STUDY COMPARISON OF SVM-, K-NN- AND BACKPROPAGATION-BASED CLASSIFIER FOR IMAGE RETRIEVAL

Muhammad Athoillah, M. Isa Irawan, Elly Matul Imah

Abstract


Classification is a method for compiling data systematically according to the rules that have been set previously. In recent years classification method has been proven to help many people’s work, such as image classification, medical biology, traffic light, text classification etc. There are many methods to solve classification problem. This variation method makes the researchers find it difficult to determine which method is best for a problem. This framework is aimed to compare the ability of classification methods, such as Support Vector Machine (SVM), K-Nearest Neighbor (K-NN), and Backpropagation, especially in study cases of image retrieval with five category of image dataset. The result shows that K-NN has the best average result in accuracy with 82%. It is also the fastest in average computation time with 17,99 second during retrieve session for all categories class. The Backpropagation, however, is the slowest among three of them. In average it needed 883 second for training session and 41,7 second for retrieve session.

Keywords


Backpropagation, Classification, Image Retrieval, K-NN, SVM

Full Text:

PDF


DOI: http://dx.doi.org/10.21609/jiki.v8i1.279

Refbacks

  • There are currently no refbacks.


Copyright © Jurnal Ilmu Komputer dan Informasi. Faculty of Computer Science Universitas Indonesia.

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

View JIKI Statistic