XMIAR: X-ray medical image annotation and retrieval
The huge development of the digitized medical image has been steered to the enlargement and research of the Content Based Image Retrieval (CBIR) systems. Those systems retrieve and extract the images by their own low level features, like texture, shape and color. But those visual features did...
Main Authors: | , , , , |
---|---|
Format: | Conference or Workshop Item |
Language: | English English |
Published: |
Springer Verlag
2019
|
Subjects: | |
Online Access: | http://irep.iium.edu.my/76758/ http://irep.iium.edu.my/76758/ http://irep.iium.edu.my/76758/2/2020_Bookmatter_AdvancesInComputerVision.pdf http://irep.iium.edu.my/76758/1/10.1007%40978-3-030-17798-051.pdf |
Summary: | The huge development of the digitized medical image has been steered
to the enlargement and research of the Content Based Image Retrieval (CBIR)
systems. Those systems retrieve and extract the images by their own low level
features, like texture, shape and color. But those visual features did not aloe the
users to request images by the semantic meanings. The image annotation or
classification systems can be considered as the solution for the limitations of the
CBIR, and to reduce the semantic gap, this has been aimed annotating or to make
the classification of the image with few controlled keywords. In this paper, we
suggest a new hierarchal classification for the X-ray medical image using the
machine learning techniques, which are called the Support Vector Machine
(SVM) and k-Nearest Neighbour (k-NN). Hierarchy classification design was
proposed based on the main body region. Evaluation was conducted based on
ImageCLEF2005 database. The obtained results in this research were improved
compared to the previous related studies. |
---|