Image categorization by learning and reasoning with regions

Yixin Chen, James Wang

Research output: Contribution to journalArticlepeer-review

528 Scopus citations

Abstract

Designing computer programs to automatically categorize images using low-level features is a challenging research topic in computer vision. In this paper, we present a new learning technique, which extends Multiple-Instance Learning (MIL), and its application to the problem of region-based image categorization. Images are viewed as bags, each of which contains a number of instances corresponding to regions obtained from image segmentation. The standard MIL problem assumes that a bag is labeled positive if at least one of its instances is positive; otherwise, the bag is negative. In the proposed MIL framework, DD-SVM, a bag label is determined by some number of instances satisfying various properties. DD-SVM first learns a collection of instance prototypes according to a Diverse Density (DD) function. Each instance prototype represents a class of instances that is more likely to appear in bags with the specific label than in the other bags. A nonlinear mapping is then defined using the instance prototypes and maps every bag to a point in a new feature space, named the bag feature space. Finally, standard support vector machines are trained in the bag feature space. We provide experimental results on an image categorization problem and a drug activity prediction problem.

Original languageEnglish (US)
Pages (from-to)913-939
Number of pages27
JournalJournal of Machine Learning Research
Volume5
StatePublished - Aug 1 2004

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Statistics and Probability
  • Artificial Intelligence

Fingerprint Dive into the research topics of 'Image categorization by learning and reasoning with regions'. Together they form a unique fingerprint.

Cite this