The Community for Technology Leaders
2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS) (2016)
Belfast and Dublin, Ireland
June 20, 2016 to June 24, 2016
ISSN: 2372-9198
ISBN: 978-1-4673-9037-8
pp: 152-157
Image modality classification categorizes images according to their type. It is an important module in the Open-iSM multimodal (text+image) search engine that retrieves figures from biomedical articles. It is a hierarchical classification where on the top level the input figures are classified into two general categories: regular images (X-ray, CT, MRI, photographs, etc.) vs. illustration images (cartoon sketch, charts, graphs, etc.). This binary classification task is challenged by the vast diversity of visual material (image type), and the way it is organized (simple or compound figures). We present two methods for this binary classification: (i) Support Vector Machines (SVM) with manually-selected features, including a feature based on semantic concepts, and, (ii) Deep Learning method which avoids the process of feature handcrafting. Both methods were tested and compared on a dataset of 16400 figures. Both methods achieved good performance (above 95% accuracy). The slightly better performance of the feature-based method demonstrates the effectiveness of the features we chose.
Support vector machines, Visualization, Image color analysis, Biomedical imaging, Semantics, Image edge detection, Neural networks,convolutional neural networks, Modality classification, figure searching, concept feature, support vector machine, deep learning
Zhiyun Xue, Md. Mahmudur Rahman, Sameer Antani, L. Rodney Long, Dina Demner-Fushman, George R. Thoma, "Modality Classification for Searching Figures in Biomedical Literature", 2016 IEEE 29th International Symposium on Computer-Based Medical Systems (CBMS), vol. 00, no. , pp. 152-157, 2016, doi:10.1109/CBMS.2016.29
94 ms
(Ver 3.3 (11022016))