Search results for "Inpainting"

showing 10 items of 11 documents

On the use of Denoising Autoencoders and Deep Convolutional Adversarial Networks for Automated Removal of Date Stamps

2019

Master's thesis Information- and communication technology IKT590 - University of Agder 2019 This thesis investigates to what extent the deep learning models such as DenoisingAutoencoder (DAE) and Deep Convolution General Adversarial Net (DCGAN)automate the removal of the date stamps from images with high resolution whilepreserving the rest of the images. Both DAE and DCGAN algorithms are im-plemented with Convolutional Neural Networks (CNN). The DAE algorithm canperform this task with entirely satisfactory results. The DAE can reconstruct theoriginal images from corrupted inputs with date stamps. While DCGAN deliverspoor yet interesting results. The images generated by the DCGAN are quite d…

Blind Image InpaintingIKT590utomated date stamp removalDCGANDAEVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550
researchProduct

Image Inpainting Methods Evaluation and Improvement

2014

With the upgrowing of digital processing of images and film archiving, the need for assisted or unsupervised restoration required the development of a series of methods and techniques. Among them, image inpainting is maybe the most impressive and useful. Based on partial derivative equations or texture synthesis, many other hybrid techniques have been proposed recently. The need for an analytical comparison, beside the visual one, urged us to perform the studies shown in the present paper. Starting with an overview of the domain, an evaluation of the five methods was performed using a common benchmark and measuring the PSNR. Conclusions regarding the performance of the investigated algorith…

Computer scienceInpaintinglcsh:MedicineImage processingReview Articlelcsh:TechnologyGeneral Biochemistry Genetics and Molecular BiologyDomain (software engineering)Image (mathematics)Pattern Recognition AutomatedDigital image processingImage Interpretation Computer-AssistedImage Processing Computer-AssistedComputer visionlcsh:ScienceGeneral Environmental Sciencebusiness.industrylcsh:Tlcsh:RGeneral MedicineBenchmark (computing)Partial derivativelcsh:QArtificial intelligencebusinessAlgorithmsTexture synthesisThe Scientific World Journal
researchProduct

Vertical scratches detection based on edge detection for old film

2010

Automatic detection of image damaged regions is the key to automatic video image inpainting. Vertical scratches are the common damages in the old film. In this paper, a vertical scratches detection algorithm based on edge detection is proposed. The proposed algorithm first uses the operator which has the largest response to the vertical edge in Sobel operator to detect edges, and then uses canny operator to detect edges further. Third, we detect vertical lines in the image through probabilistic Hough transform. Finally, we obtain the true locations of the vertical lines scratches through morphology and width constraints. Many experiments show that our method can detect vertical line scratch…

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONInpaintingSobel operatorVertical barEdge detectionImage (mathematics)Operator (computer programming)Canny edge detectorComputer visionArtificial intelligencebusinessImage restorationMathematicsofComputing_DISCRETEMATHEMATICS2010 2nd International Conference on Industrial and Information Systems
researchProduct

Metal artifact reduction in x-ray computed tomography: Inpainting versus missing value

2011

A comparison of algorithms for reduction of metal artifacts in x-ray cone beam computed tomography (CBCT) is presented. In the context of algebraic reconstruction techniques (ART) several inpainting algorithms in the image domain are evaluated against missing data strategies. A GPU-based iterative framework is employed for a meaningful comparison of both. Simulation results from an extended Shepp-Logan phantom and real world dental data are given.

Cone beam computed tomographyComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONInpaintingContext (language use)Iterative reconstructionMissing dataMetal ArtifactComputer visionTomographyArtificial intelligencebusinessImage restorationComputingMethodologies_COMPUTERGRAPHICS2011 IEEE Nuclear Science Symposium Conference Record
researchProduct

A Portable Dynamic Laser Speckle System for Sensing Long-Term Changes Caused by Treatments in Painting Conservation

2018

[EN] Dynamic laser speckle (DLS) is used as a reliable sensor of activity for all types of materials. Traditional applications are based on high-rate captures (usually greater than 10 frames-per-second, fps). Even for drying processes in conservation treatments, where there is a high level of activity in the first moments after the application and slower activity after some minutes or hours, the process is based on the acquisition of images at a time rate that is the same in moments of high and low activity. In this work, we present an alternative approach to track the drying process of protective layers and other painting conservation processes that take a long time to reduce their levels …

CyclododecaneComputer sciencedynamic speckleVarnishVarnishInpaintingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologylcsh:Chemical technologyCyclododecane01 natural sciencesBiochemistrycyclododecaneArticleAnalytical Chemistrylaw.invention010309 opticschemistry.chemical_compoundSpeckle patternDynamic specklelaw0103 physical scienceslcsh:TP1-1185Sensitivity (control systems)Electrical and Electronic EngineeringInstrumentationSimulationDynamic speckleTemporal history speckle patternactivityProcess (computing)021001 nanoscience & nanotechnologyLaserAtomic and Molecular Physics and OpticsActivityARQUITECTURA Y TECNOLOGIA DE COMPUTADORESchemistryvisual_artPINTURAFISICA APLICADAvisual_art.visual_art_mediumdynamic speckle; activity; temporal history speckle pattern; varnish; cyclododecane0210 nano-technologytemporal history speckle patternvarnish
researchProduct

Face Inpainting via Nested Generative Adversarial Networks

2019

Face inpainting aims to repaired damaged images caused by occlusion or cover. In recent years, deep learning based approaches have shown promising results for the challenging task of image inpainting. However, there are still limitation in reconstructing reasonable structures because of over-smoothed and/or blurred results. The distorted structures or blurred textures are inconsistent with surrounding areas and require further post-processing to blend the results. In this paper, we present a novel generative model-based approach, which consisted by nested two Generative Adversarial Networks (GAN), the sub-confrontation GAN in generator and parent-confrontation GAN. The sub-confrontation GAN…

General Computer ScienceComputer scienceInpaintingComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION02 engineering and technologyFace inpainting010501 environmental sciencesResidual01 natural sciencesImage (mathematics)0202 electrical engineering electronic engineering information engineeringGeneral Materials ScienceVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 5500105 earth and related environmental sciencesbusiness.industryDeep learningGeneral Engineeringdeep neural networkPattern recognitionGenerative modelFace (geometry)020201 artificial intelligence & image processingArtificial intelligencenested GANlcsh:Electrical engineering. Electronics. Nuclear engineeringbusinesslcsh:TK1-9971Generator (mathematics)
researchProduct

Non-linear Local Polynomial Regression Multiresolution Methods Using $$\ell ^1$$-norm Minimization with Application to Signal Processing

2015

Harten’s Multiresolution has been developed and used for different applications such as fast algorithms for solving linear equations or compression, denoising and inpainting signals. These schemes are based on two principal operators: decimation and prediction. The goal of this paper is to construct an accurate prediction operator that approximates the real values of the signal by a polynomial and estimates the error using \(\ell ^1\)-norm in each point. The result is a non-linear multiresolution method. The order of the operator is calculated. The stability of the schemes is ensured by using a special error control technique. Some numerical tests are performed comparing the new method with…

Polynomial regressionDecimationMathematical optimizationSignal processingPolynomialOperator (computer programming)Computer scienceCompression (functional analysis)InpaintingData_CODINGANDINFORMATIONTHEORYAlgorithmLinear equation
researchProduct

Non-consistent cell-average multiresolution operators with application to image processing

2016

In recent years different techniques to process signal and image have been designed and developed. In particular, multiresolution representations of data have been studied and used successfully for several applications such as compression, denoising or inpainting. A general framework about multiresolution representation has been presented by Harten (1996) 20. Harten's schemes are based on two operators: decimation, D , and prediction, P , that satisfy the consistency property D P = I , where I is the identity operator. Recently, some new classes of multiresolution operators have been designed using learning statistical tools and weighted local polynomial regression methods obtaining filters…

Polynomial regressionDecimationTheoretical computer scienceApplied MathematicsInpaintingImage processing010103 numerical & computational mathematics01 natural sciences010101 applied mathematicsComputational MathematicsOperator (computer programming)Consistency (statistics)0101 mathematicsRepresentation (mathematics)AlgorithmMathematicsImage compressionApplied Mathematics and Computation
researchProduct

Filling-in Gaps in Textured Images Using Bit-Plane Statistics

2008

In this paper we propose a novel approach for the texture analysis-synthesis problem, with the purpose to restore missing zones in greyscale images. Bit-plane decomposition is used, and a dictionary is build with bit-blocks statistics for each plane. Gaps are reconstructed with a conditional stochastic process, to propagate texture global features into the damaged area, using information stored in the dictionary. Our restoration method is simple, easy and fast, with very good results for a large set of textured images. Results are compared with a state-of-the-art restoration algorithm.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniDigital Restoration Inpainting Texture Synthesis Bit-Plane Slicing
researchProduct

Restoration of Digitized Damaged Photos using Bit-Plane Slicing

2007

Digital image restoration aims to recover damaged zones of a digital image, using surrounding information. In this paper we propose a novel approach, based on bit-plane slicing decomposition, with the purpose to make information analysis and reconstruction process easy, fast and effective. Tests have been made on digitized damaged old photos to restore several classes of typical defects in old photographic prints.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPixelComputer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONProcess (computing)Image processingIterative reconstructionDigital imageImage restorationComputer graphics (images)Computer visionArtificial intelligenceBit plane slicingbusinessImage restorationBit-plane slicing Digital inpainting Image restoration
researchProduct