006. Google ScholarDigital Library
- S. Arya et al. Approximate nearest neighbor queries in fixed dimensions. ACM-SIAM SODA, 1993. Google ScholarDigital Library
- A. Broder et al. Min-wise independent permutations. JCSS 1998.Google Scholar
- R. Cai et al. Scalable music recommendation by search. ACM Multimedia 2007. Google ScholarDigital Library
- J. G. Carbonell et al. Translingual information retrieval: A comparative evaluation. IJCAI 1997.Google Scholar
- M. Casey et al. Fast recognition of remixed music audio. ICASSP 2007Google Scholar
- T.-C. Chang et al. TRECVID 2004 search and feature extraction task by NUS PRIS. TRECVID Workshop 2004.Google Scholar
- M. Charikar. Similarity estimation techniques from rounding algorithms. STOCI 2002. Google ScholarDigital Library
- O. Chum et al. Total recall: Automatic query expansion with a generative feature model for object retrieval. ICCV 2007.Google ScholarCross Ref
- M. Datar, et al. Locality-sensitive hashing scheme based on p-stable distributions. SoCG 2004. Google ScholarDigital Library
- W. Dong et al. Efficiently matching sets of features with random histograms. ACM Multimedia 2008. Google ScholarDigital Library
- A. Fischler et al. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. CACM 1981. Google ScholarDigital Library
- M. Flickner et al. Query by image and video content: The QBIC system. IEEE Computer, 1995. Google ScholarDigital Library
- A. Gionis et al. Similarity search in high dimensions via hashing. VLDB 1999. Google ScholarDigital Library
- P. Indyk et al. Approximate Nearest Neighbors: Towards Removing the Curse of Dimensionality. STOC 1998. Google ScholarDigital Library
- Y. Ke et al. Efficient near-duplicate detection and sub-image retrieval. ACM Multimedia 2004. Google ScholarDigital Library
- D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV 2004. Google ScholarDigital Library
- Q. Lv et al. Multi-probe lsh: efficient indexing for high-dimensional similarity search. VLDB 2007. Google ScholarDigital Library
- W.-S. Liao et al. AdImage: video advertising by image matching and ad scheduling optimization. ACM SIGIR 2008. Google ScholarDigital Library
- D. Nistér et al. Scalable Recognition with a Vocabulary Tree. CVPR 2006. Google ScholarDigital Library
- J. Philbin et al. Object retrieval with large vocabularies and fast spatial matching. CVPR 2007.Google ScholarCross Ref
- J.R. Smith et al. VisualSEEK: A Fully Automated Content-Based Image Query System. ACM Multimedia 1996. Google ScholarDigital Library
- N. Snavely et al. Photo tourism: exploring photo collections in 3D. ACM TOG, 2006 Google ScholarDigital Library
- B. Stein. Principles of hash-based text retrieval. ACM SIGIR 2007. Google ScholarDigital Library
- X.-J. Wang et al. Annosearch: Image auto-annotation by search. CVPR 2006. Google ScholarDigital Library
- J. Xu et al. Query expansion using local and global document analysis. ACM SIGIR 1996.Google ScholarDigital Library
- R. Yan et al. Multimedia search with pseudo-relevance feedback. CIVR 2003.Google ScholarDigital Library
- Y.-H. Yang et al. ContextSeer: context search and recommendation at query time for shared consumer photos. ACM Multimedia 2008. Google ScholarDigital Library
- T. Yeh et al. Photo-based Question Answering. ACM Multimedia 2008. Google ScholarDigital Library
- K. M. Donald et al. A comparison of score, rank and probability-based fusion methods for video shot retrieval. CIVR 2005.Google ScholarDigital Library
- Y. G. Jiang et al. Bag-of-visual-words expansion using visual relatedness for video indexing. SIGIR 2008. Google ScholarDigital Library
- J. Philbin et al. Lost in quantization: Improving particular object retrieval in large scale image databases. CVPR 2008.Google ScholarCross Ref
Index Terms
- Query expansion for hash-based image object retrieval
Recommendations
Document expansion for image retrieval
RIAO '10: Adaptivity, Personalization and Fusion of Heterogeneous InformationSuccessful information retrieval requires effective matching between the user's search request and the contents of relevant documents. Often the request entered by a user may not use the same topic relevant terms as the authors' of these documents. One ...
Image-based indoor positioning system: fast image matching using omnidirectional panoramic images
MPVA '10: Proceedings of the 1st ACM international workshop on Multimodal pervasive video analysisIn this paper, we developed an image-based indoor localization system using omnidirectional panoramic images to which location information is added. By the combination of the robust image matching by PCA-SIFT and fast nearest neighbor search algorithm ...
A study on query expansion methods for patent retrieval
PaIR '11: Proceedings of the 4th workshop on Patent information retrievalPatent retrieval is a recall-oriented search task where the objective is to find all possible relevant documents. Queries in patent retrieval are typically very long since they take the form of a patent claim or even a full patent application in the ...
Comments