Meticulous classification using support vector machine for brain images retrieval
Weijuan Li, Zhentai Lu, Qianjin Feng, Wufan Chen · 2010
The objective of medical image retrieval system is to provide a tool for radiologists to retrieve the images similar to query image in content. Classification is an important part in retrieval system. This paper proposed a meticulous classification of MR-brain images using support vector machine (SVM). We used both texture and shape feature to express images, and then applied statistical association rule miner (StARMiner) algorithm to compute weight coefficient of each feature. A classifier based on SVM was trained, the parameters of which were optimized via many experiments. The result of glancing classification could achieve 92.10%. Meticulous classification can be applied in special body part retrieval system for retrieving more accurate images and reducing computational load.