Combined Feature Extraction on Medical X-ray Images
Mohammad Reza Zare, Ahmed Mueen, Woo Chaw Seng, Mohammad Hamza Awedh · 2011
Medical images form an essential source of information for various important processes such as diagnosis of diseases, surgical planning, medical reference, research and training. Therefore, effective and meaningful search and classification of these images are vital. In this paper, the approaches of content-based image retrieval (CBIR) using low level features such as shape and texture are investigated in order to create a framework that classify medical X-ray image automatically. Gray level Co-occurrence Matrix, Canny Edge Operator, Local Binary Pattern and pixel level information of the images in this work act as image based feature representations which are adopted in our method. The state-of-the-art machine learning method, Support Vector Machine (SVM) is used for classification. In addition, the performance of image classification offered by combining the promising features stated above is investigated. Experimental results using 116 different classes of 11,000 X-ray images showed 90.7% classification accuracy.