The domain expert can either discard segments of a document as irrelevant (i.e. containing no relevant information), mark segmentation errors, or create reference standard annotations manually or semi-automatically.
To address these shortcomings, this work investigates the possibility of integrating prior-known shape information into segmentation.
In this section, we give brief information about segmentation of object and background using edge-based level set methods.
Our newly developed anatomical landmark localization and brain structure identification method facilitates navigation through an image data and extracts useful information for segmentation, registration and query modules.
In this article, we propose an evidential Markov chain that uses the Dempster Shafer combination rule to bring the effect of contextual information into segmentation of multisensor nonstationary data.
Co-registered micro-computed tomography (CT) images were acquired with an eXplore 120 microCT (Gamma Medica, USA/GE Healthcare, Sevenoaks, Kent, UK) [4] to obtain anatomical information for segmentation.
It should be noted that neither the phase congruency-based method[40] nor the phase map-based approach[24] (see Figure 7) generates adequate structure information for segmentation of vasculature in fundus images[30].
HMRF-EM incorporates contextual information into segmentation through Markov Random Field theory.
They used a k-nearest neighbor (kNN) working only with MR intensity information for segmentation and lesion detection.
For anatomical information and segmentation purposes, T2-weighted turbo spin echo (TSE) images were acquired with identical FOV and voxel size.
