Research on the Second-order Retrieval Algorithm Based on SIFT Feature and Hash Distribution
AUTHORS
Junkai Yi,College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
Yueyang Su,College of Information Science and Technology, Beijing University of Chemical Technology, Beijing, China
ABSTRACT
In this paper, a second-order retrieval algorithm and an improved bag-of-words algorithm were proposed and applied to search similar images. Features of an image were firstly extracted by the method of SIFT. The word frequent table of the features was then created by the improved bag-of-words algorithm which is a combination of hash algorithm and K- Means algorithm. Based on the word frequent table, similar images were finally identified by the second-order retrieval algorithm. However, the second-order retrieval algorithm includes two steps. The first-order retrieval is a cursory search and it pays much attention to the similarities between the distributions of features, the second-order retrieval is an accurate search and it depends on the proportion of the same feature points to the total points. The experiment results imply that this method has good performance on the aspect of recall, showing high accuracy and efficiency.
KEYWORDS
SIFT features; image retrieval; bag of word algorithm; feature word frequent table; second-order retrieval
REFERENCES
[1] G.H. Liu, J.Y. Yang and Z.Y. Li, “Content-based image retrieval using computational visual attention model”, Pattern Recognition, Vol. 48, No. 8, pp. 2554-2566, (2015).
[2] K. Seetharaman and M. Kamarasan, “Statistical framework for image retrieval based on multiresolution features and similarity method”, Multimedia Tools & Applications, Vol. 73, No. 3, pp. 1943-1962, (2014).
[3] X. Wang and Z. Wang, “The method for image retrieval based on multi-factors correlation utilizing block truncation coding”, Pattern Recognition, Vol. 47, No.10, pp. 3293-3303, (2014).
[4] G.A. Montazer and D. Giveki, “Content Based Image Retrieval System Using Clustered Scale Invariant Feature Transforms”, Optik - International Journal for Light and Electron Optics, Vol. 126, No. 18, pp. 1695-1699, (2015).
[5] Y. Wang, S. Bi, M. Sun and Y. Cai, “Image retrieval algorithm based on SIFT,K-means and LDA”, Beijing Hangkong Hangtian Daxue Xuebao/journal of Beijing University of Aeronautics & Astronautics, Vol. 40, No. 9, pp. 1317-1322, (2014).
[6] R.S. Kushwah, “Combination of Local, Global and K-means using Wavelet Transform for Content Base Image Retrieval”, International Journal of Signal Processing Image Processing & Pattern Recognition, Vol. 8, pp. 253-266, (2015).
[7] P. Haibo, L. Chengming, Z. Zhe and L. Zhanbo, “Large-Scale Image Retrieval with Bag-of-Words and k- NN Re-Ranking”, International Journal of Multimedia & Ubiquitous Engineering, Vol. 10, pp. 265-276, (2015). Vol. 13, No. 1 (2018), pp. 11-26
[8] Y. Ren, A. Bugeau and J. Benois-Pineau, “Bag-of-bags of words irregular graph pyramids vs spatial pyramid matching for image retrieval”, Image Processing Theory, Tools and Applications (IPTA), 2014 4th International Conference on, Paris: IEEE, pp. 1-6, (2014).
[9] C. Wang and K. Huang, “How to use Bag-of-Words model better for image classification”, Image & Vision Computing, Vol. 38, pp. 65-74, (2015).
[10] L. Jia and L. Kitchen, “Object-based image similarity computation using inductive learning of contoursegment relations”, IEEE Transaction on Image Processing, Vol. 9, No. 1, pp. 80-88, (2000).
[11] P.T. Dong, “A Review on Image Feature Extraction and Representation Techniques”, International Journal of Multimedia & Ubiquitous Engineering, Vol. 8, No. 4, pp. 385-396, (2013).
[12] J. Qian, J. Yang, N. Zhang and Z. Yang, “Histogram of visual words based on locally adaptive regression kernels descriptors for image feature extraction”, Neurocomputing, Vol. 129, No. 5, pp. 516-527, (2014).
[13] R. Zhou, J. Wu, Q. He, C. Hu and Z. Yu, “Approach of human face recognition based on SIFT feature extraction and 3D rotation model”, IEEE International Conference on Information and Automation, IEEE, pp. 476-479, (2011).
[14] Y. Sun, L. Zhao, S. Huang, L. Yan and G. Dissanayake “L 2 L 2 mathContainer Loading Mathjax -SIFT: SIFT feature extraction and matching for large images in large-scale aerial photogrammetry”, ISPRS Journal of Photogrammetry & Remote Sensing, Vol. 91(Complete), pp. 1-16, (2014).
[15] J. Zhang, J. Zhang and R. Sun, “Pose-invariant face recognition via SIFT feature extraction and manifold projection with Hausdorff distance metric”, International Conference on Security, Pattern Analysis, and Cybernetics. IEEE, pp. 294-298, (2014).
[16] C.H. Lin, C.C. Chen, H.L. Lee and J.R. Liao, “Fast K-means algorithm based on a level histogram for image retrieval”, Expert Systems with Applications, Vol. 41, No. 7, pp. 3276-3283, (2014).
[17] K. Jenni and S. Mandala, “Pre-processing image database for efficient Content Based Image Retrieval”, International Conference on Advances in Computing, Communications and Informatics, IEEE, pp. 968-972, (2014).
[18] E. Gupta and R. Singh Kushwah, “Combination of Local, Global and K-Mean using Wavelet Transform for
Content Base Image Retrieval” International Journal of Signal Processing Image Processing & Pattern
Recognition, Vol. 8, pp. 253-266, (2015).
[19] L.B. Zheng and W.W.Y. Ng, “Rotated k-means hashing for image retrieval problems”, Vol. 1, pp. 227-234, (2014).
[20] M.V. Lande, P. Bhanodiya and P. Jain, “An Effective Content-Based Image Retrieval Using Color, Texture and Shape Feature”, Intelligent Computing, Networking, and Informatics, pp. 1163-1170, (2014).
[21] C. Yin and S. Zhang, “Parallel implementing improved k-means applied for image retrieval and anomaly detection”, Multimedia Tools & Applications, pp.1-17, (2016).
[22] H. Lacheheb and S. Aouat, “SIMIR: New mean SIFT color multi-clustering image retrieval”, Multimedia Tools & Applications, pp. 1-22, (2016).
[23] S. Pandey and P. Khanna, “Content-based image retrieval embedded with agglomerative clustering built on information loss ☆”, Computers & Electrical Engineering, (2016).
[24] S. Parui and A. Mittal, “Similarity-Invariant Sketch-Based Image Retrieval in Large Databases”, Computer Vision – ECCV 2014. Springer International Publishing, pp. 398-414, (2014).
[25] G. Khosla, N. Rajpal and J. Singh, “Evaluation of Euclidean and Manhanttan metrics in Content Based Image Retrieval system”, International Conference on Computing for Sustainable Global Development, IEEE, (2015).
[26] Y. Li, R. Wang and Z. Huang, S. Shan and X. Chen, “Face video retrieval with image query via hashing across Euclidean space and Riemannian manifold”, Computer Vision and Pattern Recognition, IEEE, pp. 4758-4767, (2015).
[27] S. Nagarajan and T.S. Subashini, “Weighted Euclidean Distance Based Sign Language Recognition Using Shape Features”, Artificial Intelligence and Evolutionary Algorithms in Engineering Systems, pp. 149-156, (2015).