A Semantic Image Search Using Approximate Methodology for Large-Scale Storage Systems

A. Leelavathi, J Siva Reddy


In this paper I  propose a near-real-time and cost-effective semantic queries based methodology, called FAST. The thought behind FAST is to investigate and misuse the semantic connection inside and among datasets through relationship mindful hashing and sensible level organized tending to altogether decrease the preparing inertness, while acquiring acceptably little loss of information look exactness. The close continuous property of FASTenables quick ID of corresponded records and the critical narrowing of the extent of information to be prepared. FASTsupports a few sorts of information examination, which can be executed in existing accessible stockpiling frameworks. We direct a certifiable utilize case in which youngsters detailed missing in a to a great degree swarmed condition (e.g., a very well known beautiful spot on a pinnacle traveler day) are recognized in a convenient mold by breaking down 60 million pictures utilizing FAST. Quick is additionally enhanced by utilizing semantic-mindful namespace to give dynamic and versatile namespace administration for ultra-huge capacity frameworks. Broad trial comes about exhibit the productivity and adequacy of FAST in the execution upgrades.

Full Text:


Copyright (c) 2018 Edupedia Publications Pvt Ltd

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.


All published Articles are Open Access at  https://journals.pen2print.org/index.php/ijr/ 

Paper submission: ijr@pen2print.org