No abstract

Segmentation of vasculature in retinal fundus image by level set methods employing classical edge detection methodologies is a tedious task. In this study, a revised level set-based retinal vasculature segmentation approach is proposed. During preprocessing, intensity inhomogeneity on the green channel of input image is corrected by utilizing all image channels, generating more efficient results compared to methods utilizing only one (green) channel. A structure-based level set method employing a modified phase map is introduced to obtain accurate skeletonization and segmentation of the retinal vasculature. The seed points around vessels are selected and the level sets are initialized automatically. Furthermore, the proposed method introduces an improved zero-level contour regularization term which is more appropriate than the ones introduced by other methods for vasculature structures. We conducted the experiments on our own dataset, as well as two publicly available datasets. The results show that the proposed method segments retinal vessels accurately and its performance is comparable to state-of-the-art supervised/unsupervised segmentation techniques.

Abstract. This paper presents a method for automatic removal of local defects such as blotches and impulse noise in old motion picture films. The method is fully automatic and includes the following steps: fuzzy prefiltering, motioncompensated blotch detection, and spatiotemporal inpainting. The fuzzy prefilter removes small defective areas such as impulse noise. Modified bidirectional motion estimation with a predictive diamond search is utilized to estimate the motion vectors. The blotches are detected by the rank-ordered-difference method. Detected missing regions are interpolated by a new exemplar-based inpainting approach that operates on three successive frames. The performance of the proposed method is demonstrated on an artificially corrupted image sequence and on a real motion picture film. The results of the experiments show that the proposed method efficiently removes flashing and still blotches and impulse noise from image sequences.