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

Rotaka Niitsuma

doi:10.1007/978-3-540-45226-3_22

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

Rotaka Niitsuma

Research output: Contribution to journal › Conference article › peer-review

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 language	English
Pages (from-to)	155-161
Number of pages	7
Journal	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	2774 PART 2
DOIs	https://doi.org/10.1007/978-3-540-45226-3_22
Publication status	Published - 2003
Externally published	Yes
Event	7th International Conference, KES 2003 - Oxford, United Kingdom Duration: Sept 3 2003 → Sept 5 2003

ASJC Scopus subject areas

Theoretical Computer Science
Computer Science(all)

Access to Document

10.1007/978-3-540-45226-3_22

Cite this

@article{0d2fdceef4a844c193c9dbab90edc1fe,

title = "A trainable Obj ect-detection method using equivalent retinotopical sampling and Fisher Kernel",

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.",

author = "Rotaka Niitsuma",

year = "2003",

doi = "10.1007/978-3-540-45226-3_22",

language = "English",

volume = "2774 PART 2",

pages = "155--161",

journal = "Lecture Notes in Computer Science",

issn = "0302-9743",

publisher = "Springer Verlag",

note = "7th International Conference, KES 2003 ; Conference date: 03-09-2003 Through 05-09-2003",

}

TY - JOUR

T1 - A trainable Obj ect-detection method using equivalent retinotopical sampling and Fisher Kernel

AU - Niitsuma, Rotaka

PY - 2003

Y1 - 2003

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=8344276700&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=8344276700&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-45226-3_22

DO - 10.1007/978-3-540-45226-3_22

M3 - Conference article

AN - SCOPUS:8344276700

SN - 0302-9743

VL - 2774 PART 2

SP - 155

EP - 161

JO - Lecture Notes in Computer Science

JF - Lecture Notes in Computer Science

T2 - 7th International Conference, KES 2003

Y2 - 3 September 2003 through 5 September 2003

ER -

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

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this