Modality prediction of biomedical literature images using multimodal feature representation
This paper presents the modelling approaches performed to automatically predict the modality of images found in biomedical literature. Various state-of-the-art visual features such as Bag-of-Keypoints computed with dense SIFT descriptors, texture features and Joint Composite Descriptors were used fo...
Main Authors: | , |
---|---|
Format: | Article |
Language: | deu |
Published: |
German Medical Science GMS Publishing House
2016-08-01
|
Series: | GMS Medizinische Informatik, Biometrie und Epidemiologie |
Subjects: | |
Online Access: | http://www.egms.de/static/en/journals/mibe/2016-12/mibe000166.shtml |