Journal: IEEE access : practical innovations, open solutions

Article Title: REDN: A Recursive Encoder-Decoder Network for Edge Detection

doi: 10.1109/access.2020.2994160

Figure Lengend Snippet: Ground truth edge image generation. From an input image (first row) with ground truth semantic segmentation (second row), we identify all boundary pixels (third row) and then apply image thinning (e.g. MATLAB’s bwmorph) to obtain the ground truth edge image (last row).

Article Snippet: To obtain the ground truth edges, we first identify all the boundary pixels, treat them as a binary image and then apply image thinning using MATLAB function bwmorph (see examples in ). fig ft0 fig mode=article f1 fig/graphic|fig/alternatives/graphic mode="anchored" m1 Open in a separate window Fig. 3: caption a7 Ground truth edge image generation.

Techniques:

Journal: Biomedical Optics Express

Article Title: Regression-based algorithm for bulk motion subtraction in optical coherence tomography angiography

doi: 10.1364/BOE.8.003053

Figure Lengend Snippet: Skeletonization of an en face angiogram. Close up of the foveal region is shown for better visualization. (A) Original angiogram. (B) Skeletonized version by applying the algorithm described in [41] separately on vessels of different calibers. This algorithm is executed by the function bwmorph in Matlab’s Image Processing Toolbox. (C) Inaccurate skeletonization obtained by the same algorithm applied directly on the original en face angiogram. Vessels of larger caliber on the upper left corner are almost indistinguishable.

Article Snippet: This algorithm is executed by the function bwmorph in Matlab’s Image Processing Toolbox. (C) Inaccurate skeletonization obtained by the same algorithm applied directly on the original en face angiogram.

Techniques: