Hierarchical object category recognition technique for image based search system

Takuya Minagawa, Hideo Saito

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

In this paper, we present an object category recognition method for an information search system which is queried by camera of mobile phone or by servers of internet services. In such a system, processing speed is an important requirement. To improve processing speed, the hierarchical object category recognition technique proposed by Serre (23) is modified using Haar-Like features, vector quantization of feature models, and reduction of processing area. In addition, by retaining the information of each feature' s position, it compensates the accuracy which is a little reduced in exchange of processing speed. We implemented this method to web server, and proved this system can work in practical processing time. Through the experiment for Caltech-101 image database and natural scene category images, we also confirm the accuracy of our approach.

Original languageEnglish
JournalIEEJ Transactions on Electronics, Information and Systems
Volume129
Issue number5
DOIs
Publication statusPublished - 2009
Externally publishedYes

Fingerprint

Object recognition
Processing
Servers
Vector quantization
Mobile phones
Computer systems
Cameras
Internet
Experiments

Keywords

  • Information search system
  • Object category recognition

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

@article{f37985805c1e4ba79f514a87c3825f5b,
title = "Hierarchical object category recognition technique for image based search system",
abstract = "In this paper, we present an object category recognition method for an information search system which is queried by camera of mobile phone or by servers of internet services. In such a system, processing speed is an important requirement. To improve processing speed, the hierarchical object category recognition technique proposed by Serre (23) is modified using Haar-Like features, vector quantization of feature models, and reduction of processing area. In addition, by retaining the information of each feature' s position, it compensates the accuracy which is a little reduced in exchange of processing speed. We implemented this method to web server, and proved this system can work in practical processing time. Through the experiment for Caltech-101 image database and natural scene category images, we also confirm the accuracy of our approach.",
keywords = "Information search system, Object category recognition",
author = "Takuya Minagawa and Hideo Saito",
year = "2009",
doi = "10.1541/ieejeiss.129.947",
language = "English",
volume = "129",
journal = "IEEJ Transactions on Electronics, Information and Systems",
issn = "0385-4221",
publisher = "The Institute of Electrical Engineers of Japan",
number = "5",

}

TY - JOUR

T1 - Hierarchical object category recognition technique for image based search system

AU - Minagawa, Takuya

AU - Saito, Hideo

PY - 2009

Y1 - 2009

N2 - In this paper, we present an object category recognition method for an information search system which is queried by camera of mobile phone or by servers of internet services. In such a system, processing speed is an important requirement. To improve processing speed, the hierarchical object category recognition technique proposed by Serre (23) is modified using Haar-Like features, vector quantization of feature models, and reduction of processing area. In addition, by retaining the information of each feature' s position, it compensates the accuracy which is a little reduced in exchange of processing speed. We implemented this method to web server, and proved this system can work in practical processing time. Through the experiment for Caltech-101 image database and natural scene category images, we also confirm the accuracy of our approach.

AB - In this paper, we present an object category recognition method for an information search system which is queried by camera of mobile phone or by servers of internet services. In such a system, processing speed is an important requirement. To improve processing speed, the hierarchical object category recognition technique proposed by Serre (23) is modified using Haar-Like features, vector quantization of feature models, and reduction of processing area. In addition, by retaining the information of each feature' s position, it compensates the accuracy which is a little reduced in exchange of processing speed. We implemented this method to web server, and proved this system can work in practical processing time. Through the experiment for Caltech-101 image database and natural scene category images, we also confirm the accuracy of our approach.

KW - Information search system

KW - Object category recognition

UR - http://www.scopus.com/inward/record.url?scp=67650565501&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650565501&partnerID=8YFLogxK

U2 - 10.1541/ieejeiss.129.947

DO - 10.1541/ieejeiss.129.947

M3 - Article

AN - SCOPUS:67650565501

VL - 129

JO - IEEJ Transactions on Electronics, Information and Systems

JF - IEEJ Transactions on Electronics, Information and Systems

SN - 0385-4221

IS - 5

ER -