Abstract | ||
---|---|---|
Classifier plays an important role in a system detecting abnormal shadows from mammograms. In this paper, we propose the novel classification system that cascades four weak classifiers and a classifier ensemble to improve both computational cost and classification accuracy. The first several weak classifiers eliminate a large number of false positives in a short time which are easy to distinguish from abnormal regions, and the final classifier ensemble focuses on the remaining candidate regions difficult to classify, which results in high accuracy. We also show the experimental results using 2,564 mammograms. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/11783237_44 | Digital Mammography / IWDM |
Keywords | Field | DocType |
classifier ensemble,abnormal region,classification accuracy,final classifier ensemble,weak classifier,cascade classification,computational cost,novel classification system,abnormal shadow,abnormal shadow detection,high accuracy,classification system,false positive | Shadow,Feature selection,Pattern recognition,Cascade,Artificial intelligence,Classifier (linguistics),Bayes classifier,Machine learning,Mathematics,False positive paradox | Conference |
Volume | ISSN | ISBN |
4046 | 0302-9743 | 3-540-35625-8 |
Citations | PageRank | References |
1 | 0.36 | 4 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mitsutaka Nemoto | 1 | 46 | 8.42 |
Akinobu Shimizu | 2 | 1 | 0.36 |
Hidefumi Kobatake | 3 | 586 | 53.42 |
Hideya Takeo | 4 | 8 | 4.20 |
Shigeru Nawano | 5 | 265 | 29.51 |