Abstract:
Biomedical images are often complex, and contain several regions that are annotated
using arrows. Annotated arrow detection is a critical precursor to region-ofinterest
(ROI) labelling, which is useful in content-based image retrieval (CBIR).
Different image layers are first segmented via fuzzy binarization. Candidate regions
are then checked whether they are arrows by using BLSTM classifier, where Npen++
features are used. In case of low confidence score (i.e., BLSTM classifier score), we take
convexity defect-based arrowhead detection technique into account. The detected arrow
are then used to segment the region-of-interest (ROI). Our test results on biomedical
images from imageCLEF 2010 collection outperforms the existing state-of-the-art arrow
detection techniques. Our region segmentation techniques is preliminary approach to
segment regions from detected arrows.
