Experiments on High Resolution Images Towards Outdoor Scene Classification

A Monadjemi; BT Thomas; M Mirmehdi

Experiments on High Resolution Images Towards Outdoor Scene Classification

A Monadjemi, BT Thomas, M Mirmehdi

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference Contribution (Conference Proceeding)

Abstract

We examine the use of high frequency features in high resolution images to increase texture classification accuracy when used in combination with lower frequency features. We used Gabor features derived from sections of 4032 2688 images. A neural network classifier was used to determine the classification performance of lower and high frequency features when used separately and then in combination. Feature shuffling and Principal Component Analysis was applied to determine both the role of each feature in the classification and to extract a smaller reduced feature set involving both lower and high frequency features.

Translated title of the contribution	Experiments on High Resolution Images Towards Outdoor Scene Classification
Original language	English
Title of host publication	Unknown
Editors	Horst Wildenauer, Walter Kropatsch
Publisher	Vienna University of Technology
Pages	325 - 334
Number of pages	9
Publication status	Published - Feb 2002

Bibliographical note

Conference Proceedings/Title of Journal: Proceedings of the Seventh Computer Vision Winter Workshop

Access to Document

http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=1000620

Handle.net

Persistent link

Cite this

@inproceedings{219b266bd83d4005a4f9be36eee22ce5,

title = "Experiments on High Resolution Images Towards Outdoor Scene Classification",

abstract = "We examine the use of high frequency features in high resolution images to increase texture classification accuracy when used in combination with lower frequency features. We used Gabor features derived from sections of 4032 2688 images. A neural network classifier was used to determine the classification performance of lower and high frequency features when used separately and then in combination. Feature shuffling and Principal Component Analysis was applied to determine both the role of each feature in the classification and to extract a smaller reduced feature set involving both lower and high frequency features.",

author = "A Monadjemi and BT Thomas and M Mirmehdi",

note = "Conference Proceedings/Title of Journal: Proceedings of the Seventh Computer Vision Winter Workshop",

year = "2002",

month = feb,

language = "English",

pages = "325 -- 334",

editor = "Horst Wildenauer and Walter Kropatsch",

booktitle = "Unknown",

publisher = "Vienna University of Technology",

address = "Austria",

}

TY - GEN

T1 - Experiments on High Resolution Images Towards Outdoor Scene Classification

AU - Monadjemi, A

AU - Thomas, BT

AU - Mirmehdi, M

N1 - Conference Proceedings/Title of Journal: Proceedings of the Seventh Computer Vision Winter Workshop

PY - 2002/2

Y1 - 2002/2

N2 - We examine the use of high frequency features in high resolution images to increase texture classification accuracy when used in combination with lower frequency features. We used Gabor features derived from sections of 4032 2688 images. A neural network classifier was used to determine the classification performance of lower and high frequency features when used separately and then in combination. Feature shuffling and Principal Component Analysis was applied to determine both the role of each feature in the classification and to extract a smaller reduced feature set involving both lower and high frequency features.

AB - We examine the use of high frequency features in high resolution images to increase texture classification accuracy when used in combination with lower frequency features. We used Gabor features derived from sections of 4032 2688 images. A neural network classifier was used to determine the classification performance of lower and high frequency features when used separately and then in combination. Feature shuffling and Principal Component Analysis was applied to determine both the role of each feature in the classification and to extract a smaller reduced feature set involving both lower and high frequency features.

M3 - Conference Contribution (Conference Proceeding)

SP - 325

EP - 334

BT - Unknown

A2 - Wildenauer, Horst

A2 - Kropatsch, Walter

PB - Vienna University of Technology

ER -

Experiments on High Resolution Images Towards Outdoor Scene Classification

Abstract

Bibliographical note

Access to Document

Handle.net

Fingerprint

Cite this