Knowledge-Based Intelligent Information and Engineering Systems
Lecture Notes in Computer Science, 2003, Volume 2774/2003, 155-161, DOI: 10.1007/978-3-540-45226-3_22

A Trainable Object-Detection Method Using Equivalent Retinotopical Sampling and Fisher Kernel

Hirotaka Niitsuma

View Related Documents

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.

Fulltext Preview

Image of the first page of the fulltext document