Marios Vlachos

Learn More
In this paper an algorithm for vessel segmentation and network extraction in retinal images is proposed. A new multi-scale line-tracking procedure is starting from a small group of pixels, derived from a brightness selection rule, and terminates when a cross-sectional profile condition becomes invalid. The multi-scale image map is derived after combining(More)
In this study, neurodegeneration phenomena were investigated, by performing third harmonic generation imaging measurements on the nematode Caenorhabditis elegans, in vivo. The in vivo, precise identification of the contour of the degenerating neurons in the posterior part of the nematode and the monitoring, in real time, of the progression of degeneration(More)
In this study, third-harmonic generation (THG) imaging measurements were performed to characterize different developmental stages of the nematode Caenorhabditis elegans (C. elegans) embryos. Femtosecond laser pulses (1028 nm) were utilized for excitation. THG image contrast modality proved as a powerful diagnostic tool, providing valuable information and(More)
A novel method for finger vein pattern extraction from infrared images is presented. This method involves four steps: preprocessing which performs local normalization of the image intensity, image enhancement, image segmentation, and finally postprocessing for image cleaning. In the image enhancement step, an image which will be both smooth and similar to(More)
In this paper, an algorithm for robust finger vessel pattern extraction from infrared images is presented based on image processing, edge suppression, fuzzy enhancement, and fuzzy clustering. Initially, the brightness variations of the images are eliminated using histogram normalization and the vessel patterns are enhanced, to facilitate the separation(More)
In this paper, a novel method for estimation of the size and the shape of human Red Blood Cell using light scattering images is presented. The information retrieval process includes, image normalization, a Discrete Cosine Transform used to derive a normalized feature vector, and a Radial Basis Neural Network is implemented to estimate the geometrical(More)
In this paper, a fully automatic blind retrospective shading correction method based mainly on a minimization of a multi-objective criterion is presented. The proposed method assumes that the acquired image has distorted from a multiplicative and an additive shading component and thus can be adequately described by the linear image formation model. The(More)
  • 1