Line scratches are common degradations in motion picture films. This paper presents an efficient method for line scratches detection strengthened by a Kalman filter. A new interpolation technique, dealing with both low and high frequencies (i.e. film grain) around the line artifacts, is investigated to achieve a nearby invisible reconstruction of damaged areas. Our line scratches detection and removal techniques have been validated on several film sequences. 1 Introduction Motion picture industry is 100 years old and chemical film (nowadays polyester, former triacetate or nitrate) is still the main support for motion picture film, despite of fast-growing digital media. It is a fact the film and dye coating for color are not stable over decades. In addition, some old films are reassembled from fragments scattered over various libraries and archives. Only digital processing will ensure the removal of the various artifacts due to age and a well balanced output to a film recorder. The ma...

This paper presents a novel relaxation labeling method called Augmented Lagrangian-Hopfield (ALH) method based on the Augmented Lagrangian multipliers and the graded Hopfield neural network. In the ALH method, RL is formulated as a problem of constrained real optimization. The augmented Lagrange multiplier method [13,14] is used for optimization with the constraints and the Hopfield method [15,16] for bridging the gap between discrete and continuous optimization. The ALH needs no gradient projection nor other normalization operations in its updating equations in keeping the labeling constraints. Therefore, it is more amenable for a neural network implementation than the exiting RL algorithms. Experiments show that the ALH produces good quality solutions in terms of the optimized objective values at a reasonable number of iterations. A recent result shows that the ALH method significantly improves the Hopfield type networks in solving the traveling salesman problem [17]. The ALH has also been used for image restoration and segmentation [18]. The rest of the paper is organized as follows: Section 2 introduces the continuous RL Method. Section 3 poses RL as a constrained optimization problem and presents the ALH method for solving it. Section 4 discusses the constrained optimization methods in connection to RL. Section 5 gives a neural network structure for the ALH computation. Section 6 presents the experimental results.

this article are addressed mainly from the computational viewpoint. The primary concerns are how to dene an objective function for the optimal solution for an image analysis problem and how to nd the optimal solution. The reason for dening the solution in an optimization sense is due to various uncertainties in imaging processes. It may be dicult to nd the perfect solution, so we usually look for an optimal one in the sense that an objective, into which constraints are encoded, is optimized

The object of this paper is to present aform ulation for thesegmF tation and restorationproblem using flexiblem dels with a robust regularized network (RRN). A two-steps iterativealgorithm is presented. In the first step an approximoh-- of the classification iscomJq-( by using a localmh)q)F)hfl-5 algorithm and in the second step the param-5hfl of the RRN are updated. The use of robust potentials ismh)N ated by (a) classification errors that can resultfrom the use of localmlh))FfiE algorithm in theimh-fiF) tation, and (b) the need to adapt the RN using localimhgradientinformfl -fi) to imfiE ve fidelity of them odel to the data.

This diploma thesis discuss the problem of applying color to the old black and white cartoons produced by original step by step technology, where each animation phase was exposed on the one frame of film negative. Thanks to possibility, which allows us to convert the original analogue material to the sequence of digital images using resolution suitable for TV broadcasting, we are able to solve our problem by methods of digital image processing. We introduce several algorithms based on unsupervised image segmentation and synthesis techniques, which exploit classical properties of cartoons produced by paper or foil technology, where foreground parts are represented by homogeneous surfaces with constant grey-scale intensity enclosed by bold contours. These algorithms together with couple of prediction techniques provide us to speed up whole inking process. An important part of this thesis is also description of application, where purposed algorithms are implemented. This implementation take into account also human driven interaction which guarantee the final image quality. Described application

Abstract. One of the classical optimization models for image segmentation is the well known Markov Random Fields (MRF) model. This model is a discrete optimization problem, which is shown here to formulate many continuous models used in image segmentation, such as total variations, denoising, level sets and some classes of Mumford-Shah functionals. In spite of the presence of MRF in the literature, the dominant perception has been that the model is not effective for image segmentation. We show here that the reason for the non-effectiveness is not due to the power of the model. Rather it is due to the lack of access to the optimal solution. Instead of solving optimally, heuristics have been engaged. Those heuristic methods cannot guarantee the quality of the solution nor the running time of the algorithm. Worse still, heuristics do not link directly the input functions and parameters to the output thus obscuring what would be ideal choices of parameters and functions which are to be selected by users in each particular application context. In other cases, inefficient algorithms were used and therefore dismissed due to excessive computational requirements. We describe here how MRF can model and solve efficiently several known continuous