Medical image annotation and retrieval by using classification techniques

M. M. Abdulrazzaq, Shahrul Azman Mohd Noah, Muayad A. Fadhil

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Given the rapid increase in the number of medical images, the process of image retrieval is considered an effective solution that can be used in the automatic search and storage of images. Content-based image retrieval is considerably affected by image classification, also called image annotation. The performance of image annotation is significantly affected by two main issues, namely, automatic extraction for image features and the annotation algorithm. This study addresses these issues by constructing a feature vector from the extraction of multi-level features. Two machine learning techniques are used for evaluation. The K-nearest neighbor and support vector machine methods of learning machine are employed to classify images. Image CLEF med2005 is used as the database for the classification approaches. Furthermore, principal component analysis is utilized thrice to decrease the length of the feature vector. Results demonstrate that the accuracy is significantly improved compared with those of similar classification approaches related to the same database.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages32-36
Number of pages5
ISBN (Electronic)9781479918454
DOIs
Publication statusPublished - 1 Apr 2014
Event3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014 - Amman, Jordan
Duration: 29 Dec 201430 Dec 2014

Other

Other3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014
CountryJordan
CityAmman
Period29/12/1430/12/14

Fingerprint

Image retrieval
Learning systems
Image classification
Principal component analysis
Support vector machines

Keywords

  • Content-Based Image Retrierval (CBIR)
  • Discrete Wavelet Transformation (DWT)
  • Feature Extraction
  • Gray Level Co-occurrence Matrix (GLCM)
  • Histogram of Oriented Gradients (HOG)
  • imageCLEF2005
  • K-Nearest Neighbor (KNN)
  • Principal Component Analysis (PCA)
  • Support Vector Machine (SVM)

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Science (miscellaneous)

Cite this

Abdulrazzaq, M. M., Mohd Noah, S. A., & Fadhil, M. A. (2014). Medical image annotation and retrieval by using classification techniques. In Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014 (pp. 32-36). [07076865] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ACSAT.2014.13

Medical image annotation and retrieval by using classification techniques. / Abdulrazzaq, M. M.; Mohd Noah, Shahrul Azman; Fadhil, Muayad A.

Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. p. 32-36 07076865.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abdulrazzaq, MM, Mohd Noah, SA & Fadhil, MA 2014, Medical image annotation and retrieval by using classification techniques. in Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014., 07076865, Institute of Electrical and Electronics Engineers Inc., pp. 32-36, 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014, Amman, Jordan, 29/12/14. https://doi.org/10.1109/ACSAT.2014.13
Abdulrazzaq MM, Mohd Noah SA, Fadhil MA. Medical image annotation and retrieval by using classification techniques. In Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014. Institute of Electrical and Electronics Engineers Inc. 2014. p. 32-36. 07076865 https://doi.org/10.1109/ACSAT.2014.13
Abdulrazzaq, M. M. ; Mohd Noah, Shahrul Azman ; Fadhil, Muayad A. / Medical image annotation and retrieval by using classification techniques. Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014. Institute of Electrical and Electronics Engineers Inc., 2014. pp. 32-36
@inproceedings{e8707921074c42f2a313bb50ec3baf67,
title = "Medical image annotation and retrieval by using classification techniques",
abstract = "Given the rapid increase in the number of medical images, the process of image retrieval is considered an effective solution that can be used in the automatic search and storage of images. Content-based image retrieval is considerably affected by image classification, also called image annotation. The performance of image annotation is significantly affected by two main issues, namely, automatic extraction for image features and the annotation algorithm. This study addresses these issues by constructing a feature vector from the extraction of multi-level features. Two machine learning techniques are used for evaluation. The K-nearest neighbor and support vector machine methods of learning machine are employed to classify images. Image CLEF med2005 is used as the database for the classification approaches. Furthermore, principal component analysis is utilized thrice to decrease the length of the feature vector. Results demonstrate that the accuracy is significantly improved compared with those of similar classification approaches related to the same database.",
keywords = "Content-Based Image Retrierval (CBIR), Discrete Wavelet Transformation (DWT), Feature Extraction, Gray Level Co-occurrence Matrix (GLCM), Histogram of Oriented Gradients (HOG), imageCLEF2005, K-Nearest Neighbor (KNN), Principal Component Analysis (PCA), Support Vector Machine (SVM)",
author = "Abdulrazzaq, {M. M.} and {Mohd Noah}, {Shahrul Azman} and Fadhil, {Muayad A.}",
year = "2014",
month = "4",
day = "1",
doi = "10.1109/ACSAT.2014.13",
language = "English",
pages = "32--36",
booktitle = "Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Medical image annotation and retrieval by using classification techniques

AU - Abdulrazzaq, M. M.

AU - Mohd Noah, Shahrul Azman

AU - Fadhil, Muayad A.

PY - 2014/4/1

Y1 - 2014/4/1

N2 - Given the rapid increase in the number of medical images, the process of image retrieval is considered an effective solution that can be used in the automatic search and storage of images. Content-based image retrieval is considerably affected by image classification, also called image annotation. The performance of image annotation is significantly affected by two main issues, namely, automatic extraction for image features and the annotation algorithm. This study addresses these issues by constructing a feature vector from the extraction of multi-level features. Two machine learning techniques are used for evaluation. The K-nearest neighbor and support vector machine methods of learning machine are employed to classify images. Image CLEF med2005 is used as the database for the classification approaches. Furthermore, principal component analysis is utilized thrice to decrease the length of the feature vector. Results demonstrate that the accuracy is significantly improved compared with those of similar classification approaches related to the same database.

AB - Given the rapid increase in the number of medical images, the process of image retrieval is considered an effective solution that can be used in the automatic search and storage of images. Content-based image retrieval is considerably affected by image classification, also called image annotation. The performance of image annotation is significantly affected by two main issues, namely, automatic extraction for image features and the annotation algorithm. This study addresses these issues by constructing a feature vector from the extraction of multi-level features. Two machine learning techniques are used for evaluation. The K-nearest neighbor and support vector machine methods of learning machine are employed to classify images. Image CLEF med2005 is used as the database for the classification approaches. Furthermore, principal component analysis is utilized thrice to decrease the length of the feature vector. Results demonstrate that the accuracy is significantly improved compared with those of similar classification approaches related to the same database.

KW - Content-Based Image Retrierval (CBIR)

KW - Discrete Wavelet Transformation (DWT)

KW - Feature Extraction

KW - Gray Level Co-occurrence Matrix (GLCM)

KW - Histogram of Oriented Gradients (HOG)

KW - imageCLEF2005

KW - K-Nearest Neighbor (KNN)

KW - Principal Component Analysis (PCA)

KW - Support Vector Machine (SVM)

UR - http://www.scopus.com/inward/record.url?scp=84946692224&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84946692224&partnerID=8YFLogxK

U2 - 10.1109/ACSAT.2014.13

DO - 10.1109/ACSAT.2014.13

M3 - Conference contribution

SP - 32

EP - 36

BT - Proceedings - 3rd International Conference on Advanced Computer Science Applications and Technologies, ACSAT 2014

PB - Institute of Electrical and Electronics Engineers Inc.

ER -