Togiti Priyanka, Thalla Shankar


A single destination function is proposed to improve the codebook within a P2P atmosphere, which shows both the convenience information and the synchronization of the workload synchronously. Therefore, we recommend using the code line update method to improve the information exchanged between ID information and related information, as well as balancing the workload between the nodes that manage different coded words. It is proposed that the code update formula be distributed according to the code words, which improves the functionality of the objective at a low update cost. While most of the current methods focus on the indexing of high-dimensional visual characteristics and also on scalability limitations, we recommend in this document scalable ways to retrieve content-based images in point-to-point systems using a word bag. The codebook should be updated as the atmosphere periodically, instead of static storage. In this document, we offer a unique approach to dynamically generate a blade notebook around the world, which shows discrimination and workload balance. In addition, a peer-to-peer network is being developed dynamically, which makes the difficult codebook less efficient for recovery tasks. In order to further improve the recovery performance and reduce the cost of the network, the development of the cataloging of pruning techniques. Unlike central environments, the important challenge would be to have an efficient global codebook, where the images are distributed throughout the peer network.


Image Search; Re-Ranking Information Maximization; Bag-Of-Visual-Words (Bovw); Codebook;


A. Ksibi, A. Ammar, and C. Amar, “Adaptive diversification for tagbased social image retrieval”. International Journal of Multimedia Information Retrieval, 2014, 3(1): 29-39.

Y. Gao, M. Wang, H. Luan, J. Shen, S. Yan, and D. Tao, “Tag-based social image search with visual-text joint hypergraph learning”. ACM Multimedia information retrieval, 2011:1517-1520.

A. Ksibi, G. Feki, and A. Ammar, “Effective Diversification for Ambiguous Queries in Social Image Retrieval”. In Computer Analysis of Images and Patterns (pp. 571-578), 2013.

Y. Guo, G. Ding, L. Liu, J. Han, and L. Shao, “Learning to hash with optimized anchor embedding for scalable retrieval,” IEEE Trans. Image Processing, vol. 26, no. 3, pp. 1344–1354, 2017.

G. Dupret, “A model to estimate intrinsic document relevance from the clickthrough logs of a web search engine”. ACM international conference on Web search and data mining (pp. 181-190), 2010.

X. Lu, X. Li, and L. Mou, Semi-Supervised Multi-task Learning for Scene Recognition, IEEE Trans. Cybernetics, vol. 45, no. 9, pp. 1967-1976, 2015.

Full Text: PDF


  • There are currently no refbacks.

Copyright © 2012 - 2021, All rights reserved.|

Creative Commons License
International Journal of Innovative Technology and Research is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJITR , Permissions beyond the scope of this license may be available at