Research articles
ScienceAsia (): 34-41 |doi:
10.2306/scienceasia1513-1874...034
An evolutionary approach for optimizing content-based image retrieval using a support vector machine
T.˙Kanimozhi*, K.˙Latha
ABSTRACT: One of the vital challenges in the field of image retrieval is the semantic gap between visual features and high-level semantic concepts. Various kinds of relevance feedback approaches have been developed to deal with this semantic gap. Of these, the support vector machine is important. The support vector machine relies upon its parameters and the number of feedback samples. This paper uses a Gaussian firefly algorithm along with support vector machine to raise the relevance feedback performance. The proposed approach determines the parameters of the support vector machine and increases the number of relevant feedback samples, thereby optimizing the retrieval process. The performance of the proposed approach is compared with other existing retrieval methods.
Download PDF
22 Downloads 1763 Views
| Department˙of˙Computer˙Science˙and˙Engineering, University˙College˙of˙Engineering, BIT˙Campus, Tiruchirappalli˙620024, Tamilnadu, India |
* Corresponding author, E-mail: csrkani@gmail.com
Received 31 Aug 2014, Accepted 20 Jul 2016
|
