Novel EFM-KNN classifier and a new color descriptor for image classification

Abhishek Verma; Chengjun Liu

doi:10.1109/WOCC.2011.5872302

Novel EFM-KNN classifier and a new color descriptor for image classification

Abhishek Verma, Chengjun Liu

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

6 Scopus citations

Abstract

We propose a new CGSFPHOG descriptor and perform image classification using a novel EFM-KNN classifier, which combines the Enhanced Fisher Model (EFM) and the K Nearest Neighbor (KNN) decision rule. We integrate the oRGB-SIFT descriptor with other color SIFT features to produce the Color SIFT Fusion (CSF) and the Color Grayscale SIFT Fusion (CGSF) descriptors. The CGSF is integrated to the PHOG to obtain the novel CGSFPHOG descriptor. The effectiveness of the proposed new descriptor and the classification method is evaluated using two grand challenge datasets: the Oxford flower database and the MIT scene database. The classification results using the EFM-KNN classifier show that (i) the CGSFPHOG descriptor improves recognition performance upon other descriptors; and (ii) the oRGB-SIFT, the CSF, and the CGSF perform better than the other color SIFT descriptors.

Original language	English (US)
Title of host publication	WOCC 2011 - 20th Annual Wireless and Optical Communications Conference
DOIs	https://doi.org/10.1109/WOCC.2011.5872302
State	Published - 2011
Externally published	Yes
Event	20th Annual Wireless and Optical Communications Conference, WOCC 2011 - Newark, NJ, United States Duration: Apr 15 2011 → Apr 16 2011

Publication series

Name	WOCC 2011 - 20th Annual Wireless and Optical Communications Conference

Other

Other	20th Annual Wireless and Optical Communications Conference, WOCC 2011
Country/Territory	United States
City	Newark, NJ
Period	4/15/11 → 4/16/11

All Science Journal Classification (ASJC) codes

Computer Networks and Communications
Communication

Keywords

CGSFPHOG descriptor
Color Grayscale SIFT Fusion (CGSF)
Color SIFT Fusion (CSF)
EFM-KNN classifier
image classification
oRGB-SIFT descriptor

Access to Document

10.1109/WOCC.2011.5872302

Cite this

@inproceedings{58b1f1581e1e43508fbddeac3a4b058b,

title = "Novel EFM-KNN classifier and a new color descriptor for image classification",

abstract = "We propose a new CGSFPHOG descriptor and perform image classification using a novel EFM-KNN classifier, which combines the Enhanced Fisher Model (EFM) and the K Nearest Neighbor (KNN) decision rule. We integrate the oRGB-SIFT descriptor with other color SIFT features to produce the Color SIFT Fusion (CSF) and the Color Grayscale SIFT Fusion (CGSF) descriptors. The CGSF is integrated to the PHOG to obtain the novel CGSFPHOG descriptor. The effectiveness of the proposed new descriptor and the classification method is evaluated using two grand challenge datasets: the Oxford flower database and the MIT scene database. The classification results using the EFM-KNN classifier show that (i) the CGSFPHOG descriptor improves recognition performance upon other descriptors; and (ii) the oRGB-SIFT, the CSF, and the CGSF perform better than the other color SIFT descriptors.",

keywords = "CGSFPHOG descriptor, Color Grayscale SIFT Fusion (CGSF), Color SIFT Fusion (CSF), EFM-KNN classifier, image classification, oRGB-SIFT descriptor",

author = "Abhishek Verma and Chengjun Liu",

year = "2011",

doi = "10.1109/WOCC.2011.5872302",

language = "English (US)",

isbn = "9781457704543",

series = "WOCC 2011 - 20th Annual Wireless and Optical Communications Conference",

booktitle = "WOCC 2011 - 20th Annual Wireless and Optical Communications Conference",

}

Verma, A & Liu, C 2011, Novel EFM-KNN classifier and a new color descriptor for image classification. in WOCC 2011 - 20th Annual Wireless and Optical Communications Conference., 5872302, WOCC 2011 - 20th Annual Wireless and Optical Communications Conference, 20th Annual Wireless and Optical Communications Conference, WOCC 2011, Newark, NJ, United States, 4/15/11. https://doi.org/10.1109/WOCC.2011.5872302

TY - GEN

T1 - Novel EFM-KNN classifier and a new color descriptor for image classification

AU - Verma, Abhishek

AU - Liu, Chengjun

PY - 2011

Y1 - 2011

N2 - We propose a new CGSFPHOG descriptor and perform image classification using a novel EFM-KNN classifier, which combines the Enhanced Fisher Model (EFM) and the K Nearest Neighbor (KNN) decision rule. We integrate the oRGB-SIFT descriptor with other color SIFT features to produce the Color SIFT Fusion (CSF) and the Color Grayscale SIFT Fusion (CGSF) descriptors. The CGSF is integrated to the PHOG to obtain the novel CGSFPHOG descriptor. The effectiveness of the proposed new descriptor and the classification method is evaluated using two grand challenge datasets: the Oxford flower database and the MIT scene database. The classification results using the EFM-KNN classifier show that (i) the CGSFPHOG descriptor improves recognition performance upon other descriptors; and (ii) the oRGB-SIFT, the CSF, and the CGSF perform better than the other color SIFT descriptors.

AB - We propose a new CGSFPHOG descriptor and perform image classification using a novel EFM-KNN classifier, which combines the Enhanced Fisher Model (EFM) and the K Nearest Neighbor (KNN) decision rule. We integrate the oRGB-SIFT descriptor with other color SIFT features to produce the Color SIFT Fusion (CSF) and the Color Grayscale SIFT Fusion (CGSF) descriptors. The CGSF is integrated to the PHOG to obtain the novel CGSFPHOG descriptor. The effectiveness of the proposed new descriptor and the classification method is evaluated using two grand challenge datasets: the Oxford flower database and the MIT scene database. The classification results using the EFM-KNN classifier show that (i) the CGSFPHOG descriptor improves recognition performance upon other descriptors; and (ii) the oRGB-SIFT, the CSF, and the CGSF perform better than the other color SIFT descriptors.

KW - CGSFPHOG descriptor

KW - Color Grayscale SIFT Fusion (CGSF)

KW - Color SIFT Fusion (CSF)

KW - EFM-KNN classifier

KW - image classification

KW - oRGB-SIFT descriptor

UR - http://www.scopus.com/inward/record.url?scp=79959877570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959877570&partnerID=8YFLogxK

U2 - 10.1109/WOCC.2011.5872302

DO - 10.1109/WOCC.2011.5872302

M3 - Conference contribution

AN - SCOPUS:79959877570

SN - 9781457704543

T3 - WOCC 2011 - 20th Annual Wireless and Optical Communications Conference

BT - WOCC 2011 - 20th Annual Wireless and Optical Communications Conference

T2 - 20th Annual Wireless and Optical Communications Conference, WOCC 2011

Y2 - 15 April 2011 through 16 April 2011

ER -

Novel EFM-KNN classifier and a new color descriptor for image classification

Abstract

Publication series

Other

All Science Journal Classification (ASJC) codes

Keywords

Access to Document

Other files and links

Fingerprint

Cite this