Two-stage hybrid classifier ensembles for subcellular phenotype images classification

Bailing Zhang*

*Corresponding author for this work

Research output: Contribution to journalConference articlepeer-review

2 Citations (Scopus)


An automatic, reliable and efficient prediction system for protein subcellular localization can be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen systems for drug discovery or for early diagnosis of a disease. In this paper, we propose a two-stage multiple classifier system to improve classification reliability by introducing rejection option. The system is built as a cascade of two classifier ensembles. The first ensemble consists of set of binary SVMs which generalizes to learn a general classification rule and the second ensemble focus on the exceptions rejected by the rule. To enhance diversity for the classifier ensembles, multiple features are introduced, including the local binary patterns (LBP), Gabor filtering and Gray Level Coocurrence Matrix (GLCM). Using the public benchmark 2D HeLa cell images, a high classification accuracy 96% is obtained with rejection rate 21%.

Original languageEnglish
Pages (from-to)554-562
Number of pages9
JournalProcedia Environmental Sciences
Publication statusPublished - 2011
Event1st 2011 International Conference on Environment Science and Biotechnology, ICESB 2011 - Male, Maldives
Duration: 25 Nov 201126 Nov 2011


  • Gabor filtering
  • Gray level coocurrence matrix
  • Hybrid classifier
  • Local binary patterns
  • Multiple layer perceptron
  • Subcellular phenotype images classification
  • Support vector machine


Dive into the research topics of 'Two-stage hybrid classifier ensembles for subcellular phenotype images classification'. Together they form a unique fingerprint.

Cite this