A trainable Obj ect-detection method using equivalent retinotopical sampling and Fisher Kernel

Rotaka Niitsuma

Research output: Contribution to journalConference article

Abstract

The paper proposes an extension of support vector machines (SVMs) for recognizing position and size of objects in digital images. The discriminant function is given as an analytical function of the object position and size. Using Fisher kernel, a concept of Retinotopical Sampling(RS) is introduced to SVMs.

Original languageEnglish
Pages (from-to)155-161
Number of pages7
JournalLecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume2774 PART 2
Publication statusPublished - Dec 1 2003
Event7th International Conference, KES 2003 - Oxford, United Kingdom
Duration: Sep 3 2003Sep 5 2003

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Computer Science(all)

Fingerprint Dive into the research topics of 'A trainable Obj ect-detection method using equivalent retinotopical sampling and Fisher Kernel'. Together they form a unique fingerprint.

  • Cite this