and contributions In this thesis a novel approach to analysis and processing of classical cartoon animations is presented. It focuses on a popular animation technique where each frame is created as a planar composition of two visually distinct layers: static textural background and dynamic homogenous foreground. The aim of the proposed framework is (1) to precisely detach these two layers to re...

bstract. We develop a method for automatic colorization of imges (or two-dimensional fields) in order to visualize pixel values nd their local differences. In many applications, local differences in ixel values are as important as their values. For example, in topogaphy, both elevation and slope often must be considered. Gradientased value mapping (GBVM) is a technique for colorizing pixels ase...

This paper considers supervised multi-class image segmentation: from a labeled set of pixels in one image, we learn the segmentation and apply it to the rest of the image or to other similar images. We study approaches with p-Laplacians, (vector-valued) Reproducing Kernel Hilbert Spaces (RKHSs) and combinations of both. In all approaches we construct segment membership vectors. In the p-Laplaci...

We introduce a novel colorization framework for old black-and-white cartoons which has been originally produced by a cel or paper based technology. In this case the dynamic part of the scene is represented by a set of outlined homogeneous regions that superimpose static background. To reduce a large amount of manual intervention we combine unsupervised image segmentation, background reconstruct...

We present a convolutional-neural-network-based system that faithfully colorizes black and white photographic images without direct human assistance. We explore various network architectures, objectives, color spaces, and problem formulations. The final classification-based model we build generates colorized images that are significantly more aesthetically-pleasing than those created by the bas...

Hartley, Cosine, Slant and Haar Transforms for Grayscale Image Colorization Using Thepade‟s Transform Error Vector Rotation(TTEVR) Algorithms of Vector Quantization in YIQ, RGB and YCbCr color spaces are compared here for color pallet(codebook) size 32, 64, 128, 256 and 512. Here a color pallet is produced from reference(color) image from which color traits need to be taken using vector quantiz...

Premature newborns have a lower survival expectancy than full term neonates. Determining their possible health risks is crucial. Training for health risk assessment is one of the factors that might help in lowering the mortality of premature neonates. The paper describes the design approach to develop a premature neonate simulator showing colorization of the facial skin to simulate cyanosis to ...