Automatic classification of body parts X-ray images

Moshe Aboud, Assaf B. Spanier, Leo Joskowicz

Research output: Contribution to journalConference articlepeer-review


The development of automatic analysis and classification methods for large databases of X-ray images is a pressing need that may have a great impact on clinical practice. To advance this objective the ImageCLEF-2015 clustering of body part X-ray images challenge was created. The aim of the challenge is to group digital X-ray images into five structural groups: head-neck, upper-limb, body, lower-limb, and other. This paper presents the results of an experimental evaluation of X-ray images classification in the ImageCLEF-2015 challenge. We apply state-of-the-art classification and feature extraction methods for image classification and optimize them for the challenge task with emphasis on features indicating bone size and structure. The best classification results were obtained using the intensity, texture and HOG features and the KNN classifier. This combination has an accuracy of 86%and 73%for the 500 training images and 250 test images, respectively.

Original languageAmerican English
JournalCEUR Workshop Proceedings
StatePublished - 2015
Event16th Conference and Labs of the Evaluation Forum, CLEF 2015 - Toulouse, France
Duration: 8 Sep 201511 Sep 2015


  • Classification
  • ImageCLEF-2015
  • X-ray images


Dive into the research topics of 'Automatic classification of body parts X-ray images'. Together they form a unique fingerprint.

Cite this