Measuring and alleviating the discrepancies between synthetic (source) real scene (target) data is core issue for domain adaptive semantic segmentation. Though recent works have introduced depth information in source to reinforce geometric knowledge transfer, they cannot extract intrinsic 3D of objects, including positions shapes, merely based on 2D estimated depth. In this work, we propose a n...

Thresholding is a simple but effective technique for image segmentation. In this paper, a general locally adaptive thresholding methods using neighborhood processing is presented. Local adaptive techniques are more effective in eliminating both uneven lighting disturbance, noise and ghost objects. In order to demonstrate the effectiveness, locally adaptive thresholding methods namely Niblack, S...

This paper proposes an adaptive over-segmentation meth-od for image copy-move forgery detection. Firstly, the Adaptive Over-Segmentation algorithm is proposed to adaptively segment the host image into non-overlapping and irregular blocks. Then the feature points are extracted and matched with each other to locate the labeled feature points which can approximately indicate the suspected forgery ...

Background: Accurate brain tissue segmentation from magnetic resonance (MR) images is an important step in analysis of cerebral images. There are software packages which are used for brain segmentation. These packages usually contain a set of skull stripping, intensity non-uniformity (bias) correction and segmentation routines. Thus, assessment of the quality of the segmented gray matter (GM), ...