Development of a multidimensional data model for efficient content-based image retrieval in big data storage

Stanislav Danylenko, Serhii Smelyakov

Abstract


The object of the study is content-based image retrieval. The subject of the study is the models and methods of content-based image retrieval in Big Data storage under high-intensity search queries. The purpose of this study is to develop a multidimensional data model and related search methods that can use and adapt to existing image descriptors and perform searches based on them. The task is to: analyze modern approaches and solutions for effective content-based image retrieval, formulate the problem and requirements for the search system; develop a model that will effectively process descriptors and place them inside in such a way as to minimize the number of descriptors with which comparisons need to be made during the search; develop a search algorithm; develop metrics, perform experiments and compare the results obtained with analogs. The methodology includes analyzing the search process and highlighting the stages of descriptor formation, its placement in the model, determining the level of similarity and comparing and forming the results; building a data model and placing it in memory; conducting experiments with data sets available on the Internet; evaluating the effectiveness of the search and forming the resulting tables for comparison with analogs. The following results were obtained: Multi-Dimensional Cube (MDC) model with optimizations and search algorithms was developed. It was compared with the brute-force search and the search that uses Inverted Multi-Index (IMI). The experimental results showed that MDC provides the best search speed among competitors. Demonstrates search quality at the level of competitors. The search labor intensity shown by the MDC is the best for searching for original images in the storage (checking whether they are present in storage). The labor intensity of searching for modifications of the images is better than in brute-force search by more than 100 times, but worse by 30% than when using IMI. Conclusions: The developed MDC model with its search algorithm solves the task of efficient content-based image retrieval, using existing image descriptors. The obtained results are satisfactory, but a promising direction is to improve the cell boundaries optimization algorithm and apply parallel computing.

Keywords


multidimensional data model; search model; content-based image retrieval; big data; image processing; image storage; feature database

Full Text:

PDF

References


Joshi, S. 35+ Google Search Statistics to Adapt to The Latest Trends. Available at: https://learn.g2.com/google-search-statistics (accessed 30.11.2024).

Kumar, N. How Many Google Searches Per Day (2024 Statistics). Available at: https://www.demandsage.com/google-search-statistics/ (accessed 30.11.2024).

Li, X., Yang J., & Ma J. Recent developments of content-based image retrieval (CBIR). Neurocomputing, 2021, vol. 452, pp. 675-689. DOI: 10.1016/j.neucom.2020.07.139.

Padma, Y. Advancements in Non-Linear Content-Based Image Retrieval (CBIR) Systems for Image Analysis. Communications on Applied Nonlinear Analysis, 2024, vol. 31, no. 2s, pp. 253-265. DOI: 10.52783/cana.v31.639.

Hirwane, R. Fundamental of Content Based Image Retrieval. International Journal of Computer Science and Information Technologies, 2012, no. 3, pp. 3260-3263.

Long, F., Zhang, H., & Feng, D. D. Fundamentals of Content-Based Image Retrieval. Signals and Communication Technology, Springer Berlin Heidelberg, Berlin, Heidelberg, 2003, pp. 1-26. DOI: 10.1007/978-3-662-05300-3_1.

Zheng, L., Yang Y., Tian, Q. SIFT Meets CNN: A Decade Survey of Instance Retrieval. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, vol. 40, no. 5, pp. 1224-1244. DOI: 10.1109/tpami.2017.2709749.

Li, Y., Shapiro, L. O., & Bilmes, J. A. A generative/discriminative learning algorithm for image classification. Tenth IEEE International Conference on Computer Vision (ICCV’05) Volume 1, IEEE, Beijing, China, 2005, vol. 2, pp. 1605-1612, DOI: 10.1109/iccv.2005.7.

Sivic, J., & Zisserman, A. Video Google: Efficient Visual Search of Videos. Lecture Notes in Computer Science, Springer Berlin Heidelberg, Berlin, Heidelberg, 2006, vol. 4170, pp. 127-144. DOI: 10.1007/11957959_7.

Babenko, A. Slesarev, A. Chigorin, A., & Lempitsky, V. Neural Codes for Image Retrieval. Computer Vision – ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, Springer, Cham., 2014, vol, 8689, pp. 584-599. DOI: 10.1007/978-3-319-10590-1_38.

Razavian, A. S., Azizpour, H., Sullivan, J., & Carlsson, S. CNN Features off-the-shelf: an Astounding Baseline for Recognition. 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Columbus, OH, USA, 2014, pp. 512-519. DOI: 10.1109/CVPRW.2014.131.

Gordo, A., Almazan, J., Revaud, J., & Larlus, D. End-to-end Learning of Deep Visual Representations for Image Retrieval. Int J Comput Vis, 2017, vol. 124, pp. 237-254. DOI: 10.1007/s11263-017-1016-8.

Datar, M., Immorlica, N., Indyk, P., & Mirrokni, V. S. Locality-sensitive hashing scheme based on p-stable distributions. Proceedings of the Twentieth Annual Symposium on Computational Geometry, ACM, New York, NY, USA, 2004, pp. 253-262. DOI: 10.1145/997817.997857.

Lin, G., Shen, C., Shi, Q., van den Hengel A., & Suter, D. Fast Supervised Hashing with Decision Trees for High-Dimensional Data. 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, IEEE, 2014, pp. 1971-1978. DOI: 10.1109/cvpr.2014.253.

Zhang, D., Islam, M. M., Lu, G., & Hou, J. Semantic Image Retrieval Using Region Based Inverted File. 2009 Digital Image Computing: Techniques and Applications, Melbourne, VIC, Australia, IEEE, 2009, pp. 242-249. DOI: 10.1109/dicta.2009.48.

Berman, A. P., & Shapiro, L. G. A flexible image database system for content-based retrieval. Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170), IEEE Comput. Soc., Brisbane, QLD, Australia, 1998, pp. 894-898. DOI: 10.1109/icpr.1998.711295.

Jégou, H., Douze, M., & Schmid, C. Product Quantization for Nearest Neighbor Search, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, 2011, vol. 33, no. 1, pp. 117-128. DOI: 10.1109/tpami.2010.57.

Jegou, H., Tavenard, R., Douze, M., & Amsaleg, L. Searching in one billion vectors: Re-rank with source coding. 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Prague, Czech Republic, IEEE, 2011, pp. 861-864. DOI: 10.1109/ICASSP.2011.5946540.

Babenko, A., & Lempitsky, V. The inverted multi-index. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA, IEEE, 2012, pp. 3069-3076. DOI: 10.1109/CVPR.2012.6248038.

Ge, T., He, K., Ke, Q., & Sun, J. Optimized Product Quantization for Approximate Nearest Neighbor Search. 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, IEEE, 2013, pp. 2946-2953, DOI: 10.1109/cvpr.2013.379.

Mensah, M. E., Li, X., Lei, H., Obed, A., & Bombie, N. C. Improving Performance of Colour-Histogram-Based CBIR Using Bin Matching for Similarity Measure. Artificial Intelligence and Security, Springer International Publishing, Cham, 2020, vol. 12239, pp. 586-596. DOI: 10.1007/978-3-030-57884-8_52.

Guldogan, E., & Gabbouj, M. Feature selection for content-based image retrieval. Signal, Image and Video Processing, 2008, vol. 2, iss. 3, pp. 241-250. DOI: 10.1007/s11760-007-0049-9.

Guldogan, E., & Gabbouj, M. System profiles in content-based image indexing and retrieval. Signal, Image and Video Processing, 2009, vol. 4, iss. 4, 463-480. DOI: 10.1007/s11760-009-0137-0.

Qazanfari, H., AlyanNezhadi, M. M., & Khoshdaregi, Z. N. Advancements in Content-Based Image Retrieval: A Comprehensive Survey of Relevance Feedback Techniques, arXiv.Org, 2023. Available at: https://arxiv.org/abs/2312.10089 (accessed: 01.12.2024).

Muja, M., & Lowe, D. G. Fast approximate nearest neighbors with automatic algorithm configuration. Proceedings of the Fourth International Conference on Computer Vision Theory and Applications (VISIGRAPP 2009), 2009, vol. 1, pp. 331-340. DOI: 10.5220/0001787803310340.

Qi, J. Faiss. GitHub. Available at: https://github.com/facebookresearch/faiss/wiki (accessed 22.12.2024).

Lux, M., & Chatzichristofis, S. A. Lire: lucene image retrieval. Proceedings of the 16th ACM International Conference on Multimedia, ACM, New York, NY, USA, 2008, pp. 1085-1088. DOI: 10.1145/1459359.1459577.

Jensen, C. S., Pedersen, T. B., & Thomsen, C. Multidimensional Databases and Data Warehousing, Springer Cham, 2010. 111 p. DOI: 10.2200/s00299ed1v01y201009dtm009.

EsotericSoftware. GitHub - EsotericSoftware/kryo: Java binary serialization and cloning: fast, efficient, automatic. Available at: https://github.com/EsotericSoftware/kryo (accessed 23.12.2024).

COCO, Common Objects in Context. Available at: https://cocodataset.org/ (accessed 5.12.2024)

Danylenko, S. MDC-2025-ukr-art-1, Google Drive. Available at: https://drive.google.com/drive/folders/1iTBbD1dKPxGnAAKOhXFRBDdO31jcRQf9?usp =sharing (accessed 22.12.2024).




DOI: https://doi.org/10.32620/reks.2025.1.10

Refbacks

  • There are currently no refbacks.