Integrating semantic and content features into bloom filters for efficient image retrieval
Ali Mustafa Qamar, Rehan Ullah Khan, Mohammed Alsuhaibani, Suliman A. Alsuhibany · 2025
Read Integrating semantic and content features into bloom filters for efficient image retrieval by Ali Mustafa Qamar, Rehan Ullah Khan, Mohammed Alsuhaibani, Suliman A. Alsuhibany (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12739126.txt.
Description
Ali Mustafa Qamar and co-authors published this study in 2025. It trims false hits in Bloom filters used for image search. A Bloom filter is a compact structure that answers set membership fast, at the price of occasional false positives. With huge image collections, those errors pile up. The team's fix adds check bits drawn from the images themselves: their captions and their brightness patterns.
Tests ran on nearly thirty-two thousand Flickr photos. The added checks cut the false positive rate sharply. They also let the filter shrink without losing performance. Smaller filters mean less memory and less compute per query. The authors suggest the same trick suits databases and network security tools. The lesson is general: a filter that peeks at its data's side information can punch above its size.
Catalog record
| CREATOR | Ali Mustafa Qamar, Rehan Ullah Khan, Mohammed Alsuhaibani, Suliman A. Alsuhibany |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 32 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |