Region-based image classification

Qing Nie; Shou Yi Zhan

Region-based image classification

Qing Nie^*, Shou Yi Zhan

^*Corresponding author for this work

School of Information and Electronics

Beijing Institute of Technology

Research output: Contribution to journal › Article › peer-review

1 Citation (Scopus)

Abstract

Proposes a region-based feature descriptor for general object classification. The method uses polygonal approximation algorithm to simplify region boundaries, and uses a simplified SIFT descriptor to describe region appearance features. Demonstrates the high performance of this region descriptor within a powerful bag of words classify scheme. Through extensive evaluation on PASCAL 2007 visual recognition challenge dataset set. Test results showed that this region descriptor has many advantages. It can capture both shape and appearance features. It is simple and computation efficient, and is easy to reuse in under other frameworks.

Original language	English
Pages (from-to)	885-889
Number of pages	5
Journal	Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology
Volume	28
Issue number	10
Publication status	Published - Oct 2008

Keywords

Bag of words
Feature extraction
Image classify
Object recognition
Region feature

Cite this

@article{e855bfb807404501a61b9ce669f7916b,

title = "Region-based image classification",

abstract = "Proposes a region-based feature descriptor for general object classification. The method uses polygonal approximation algorithm to simplify region boundaries, and uses a simplified SIFT descriptor to describe region appearance features. Demonstrates the high performance of this region descriptor within a powerful bag of words classify scheme. Through extensive evaluation on PASCAL 2007 visual recognition challenge dataset set. Test results showed that this region descriptor has many advantages. It can capture both shape and appearance features. It is simple and computation efficient, and is easy to reuse in under other frameworks.",

keywords = "Bag of words, Feature extraction, Image classify, Object recognition, Region feature",

author = "Qing Nie and Zhan, {Shou Yi}",

year = "2008",

month = oct,

language = "English",

volume = "28",

pages = "885--889",

journal = "Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology",

issn = "1001-0645",

publisher = "Beijing Institute of Technology",

number = "10",

}

TY - JOUR

T1 - Region-based image classification

AU - Nie, Qing

AU - Zhan, Shou Yi

PY - 2008/10

Y1 - 2008/10

N2 - Proposes a region-based feature descriptor for general object classification. The method uses polygonal approximation algorithm to simplify region boundaries, and uses a simplified SIFT descriptor to describe region appearance features. Demonstrates the high performance of this region descriptor within a powerful bag of words classify scheme. Through extensive evaluation on PASCAL 2007 visual recognition challenge dataset set. Test results showed that this region descriptor has many advantages. It can capture both shape and appearance features. It is simple and computation efficient, and is easy to reuse in under other frameworks.

AB - Proposes a region-based feature descriptor for general object classification. The method uses polygonal approximation algorithm to simplify region boundaries, and uses a simplified SIFT descriptor to describe region appearance features. Demonstrates the high performance of this region descriptor within a powerful bag of words classify scheme. Through extensive evaluation on PASCAL 2007 visual recognition challenge dataset set. Test results showed that this region descriptor has many advantages. It can capture both shape and appearance features. It is simple and computation efficient, and is easy to reuse in under other frameworks.

KW - Bag of words

KW - Feature extraction

KW - Image classify

KW - Object recognition

KW - Region feature

UR - http://www.scopus.com/inward/record.url?scp=55949119325&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:55949119325

SN - 1001-0645

VL - 28

SP - 885

EP - 889

JO - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

JF - Beijing Ligong Daxue Xuebao/Transaction of Beijing Institute of Technology

IS - 10

ER -

Region-based image classification

Abstract

Keywords

Other files and links

Fingerprint

Cite this