Аннотация.

В работе исследуется метод поиска изображений по визуальному подобию на основе сопоставления изображений по цветовым гистограммам. Предложен метод построения инвертированного индекса для быстрого поиска визуально схожих изображений по динамически пополняемой коллекции.

Ключевые слова:

поиск по визуальному подобию, инвертированный индекс, анализ гистограмм, поиск в коллекциях изображений.

Стр. 86-94.

I.V. Sochenkov, A.V. Vokhmintsev, V.V Kuznetsov, N.A. Khromov, K.S. Grigoryeva

"Visual Duplicates Image Search based on Inverted Index of Color Histograms"

Paper presents method for search of visually similar images. The proposed method is based on color histogram analysis and inverted index for fast search in large image collections.

Keywords: Image search, inverted index, histogram analysis, vector-space metrics.

 Полная версия статьи в формате pdf.

REFERENCES

1. Melnichenko, A. Metody poiska izobrazheniy po vizualnomu podobiyu i detektsii nechetkikh dublikatov   izobrazheniy / A. Melnichenko, A. Goncharov // Trudy ROMIP 2009. – SPb.:NU TsSI. – 2009. – S. 108-121.
2. R. Mojsilović, J. Kovačević, J. Hu, R. J. Safranek, & S. K. Ganapathy. Matching and retrieval based on the vocabulary and 121 grammar of color patterns, In IEEE Trans. Image Processing, volume 9, pages 38-54, 2000.
3. Lowe D. G. Object recognition from local scale-invariant features //Computer vision, 1999. The proceedings of the seventh IEEE international conference on. – Ieee, 1999. – T. 2. – S. 1150-1157.
4. Bay H., Tuytelaars T., Van Gool L. Surf: Speeded up robust features //Computer vision–ECCV 2006. – Springer Berlin Heidelberg, 2006. – S. 404-417.
5. Rublee E. et al. ORB: an efficient alternative to SIFT or SURF //Computer Vision (ICCV), 2011 IEEE International Conference on. – IEEE, 2011. – S. 2564-2571.
6. Tamura H., Mori S., Yamawaki T. Textural features corresponding to visual perception //Systems, Man and Cybernetics, IEEE Transactions on. – 1978. – T. 8. – №. 6. – S. 460-473.
7. Murala S., Gonde A. B., Maheshwari R. P. Color and texture features for image indexing and retrieval //Advance Computing Conference, 2009. IACC 2009. IEEE International. – IEEE, 2009. – S. 1411-1416.
8. Markus Stricker and Alexander Dimai. Color indexing with weak spatial constraints. SPIE proceedings, 2670:29– 40, February 1996.
9. D. M. Squire, W. Müller, H. Müller & J. Raki. Contentbased query of image databases, inspirations from text retrieval: inverted files, frequency-based weights and relevance feedback, In Pattern Recognition Letters, pages
143-149, 1999.
10. Pimenov V. Yu. Prostye metody poiska izobrazheniy po soderzhaniyu //Rossiyskiy seminar po Otsenke Metodov Informatsionnogo Poiska. Trudy ROMIP. – 2010. – S. 69-79.
11. Chum O. et al. Near Duplicate Image Detection: min-Hash and tf-idf Weighting //BMVC. – 2008. – T. 810. – S. 812-815.
12. Zheng L. et al. Lp-norm idf for large scale image search //Computer Vision and Pattern Recognition (CVPR), 2013 IEEE Conference on. – IEEE, 2013. – S. 1626-1633.
13. Chen D. M. et al. Inverted Index Compression for Scalable Image Matching //DCC. – 2010. – S. 525.
14. Dalal N., Triggs B. Histograms of oriented gradients for human detection //Computer Vision and Pattern Recognition,
2005. CVPR 2005. IEEE Computer Society Conference on. – IEEE, 2005. – T. 1. – S. 886-893.
15. Miramontes-Jaramillo, Daniel, Vitaly Kober, and Víctor Hugo Díaz-Ramírez. "Rotation Invariant Tracking Algorithm
Based on Circular HOGs." Pattern Recognition. Springer International Publishing, 2015. 115-124.