Serial fusion of random subspace ensemble for subcellular phenotype images classification

Bailing Zhang*, Tuan D. Pham

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review


Subcellular localisation is a key functional characteristic of proteins. In this paper, we apply Haralick texture analysis and Curvelet Transform for feature description and propose a cascade Random Subspace (RS) ensemble with rejection options for subcellular phenotype classification. Serial fusions of RS classifier ensembles much improve classification reliability. The rejection option is implemented by relating the consensus degree from majority voting to a confidence measure and abstaining to classify ambiguous samples if the consensus degree is lower than a threshold. Using the public 2D HeLa cell images, classification accuracy 93% is obtained with rejection rate 2.7% from the proposed system.

Original languageEnglish
Pages (from-to)386-406
Number of pages21
JournalInternational Journal of Bioinformatics Research and Applications
Issue number4
Publication statusPublished - 2013


  • CT
  • Cascade classifier
  • Curvelet transform
  • Haralick texture feature
  • MLP
  • Multiple layer perceptron
  • RS
  • Random subspace
  • SVM
  • Subcellular phenotype images classification
  • Support vector machine


Dive into the research topics of 'Serial fusion of random subspace ensemble for subcellular phenotype images classification'. Together they form a unique fingerprint.

Cite this