International Journal of Advanced Science and Engineering Research
For Queries/Clarification
alameenpublications@gmail.com
e-ISSN 2455-9288
alameenpublications@gmail.com
e-ISSN 2455-9288
ijaser
IJASER publishes high-quality, original research papers, brief reports, and critical reviews in all theoretical, technological, and interdisciplinary studies that make up the fields of advanced science and engineering and its applications.
Image search reranking is an effective identify approach to refine the text-based image search
result. existing reranking approaches are based on low-level visual features. Based on the classifiers for all
the predefined attributes, each image is represented by an attribute feature consisting of the responses from
these classifiers. A Semantic Graph is then used to model the relationship between images by integrating
low-level visual features and attribute features. Semantic Graph ranking is then performed to order the
images. Its basic principle is that visually similar images should have similar ranking scores. In this paper,
we propose a visual-attribute joint semantic graph learning approach to simultaneously explore two
information sources. A semantic graph is constructed to model the relationship of all images. We conduct
experiments on more than 1,000 queries in Corel and Caltech data set.