Using Particle Swarm Optimization for Image Regions Annotation

Citation:
Sami, M., N. El-Bendary, T. - H. Kim, and A. E. Hassanien, "Using Particle Swarm Optimization for Image Regions Annotation", Future Generation Information Technology (FGIT 2012),, 241--250. Springer, Heidelberg. Kangwondo, Korea , cember 16-19,, 2012.

Date Presented:

cember 16-19,

Abstract:

In this paper, we propose an automatic image annotation approach
for region labeling that takes advantage of both context and semantics present
in segmented images. The proposed approach is based on multi-class K-nearest
neighbor, k-means and particle swarm optimization (PSO) algorithms for feature
weighting, in conjunction with normalized cuts-based image segmentation technique.
This hybrid approach refines the output of multi-class classification that
is based on the usage of K-nearest neighbor classifier for automatically labeling
images regions from different classes. Each input image is segmented using the
normalized cuts segmentation algorithm then a descriptor created for each segment.
The PSO algorithm is employed as a search strategy for identifying an optimal
feature subset. Extensive experimental results demonstrate that the proposed
approach provides an increase in accuracy of annotation performance by about
40%, via applying PSO models, compared to having no PSO models applied, for
the used dataset.

PreviewAttachmentSize
77090241.pdf417.36 KB