Japanese / English

Detail of Publication

Text Language English
Authors Tomohiro Sakata, Koichi Kise
Title Flower Classification by Using Multiple Kernel Learning
Journal Proceedings of The 2nd China-Japan-Korea Joint Workshop on Pattern Recognition (CJKPR2010)
Pages pp.144-147
Reviewed or not Reviewed
Month & Year November 2010
Abstract Object classification for categories with a significant visual similarity is a difficult problem. Because natural objects are slightly different for each individual, it is difficult to classify them with one feature. Therefore multiple features are needed for classification. As a method of combining multiple features, MKL has recently been focused. In this research, we employ color, shape, and texture features. We classify the flower images by using MKL and investigate the recognition rate. As a result, the best recognition rate is 75.66% in combining three features with flower 17 category dataset published by Visual Geometry Group of Oxford University.
Back to list