DefinePK

DefinePK hosts the largest index of Pakistani journals, research articles, news headlines, and videos. It also offers chapter-level book search.

An effective feature integration in image rich information networks


Article Information

Title: An effective feature integration in image rich information networks

Authors: M. Maheswari, K. S. Neelu Kumari

Journal: ARPN Journal of Engineering and Applied Sciences

HEC Recognition History
Category From To
Y 2023-07-01 2024-09-30
Y 2022-07-01 2023-06-30
Y 2021-07-01 2022-06-30
X 2020-07-01 2021-06-30

Publisher: Khyber Medical College, Peshawar

Country: Pakistan

Year: 2015

Volume: 10

Issue: 9

Language: English

Keywords: feature extractionimage-rich information networkHMoK-SimRank algorithm

Categories

Abstract

An image-rich information network is a social media website which contains billions of images uploaded by users which are associated with information about owner, consumer, producer, annotations, and comments are forming heterogeneous image-rich information networks. In feature extraction has been extract both global feature as visual and local feature as color for an image and the relevance feedback approach to increase retrieval accuracy and gives more personalized results for the user. In a hybrid approach which measures the similarity of images to retrieve based on the link based, content based and relevance feedback. The link similarity based on HMoK-SimRank algorithm depends upon the social network information like tags, groups and human annotation over the images. Content based similarity considers both global and local features, for measuring the similarity. In relevance feedback based approaches, a system learns from feedback provided by the user for an efficient way to retrieve the image. The Main advantage is to improve the image retrieval very effective and performance has to be improved.


Paper summary is not available for this article yet.

Loading PDF...

Loading Statistics...