A framework for image classification

Mamoun Awad; Lei Wang; Yuhan Chin; Latifur Khan; George Chen; Fehmi Chebil

A framework for image classification

Mamoun Awad, Lei Wang, Yuhan Chin, Latifur Khan, George Chen, Fehmi Chebil

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

Abstract

Image annotation process requires time and human intervention. In this research we propose a framework to incrementally annotate images in the database based on user feedback. At the beginning users provide some annotations for images manually as a ground truth. Classifier will be trained based on this ground truth. The classifier predicts annotation for new images that are not part of the ground truth. Feedback is collected from the users to increase the size of the training set and then the classifier is retrained. The system strives to capture feedback from users and retrains the classifier on the new training set. Our proposed framework facilitates semi-automatic image annotation

Original language	English
Title of host publication	7th IEEE Southwest Symposium on Image Analysis and Interpretation
Pages	134-138
Number of pages	5
Publication status	Published - 2006
Externally published	Yes
Event	7th IEEE Southwest Symposium on Image Analysis and Interpretation - Denver, CO, United States Duration: Mar 26 2006 → Mar 28 2006

Publication series

Name	Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Volume	2006

Other

Other	7th IEEE Southwest Symposium on Image Analysis and Interpretation
Country/Territory	United States
City	Denver, CO
Period	3/26/06 → 3/28/06

ASJC Scopus subject areas

Software
Computer Vision and Pattern Recognition
Computer Science Applications

Cite this

Awad, M, Wang, L, Chin, Y, Khan, L, Chen, G & Chebil, F 2006, A framework for image classification. in 7th IEEE Southwest Symposium on Image Analysis and Interpretation., 1633737, Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation, vol. 2006, pp. 134-138, 7th IEEE Southwest Symposium on Image Analysis and Interpretation, Denver, CO, United States, 3/26/06.

@inproceedings{01cfe345c3a64bf684454713f7b2de0a,

title = "A framework for image classification",

abstract = "Image annotation process requires time and human intervention. In this research we propose a framework to incrementally annotate images in the database based on user feedback. At the beginning users provide some annotations for images manually as a ground truth. Classifier will be trained based on this ground truth. The classifier predicts annotation for new images that are not part of the ground truth. Feedback is collected from the users to increase the size of the training set and then the classifier is retrained. The system strives to capture feedback from users and retrains the classifier on the new training set. Our proposed framework facilitates semi-automatic image annotation",

author = "Mamoun Awad and Lei Wang and Yuhan Chin and Latifur Khan and George Chen and Fehmi Chebil",

year = "2006",

language = "English",

isbn = "1424400694",

series = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

pages = "134--138",

booktitle = "7th IEEE Southwest Symposium on Image Analysis and Interpretation",

note = "7th IEEE Southwest Symposium on Image Analysis and Interpretation ; Conference date: 26-03-2006 Through 28-03-2006",

}

TY - GEN

T1 - A framework for image classification

AU - Awad, Mamoun

AU - Wang, Lei

AU - Chin, Yuhan

AU - Khan, Latifur

AU - Chen, George

AU - Chebil, Fehmi

PY - 2006

Y1 - 2006

N2 - Image annotation process requires time and human intervention. In this research we propose a framework to incrementally annotate images in the database based on user feedback. At the beginning users provide some annotations for images manually as a ground truth. Classifier will be trained based on this ground truth. The classifier predicts annotation for new images that are not part of the ground truth. Feedback is collected from the users to increase the size of the training set and then the classifier is retrained. The system strives to capture feedback from users and retrains the classifier on the new training set. Our proposed framework facilitates semi-automatic image annotation

AB - Image annotation process requires time and human intervention. In this research we propose a framework to incrementally annotate images in the database based on user feedback. At the beginning users provide some annotations for images manually as a ground truth. Classifier will be trained based on this ground truth. The classifier predicts annotation for new images that are not part of the ground truth. Feedback is collected from the users to increase the size of the training set and then the classifier is retrained. The system strives to capture feedback from users and retrains the classifier on the new training set. Our proposed framework facilitates semi-automatic image annotation

UR - http://www.scopus.com/inward/record.url?scp=33751046075&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33751046075&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:33751046075

SN - 1424400694

SN - 9781424400690

T3 - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

SP - 134

EP - 138

BT - 7th IEEE Southwest Symposium on Image Analysis and Interpretation

T2 - 7th IEEE Southwest Symposium on Image Analysis and Interpretation

Y2 - 26 March 2006 through 28 March 2006

ER -

A framework for image classification

Abstract

Publication series

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this