Efficient Feature Mapping in Classifying Proportional Data

Md Hafizur Rahman, Nizar Bouguila

Research output: Contribution to journalArticlepeer-review


In image classification, traditional kernels or feature mapping functions of Support Vector Machine(SVM) use discriminative features without considering the true nature of the data. Our work in this paper is motivated by the need to consider intrinsic distribution of L1 normalized histograms and develop a flexible feature mapping technique by combining histogram based features and distribution based density features. The proposed mapping technique contains prior knowledge about the the data which provides a flexible representation and thus increases the discriminative power of the classifier. Such flexibility is achieved due to the explanatory capabilities of Dirichlet, generalized Dirichlet and Beta-Liouville distributions to model proportional data. In addition to that, we present a general framework to estimate the parameters of these distributions by taking maximum likelihood (MLE) approach. Experimental results show that the proposed technique increases the effectiveness of SVM kernels for different computer vision tasks such as natural scene recognition, satellite image classification and human action recognition in videos.

Original languageEnglish (US)
JournalIEEE Access
StateAccepted/In press - 2020


  • Beta-Liouville Distribution
  • Data models
  • Dirichlet Distribution
  • Generalized Dirichlet Distribution
  • Histograms
  • Human Action Recognition
  • Image Classification
  • Kernel
  • Probabilistic logic
  • Proportional Data
  • Random variables
  • Support Vector Machines
  • Support vector machines
  • Task analysis

ASJC Scopus subject areas

  • Computer Science(all)
  • Materials Science(all)
  • Engineering(all)

Fingerprint Dive into the research topics of 'Efficient Feature Mapping in Classifying Proportional Data'. Together they form a unique fingerprint.

Cite this