Bag–of–Colors for Biomedical Document Image Classification

• Published in: Medical Content-Based Retrieval for Clinical Decision Support pp. 110 - 121
• Main Authors: García Seco de Herrera, Alba, Markonis, Dimitrios, Müller, Henning
• Format: Book Chapter
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg
• Series: Lecture Notes in Computer Science
• Subjects: bag–of–colors; image categorization; ImageCLEF; SIFT
• ISBN: 3642366775; 9783642366772
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-642-36678-9_11

The number of biomedical publications has increased noticeably in the last 30 years. Clinicians and medical researchers regularly have unmet information needs but require more time for searching than is usually available to find publications relevant to a clinical situation. The techniques described in this article are used to classify images from the biomedical open access literature into categories, which can potentially reduce the search time. Only the visual information of the images is used to classify images based on a benchmark database of ImageCLEF 2011 created for the task of image classification and image retrieval. We evaluate particularly the importance of color in addition to the frequently used texture and grey level features. Results show that bags–of–colors in combination with the Scale Invariant Feature Transform (SIFT) provide an image representation allowing to improve the classification quality. Accuracy improved from 69.75% of the best system in ImageCLEF 2011 using visual information, only, to 72.5% of the system described in this paper. The results highlight the importance of color for the classification of biomedical images.