Thèses sur le sujet « Color transfers »
Créez une référence correcte selon les styles APA, MLA, Chicago, Harvard et plusieurs autres
Consultez les 50 meilleures thèses pour votre recherche sur le sujet « Color transfers ».
À côté de chaque source dans la liste de références il y a un bouton « Ajouter à la bibliographie ». Cliquez sur ce bouton, et nous générerons automatiquement la référence bibliographique pour la source choisie selon votre style de citation préféré : APA, MLA, Harvard, Vancouver, Chicago, etc.
Vous pouvez aussi télécharger le texte intégral de la publication scolaire au format pdf et consulter son résumé en ligne lorsque ces informations sont inclues dans les métadonnées.
Parcourez les thèses sur diverses disciplines et organisez correctement votre bibliographie.
Forcales, Fernández Manuel. « Two-color spectroscopy of energy transfers in Si:Er ». [S.l. : Amsterdam : s.n.] ; Universiteit van Amsterdam [Host], 2004. http://dare.uva.nl/document/77576.
Texte intégralCarrillo, Hernan. « Colorisation d'images avec réseaux de neurones guidés par l'intéraction humaine ». Electronic Thesis or Diss., Bordeaux, 2024. http://www.theses.fr/2024BORD0016.
Texte intégralColorization is the process of adding colors to grayscale images. It is an important task in the image-editing and animation community. Although automatic colorization methods exist, they often produce unsatisfying results due to artifacts such as color bleeding, inconsistency, unnatural colors, and the ill-posed nature of the problem. Manual intervention is often necessary to achieve the desired outcome. Consequently, there is a growing interest in automating the colorization process while allowing artists to transfer their own style and vision to the process. In this thesis, we investigate various interaction formats by guiding colors of specific areas of an image or transferring them from a reference image or object. As part of this research, we introduce two semi-automatic colorization frameworks. First, we describe a deep learning architecture for exemplar-based image colorization that takes into account user’s reference images. Our second framework uses a diffusion model to colorize line art using user-provided color scribbles. This thesis first delves into a comprehensive overview of state-of-the-art image colorization methods, color spaces, evaluation metrics, and losses. While recent colorization methods based on deep-learning techniques are achieving the best results on this task, these methods are based on complex architectures and a high number of joint losses, which makes the reasoning behind each of these methods difficult. Here, we leverage a simple architecture in order to analyze the impact of different color spaces and several losses. Then, we propose a novel attention layer based on superpixel features to establish robust correspondences between high-resolution deep features from target and reference image pairs, called super-attention. This proposal deals with the quadratic complexity problem of the non-local calculation in the attention layer. Additionally, it helps to overcome color bleeding artifacts. We study its use in color transfer and exemplar-based colorization. We finally extend this model to specifically guide the colorization on segmented objects. Finally, we propose a diffusion probabilistic model based on implicit and explicit conditioning mechanism, to learn colorizing line art. Our approach enables the incorporation of user guidance through explicit color hints while leveraging on the prior knowledge from the trained diffusion model. We condition with an application-specific encoder that learns to extract meaningful information on user-provided scribbles. The method generates diverse and high-quality colorized images
Philbrick, Gregory Eric. « Color Relationship Transfer for Digital Painting ». BYU ScholarsArchive, 2015. https://scholarsarchive.byu.edu/etd/5552.
Texte intégralJeong, Kideog. « OBJECT MATCHING IN DISJOINT CAMERAS USING A COLOR TRANSFER APPROACH ». UKnowledge, 2007. http://uknowledge.uky.edu/gradschool_theses/434.
Texte intégralThornton, A. L. « Colour object recognition using a complex colour representation and the frequency domain ». Thesis, University of Reading, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.301911.
Texte intégralMazauric, Serge. « Modèles spectraux à transferts de flux appliqués à la prédiction de couleurs sur des surfaces imprimées en demi-ton ». Thesis, Lyon, 2016. http://www.theses.fr/2016LYSES064/document.
Texte intégralThe protection of banknotes or identity documents against counterfeiting demands the development of control tools based on visual effects that are continuously renewed. These visual effects become thus difficult to counterfeit even by an expert forger ! This research tries to deal with that issue. Its objective is to bring new solutions using on the one side, the printing of diffusing materials, and on the other side the development of visual rendering models that can be observed. The visual effects that are sought-after are the color matching on both sides of a printed document when observed against thelight. To easily obtain a color matching, whatever the colors that are aimed for, it is essential to have a model that helps in calculating the quantity of ink to be left on the document. A model must be used to predict the spectral reflectance and the transmittance factors of the printed document by describing the phenomena of optical diffusion really present in the ink layers and in the document. We shall focus our interest especially on translucent printed documents that have halftone colors on both sides. Our goal here is to predict the visual rendering in different configurations of observation. To that end, we are offering a new approach based on the use of flux transfer matrices to predict the spectral reflectance and transmittance factors of prints when they are simultaneously lit up on both sides. By representing with transfer matrices the optical behavior of the different components present in a printed document, we see that the description of flux transfer between these elements is thus simplified. This mathematical framework leads to the construction of prediction models of halftone printed colors on diffusing materials. We also show that some existing models, such as the Kubelka-Munk or the Clapper-Yule models, can also be formulated in transfer matrices terms. The results that we get with the models used in this work make apparent identical prediction quality and in some cases even better ones to the ones found in the state of the art, while offering a simplification of the mathematical formulation and the physical description of the flux transfer. This simplification thus transforms these models into calculation tools that can easily be used especially for the choice of quantities of ink that must be left on both sides of the document in order to obtain color matching
Muhammad, Imran. « Colorizing Grey Scale Images ». Thesis, Högskolan Dalarna, Datateknik, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:du-6181.
Texte intégralNilsson, Linus. « Quality and real-time performance assessment of color-correction methods : A comparison between histogram-based prefiltering and global color transfer ». Thesis, Mittuniversitetet, Avdelningen för informationssystem och -teknologi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-33877.
Texte intégralFurman, Gary S. « The contribution of charge-transfer complexes to the color of kraft lignin ». Diss., Georgia Institute of Technology, 1986. http://hdl.handle.net/1853/5644.
Texte intégralEdsborg, Karin. « Color Coded Depth Information in Medical Volume Rendering ». Thesis, Linköping University, Department of Science and Technology, 2003. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1823.
Texte intégralContrast-enhanced magnetic resonance angiography (MRA) is used to obtain images showing the vascular system. To detect stenosis, which is narrowing of for example blood vessels, maximum intensity projection (MIP) is typically used. This technique often fails to demonstrate the stenosis if the projection angle is not suitably chosen. To improve identification of this region a color-coding algorithm could be helpful. The color should be carefully chosen depending on the vessel diameter.
In this thesis a segmentation to produce a binary 3d-volume is made, followed by a distance transform to approximate the Euclidean distance from the centerline of the vessel to the background. The distance is used to calculate the smallest diameter of the vessel and that value is mapped to a color. This way the color information regarding the diameter would be the same from all the projection angles.
Color-coded MIPs, where the color represents the maximum distance, are also implemented. The MIP will result in images with contradictory information depending on the angle choice. Looking in one angle you would see the actual stenosis and looking in another you would see a color representing the abnormal diameter.
Delafield, Susan J. « Development of tissue and protoplast culture techniques for Impatiens walleriana Hook. f. with a view to the transfer of yellow flower colour ». Thesis, McGill University, 1989. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=59575.
Texte intégralKuo, Wen-Guey. « Quantification of metamerism and colour constancy ». Thesis, Loughborough University, 1995. https://dspace.lboro.ac.uk/2134/15373.
Texte intégralRewinska, Dorota Barbara. « "Towards Information Transfer : Competing Processes in Two-Colour Molecular Dyads" ». Thesis, University of Newcastle upon Tyne, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.525041.
Texte intégralKoenigbauer, Lee Ann. « EFFECTS OF ARTICULATION AGREEMENTS ON TRANSFER STUDENTS OF COLOR AT A PREDOMINANTLY WHITE UNIVERSITY ». Bowling Green State University / OhioLINK, 2006. http://rave.ohiolink.edu/etdc/view?acc_num=bgsu1142553231.
Texte intégralShvadchak, Volodymyr. « Two-color fluorescent dyes for sensing peptide interactions : application to the retroviral proteins ». Strasbourg, 2009. https://publication-theses.unistra.fr/public/theses_doctorat/2009/SHVADCHAK_Volodymyr_2009.pdf.
Texte intégralGeary, Kevin Thomas. « Color Feature Integration with Directional Ringlet Intensity Feature Transform for Enhanced Object Tracking ». University of Dayton / OhioLINK, 2016. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1479835464285204.
Texte intégralAUDAN, ALAIN. « Status de l'acetyl- et de la glutathion-transferases chez les porteurs d'adenomes colo-rectaux : etude preliminaire ». Nantes, 1994. http://www.theses.fr/1994NANT204M.
Texte intégralSayer, James Richard. « Preferred levels of image sharpness and their relation to image structure in thermal dye transfer prints ». Diss., This resource online, 1993. http://scholar.lib.vt.edu/theses/available/etd-07132007-143150/.
Texte intégralHristova, Hristina. « Example-guided image editing ». Thesis, Rennes 1, 2017. http://www.theses.fr/2017REN1S119/document.
Texte intégralThis thesis addresses three main topics from the domain of image processing, i.e. color transfer, high-dynamic-range (HDR) imaging and guidance-based image filtering. The first part of this thesis is dedicated to color transfer between input and target images. We adopt cluster-based techniques and apply Gaussian mixture models to carry out a more precise color transfer. In addition, we propose four new mapping policies to robustly portray the target style in terms of two key features: color, and light. Furthermore, we exploit the properties of the multivariate generalized Gaussian distributions (MGGD). in order to transfer an ensemble of features between images simultaneously. The multi-feature transfer is carried out using our novel transformation of the MGGD. Despite the efficiency of the proposed MGGD transformation for multi-feature transfer, our experiments have shown that the bounded Beta distribution provides a much more precise model for the color and light distributions of images. To exploit this property of the Beta distribution, we propose a new color transfer method, where we model the color and light distributions by the Beta distribution and introduce a novel transformation of the Beta distribution. The second part of this thesis focuses on HDR imaging. We introduce a method for automatic creation of HDR images from only two images - flash and non-flash images. We mimic the camera response function by a brightness function and we recover details from the flash image using our new chromatic adaptation transform (CAT), called bi-local CAT. That way, we efficiently recover the dynamic range of the real-world scenes without compromising the quality of the HDR image (as our method is robust to misalignment). In the context of the HDR image creation, the bi-local CAT recovers details from the flash image, removes flash shadows and reflections. In the last part of this thesis, we exploit the potential of the bi-local CAT for various image editing applications such as image de-noising, image de-blurring, texture transfer, etc. We propose a novel guidance-based filter in which we embed the bi-local CAT. The proposed filter performs as good as (and for certain applications even better than) state-of-the art methods
Jain, Dimpal. « Women of color student leaders the role of race and gender in community college transfer readiness / ». Diss., Restricted to subscribing institutions, 2009. http://proquest.umi.com/pqdweb?did=2025611511&sid=7&Fmt=2&clientId=1564&RQT=309&VName=PQD.
Texte intégralJorna, Gerard C. « Modulation transfer function measurements, image quality metrics, and subjective image quality for soft-copy color images ». Diss., This resource online, 1993. http://scholar.lib.vt.edu/theses/available/etd-10022007-145249/.
Texte intégralPattinson, Victoria A. « The transfer, storage and release of water colour in a reservoired catchment ». Thesis, University of Huddersfield, 1994. http://eprints.hud.ac.uk/id/eprint/4679/.
Texte intégralChan, Tat Leung. « Application of liquid crystal thermography in heat transfer characteristics of slot jet impingement ». Thesis, Nottingham Trent University, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.267018.
Texte intégralPaul, Daniel Earnest James. « Coat of Many Colors - Specificity of GalNAc Transferase Family of Isoenzymes ». Case Western Reserve University School of Graduate Studies / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=case1586253427484438.
Texte intégralGuducu, Hasan Volkan. « Building Detection From Satellite Images Using Shadow And Color Information ». Master's thesis, METU, 2008. http://etd.lib.metu.edu.tr/upload/12609920/index.pdf.
Texte intégraloutput. Satellite/aerial image is firstly filtered to sharpen the edges. Then, edges are extracted using Canny edge detection algorithm. These edges are the input for the Hough Transform stage which will produce line segments according to these extracted edges. Then, extracted line segments are used to generate building hypotheses. Verification of these hypotheses makes use of the outputs of the HSV color segmentation and shadow detection stages. In this study, color segmentation is processed on the HSV representation of the satellite/aerial image which is less sensitive to illumination. In order to perform the shadow detection, the basic information which is shadow areas have higher value of saturation component and lower value of value component in HSV color space is used and according to this information a mask is applied to the HSV representation of the image to produce shadow pixels. The proposed method is implemented as software written in MATLAB programming software. The approach was tested in several different areas. The results are encouraging.
Faggembauu, Débora. « Heat transfer and fluid-dynamics in double and single skin facades ». Doctoral thesis, Universitat Politècnica de Catalunya, 2006. http://hdl.handle.net/10803/6690.
Texte intégralEsta tesis incide fundamentalmente en el diseño eficiente de la fachada, ya que éste es uno de los principales elementos que determinan el comportamiento térmico de los edificios. No sólo actúa como barrera entre las condiciones externas e internas, sino que el diseño eficiente de la misma, contribuye en forma relevante a la reducción del consumo de calefacción, aire acondicionado, ventilación e iluminación. Asimismo, es un elemento que incide notablemente en las condiciones de salubridad y confort.
Actualmente, existe un gran auge del uso de fachadas completamente hechas de vidrio, este tipo de construcción presenta una serie de ventajas arquitectónicas y estéticas, pero desde el punto de vista térmico pueden representar problemas de sobrecalentamientos y pérdidas de energía importantes, tanto en las áreas mediterráneas como en otras zonas climáticas. En este sentido, las fachadas de doble piel, compuestas por dos capas separadas por un canal de aire, usado para evacuar o aprovechar la energía solar absorbida por la fachada, pueden representar una opción de diseño válida para solventar esta problemática. Asimismo, este tipo de diseño puede producir unas condiciones de confortabilidad adecuadas debido a la reducción de las temperaturas de las superficies interiores de las fachadas.
El objetivo de esta tesis es el de contribuir al estudio de sistemas pasivos en general, y fachadas avanzadas en particular. Para ello, se ha desarrollado una herramienta numérica para la simulación de fachadas de edificios de simple y doble piel. La principal característica de este código es la de asumir un comportamiento unidimensional y transitorio. Las ecuaciones gobernantes (continuidad, momentum y conservación de la energía) son resueltas mediante la aplicación del método de volúmenes finitos. Las fachadas incluyen elementos arquitectónicos novedosos, como materiales de cambio de fase, aislamiento transparente, superficies selectivas y colectores solares con acumuladores integrados en la superficie de las fachadas. En la tesis, se describen las características de los modelos físicos y matemáticos implementados y se definen parámetros instantáneos e integrados que describen el comportamiento térmico de las fachadas.
Los modelos numéricos implementados han sido sujetos a procesos de verificación y validación en diferentes formas: i) por comparación de los resultados numéricos con los obtenidos para situaciones simplificadas que cuentan con solución analítica, ii) por comparación con parámetros globales tabulados en la literatura de ciertas configuraciones de fachadas, y iii) por comparación de los resultados numéricos con los obtenidos experimentalmente en celdas de ensayo sometidas a diferentes condiciones climáticas.
Se presentan resultados de estudios paramétricos de diferentes configuraciones de fachadas y aplicaciones del código numérico para la optimización del diseño de fachadas de edificios emblemáticos del entorno. Como acciones futuras, se prevé la conexión de este tipo de simulaciones con otras de más alto nivel, bidimensionales, para optimizar zonas concretas de las fachadas.
A significant proportion of the total national energy budget of european countries goes toward energy consumption in buildings, therefore the efforts addressed to optimize building's thermal behaviour are of vital importance. In this sense, facades play a fundamental role. Not only do they act as barriers between external and internal conditions, but they can also help to reduce the consumption of energy for heating, ventilation and air conditioning. Moreover, they can help to produce healthy and comfortable indoor conditions. The use of large, transparent areas in facades is a common current practice. Despite the architectural interest of these glazed areas, in Mediterranean climatic conditions they are responsible for building overheating. In these zones, double-skin envelopes made up of two layers of glass separated by an air channel -to collect or evacuate the solar energy absorbed by the facade- are considered to be a design option that could resolve this issue. In other climatic conditions, large heat losses may constitute the most determinant factor. Anyway, the comfort parameters are influenced by the large transparent areas, also in this design aspect, double skin facades may contribute to obtain more comfortable and pleasant living spaces.
The objectives of this thesis are to give a step forward in the study and numerical analysis of passive systems in general, and advanced facades in particular. A one-dimensional and transient numerical code for the simulation of double and single skin facades including advanced technological elements, like phase change materials, transparent insulation and facade integrated collectors-accumulators has been developed. The features of the physic and mathematical models implemented are described and instantaneous or integratedperformance parameters describing thermal behaviour of the facades are defined. The numerical models implemented within the numerical tool have been subjected to a verification and validation process in different forms: by comparing the numerical results with those obtained for simplified situations with analytical solutions, with tabulated global performance coefficients of simple façade configurations and with the results of other building simulation codes. Experimental research has been carried out in test cells situated at different geographical locations, thus they were subjected to different climatic conditions. The main objective of the developed numerical code is to simulate advanced facades in order to assess the long term performance, and to account with a virtual tool to test passive designs, including challenging innovations.
The applications of the numerical tool described in this thesis, for the optimisation of facades of real buildings are presented. As future actions, the link of the one-dimensional simulations produced by this numerical tool with a multi-dimensional simulation of specific zones of the facades is foreseen.
Haigh, James Archer. « The application of Fourier transform Raman spectroscopy to problems of industrial interest ». Thesis, University of Southampton, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.307084.
Texte intégralGatti, Pruthvi Venkatesh, et Krishna Teja Velugubantla. « Contrast Enhancement of Colour Images using Transform Based Gamma Correction and Histogram Equalization ». Thesis, Blekinge Tekniska Högskola, Institutionen för tillämpad signalbehandling, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-14424.
Texte intégralBabbar, Naveen. « Regulation and function of spermidine/spermine N¹ acetyl transferase (SSAT) in colon carcinogenesis ». Diss., The University of Arizona, 2003. http://hdl.handle.net/10150/289966.
Texte intégralEslinger, Kimberly Lane Runyan Timothy J. « "-- And all the men knew the colors of the sea-- " : historical and archaeological investigation of the SS Commodore, Ponce Inlet, Florida / ». Access via ScholarShip, 2005. http://hdl.handle.net/10342/1113.
Texte intégralPresented to the faculty of the Department of History. Advisor: Timothy Runyan. Includes bibliographical references (leaves [134]-141). Also available via the World Wide Web. Adobe reader required.
Kay, Susan Barbara. « Radiative transfer modelling for sun glint correction in marine satellite imagery ». Thesis, University of Exeter, 2011. http://hdl.handle.net/10036/3523.
Texte intégralMcKee, David. « Nuclear Transparency and Single Particle Spectral Functions from Quasielastic A(e,e'p) Reactions up to Q2=8.1 GeV2 ». Washington, D.C : Oak Ridge, Tenn. : United States. Dept. of Energy. Office of Energy Research ; distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy, 2003. http://www.osti.gov/servlets/purl/824828-CBQre3/native/.
Texte intégralPublished through the Information Bridge: DOE Scientific and Technical Information. "JLAB-PHY-03-22" "DOE/ER/40150-2731" David McKee. 05/01/2003. Report is also available in paper and microfiche from NTIS.
Liu, Shuk Ming. « Single nucleotide polymorphism in human microsomal glutathione s-transferase gene and colorectal cancer / ». View Abstract or Full-Text, 2003. http://library.ust.hk/cgi/db/thesis.pl?BIOL%202003%20LIU.
Texte intégralIncludes bibliographical references (leaves 95-105). Also available in electronic version. Access restricted to campus users.
Girotti, Priscila Azevedo. « Análise morfoquantitativa dos neurônios mioentéricos e submucosos imunorreativos aos receptores P2X2 e P2X7, ao óxido nítrico sintase (NOS), à calretinina, à calbindina e à colina acetil transferase (ChAT) do colo distal de ratos submetidos à desnutrição e à renutrição protéica ». Universidade de São Paulo, 2008. http://www.teses.usp.br/teses/disponiveis/42/42131/tde-09102008-125826/.
Texte intégralThe aim of the work was to analyze the distal colon myenteric (MN) and submucous (SN) neurons immunoreactive for P2X2-7 receptors, calbindin (Calb-ir), calretinin (Calr-ir), choline acetyltransferase (ChAT) and nitric oxide synthase (NOS) of the animals submitted to undernutrition and refeeding proteic. Distal colon was used from nourished (N42), undernourished (D42) and refeeding (RN42) rats. The results have shown 100% coexpression of the myenteric and submucous Calb-ir, Calr-ir, ChAt-ir e NOS-ir neurons with P2X2-7-ir receptors. The MN density have shown increase of the 20% and 97% of the P2X2-7-ir, Calr-ir, ChAT-ir e NOS-ir neurons of the D42 group, and the SN have been increased 29% a 75% in the D42 group. In the MN neuronal profile have shown decrease P2X7-ir, Calb-ir, Calr-ir and ChAT-ir neurons of the 28% to 40% and in the PS P2X2-7-ir, Calb-ir and ChAT-ir of the 19% a 47% neurons in the D42 group. I concluded that, the undernutrition affects the enteric neurons and there was recuperation in the refeeding, this can influence the gastrintestinal functions.
Chen, Hui-Hsin, et 陳惠欣. « Applying Discrete Wavelet Transform to Color Transfer Algorithm for Color Images ». Thesis, 2014. http://ndltd.ncl.edu.tw/handle/bdx857.
Texte intégral國立臺中科技大學
資訊工程系碩士班
102
This study applied Discrete Wavelet Transform (DWT) to color transform for color images, that is different from the used complex statistical methods to calculate and determine during changing colors for the original image. The multi-resolution digital signals from LL3 values of DWT were applied to calculate the characteristics of Hue channel in HSV color space. As important information, the mean and standard deviation of LL3 are taken to determine the weights for original image and reference image individually. The Hue values of the original image were changed according to the LL3 possession of two images. According to the experimental results, the proposed color transform technology for color images can effectively use wavelet transform to obtain representative features. Even there are great color differences between original image and reference image, the original image could still be color changed without weird or unchangeable color.
Hsu, Shih-Kun, et 許世坤. « Transfer Image Color to Video ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/28557711836863587853.
Texte intégral國立暨南國際大學
資訊工程學系
93
Applying one image’s color style to a video is a promising technology for video applications. One simple solution is treating a video as a sequence of image frames and then applying the image-based color transfer algorithm on every frame. However, the transferred quality as a whole usually lacks of smoothness and harmony in color style, because the scene of the destination frame varies and is gradually different from that of the color source image (for example, during a video with panning or zooming operation). Although manually specifying the similar regions before transferring (the swatch mechansim) can get better quality, it is not suitable for our video case due to the high cost of manpower involved. To solve the visual defects and ease the cost, we propose an Adaptive Frame Pass (AFP) algorithm that is based on ιαβ color space to adaptively consider the processing parameters from not only the color source image, but the destination frame. Besides, we also discuss the problem when we apply color transfer mechanism to YCbCr color space, the working color space of JPEG and MPEG. We propose an objective “evaluation sequence” measurement to evaluate the smoothness quality of processed video shot. The experimental result shows that our approach produces perceptually more coherent, smooth, natural color style in video than the image-based approach does.
Wan, Hui-Wen, et 萬惠雯. « A Mechanism for Affective Color Transfer Based on Skin Color Preservation ». Thesis, 2013. http://ndltd.ncl.edu.tw/handle/32746908428672454677.
Texte intégral國立中央大學
資訊工程學系
101
As we know, color, one of important features for composing images, can affect people on emotional level. Photographers and designers usually enhance desired color in their works to convey feeling. Editing color theme of images achieves the goal to change the emotion evoked by images. In this thesis, a method to change the emotion in images by editing color content called affective color transfer is proposed, we focus on implementing color transfer in images to make overall color theme of input image be similar with reference image. The result can be evaluated by affective analysis proposed in our work, and the affective class of result image is consistent with reference image. The proposed skin color preserving phase prevents skin color from over-modification in original color transfer. Furthermore, we attach importance about the harmony of output image, combing both the opacity of input and output image in color transfer to reduce visual distortion. The proposed method performs well in not only general images but also images which exit human. Another mechanism is affective analysis in images. First, we define affective classes and then extract affective colors in the image to classify the affective class. By using saliency map, we extracted the affective color in the image exactly, and result of affective analysis is improved. Finally, experiment results of affective analysis and affective color transfer have confirmed the effectiveness of proposed method. Affective classes predicted by affective analysis accord with the emotion evoked by images. We compare the algorithm of color transfer between proposed method and other methods, where our method performs better.
Yao-Hsien, Huang. « Effective Color Transfer Algorithms for Images ». 2006. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0005-1708200614264800.
Texte intégralHuang, Yen-Chao, et 黃彥超. « Image Enhancement and Color Transfer Techniques ». Thesis, 2013. http://ndltd.ncl.edu.tw/handle/93686374360834703505.
Texte intégral國立臺灣大學
電信工程學研究所
101
In this thesis, we study two image processing techniques including image enhancement and color transfer. With the development of technology, people can use digital camera or cell phone to capture the photo in daily life. However, the results of these easily captured images are often not as good as expected. In order to make images clear and pleasing, one can use image enhancement techniques to adjust images. Contrast correction and sharpness enhancement are the two common methods of image enhancement. Traditional contrast enhancement is global correction. Global correction provides good results for either overexposed or underexposed images. But it produces disappoint results for images which have both bright region and dark region. Local correction can make both bright region and dark region clearer. To enhance sharpness, traditional unsharp masking uses low pass filter and usual addition and multiplication. However, traditional unsharp masking suffers from halo artifact and out-of-range problem. A general unsharp masking adopts edge preserving filter and generalized addition and multiplication to resolve above problems. After studying kinds of image enhancement techniques, we implement and compare these methods. In the applications of post-production industry and image composition, the color characteristic should be consistent between two or more images. Color transfer plays an important role in those of applications. Traditional method uses statistical matching to perform color transfer. When two images are too different, this method produces unnatural results. Histogram-based method improves the color similarity between the synthetic image and target image, but it suffers from grain artifact. We analyze and compare the methods as mentioned above, then provide an improvement of color transfer. Furthermore, we apply our color transfer method to perform image re-coloring for colorblindness. Hopefully to make a color-blind can enjoy more beautiful images. Finally, we apply our color transfer method to perform enhancement for underwater images. Ocean engineering researchers can get a clearer underwater image by our method.
Huang, Yao-Hsien, et 黃耀賢. « Effective Color Transfer Algorithms for Images ». Thesis, 2006. http://ndltd.ncl.edu.tw/handle/51575212288370065060.
Texte intégral國立中興大學
資訊科學系所
94
This dissertation presents three color transfer algorithms for images. The first algorithm is an automatic, swatch-based, color transfer (ACT) algorithm for two still images. It modifies colors in the source image by borrowing the color characteristics from the target image. The algorithm consists of three processes: a swatch generation process, a swatch matching and color transfer process, and a swatch boundary transition process. This swatch-based algorithm proceeds on color transfer with no user intervention, and produces visually plausible resultant images. Experimental results demonstrate that the ACT is superior to Reinhard et al.’s original user-intervention color transfer algorithm. The second algorithm presents a novel automatic color transfer approach for image sequence (ISCT). This ISCT algorithm renders an image sequence with color characteristics borrowed from three user-given target images. The algorithm completes the color transfer task with three processes: a forward color space conversion process, an image sequence process, and an image sequence animation process. Given a single input image (I1) and three target images (T1, T2, T3) as inputs, the algorithm produces an image sequence {Si} with color mood variations. The ISCT algorithm is fast. It achieves the goal of rendering an image sequence in several seconds. In addition, the user interface developed provides much freedom to visualize the rendered image sequence. Given only three target images, the ISCT algorithm demonstrates its feasibility to produce an image sequence with visually plausible effects. This algorithm is automatic, effective, and expeditious, and is appropriate for many applications. Finally, we recommend a generalized color transfer algorithm for image sequences (GISCT). There are two major differences between the GISCT algorithm and the ISCT algorithm. The first major difference is that the GISCT algorithm proposes a new color transfer approach (NCT) to eliminate the appearance of over-transformation, which occurs when the source and target image are not compatible. The second difference is that we present a generalized color variation curve (GCVC) in the GISCT algorithm. Specifically, a B-spline curve is automatically generated to interpolate color statistics, which provides more flexible control over in-between images. Experimental results show that the GISCT algorithm generates results in several seconds. It renders an image sequence with versatile color variations, producing more visually plausible appearance than those generated by the ISCT algorithm. In conclusion, the ACT algorithm produces results that are superior to its closest competitor. The novel ISCT and the GISCT algorithms generate an image sequence with color mood variation. These algorithms contribute significantly to the topic of color transfer in the computer graphics community.
Huang, S. C., et 黃紹傑. « Effective Color Transfer Using Transformation Techniques ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/86318354159886579745.
Texte intégral國立中興大學
資訊科學研究所
93
Colour theory has been the subject of intensive research these years in computer graphics community. Recently, researchers presented a color transfer algorithm in which needs two images, source and target images, inputted by users. The algorithm automatically delivers colors of target image onto source image. The resulting image’s color distributions will be similar to target’s. Reinhard’s algorithm has three advantages: 1) easy to understand, 2) easy to practice, and 3) less computational time. However, it has a distinct drawback, that is, as the source image’s color distributions does not match with target’s, the resulting image may not conform to our visual experiences. In this thesis, we followed Reinhard’s color transfer algorithm and employed a transformation technique to improve the drawback. The main concept is that we attempted to vary source image’s color distributions . Firstly, we let images be fit in with target’s distribution, and then we execute the color transfer operator. We used statistical transformation techniques, power and modulus transformations, to change the distributions of source image to avoid yielding an unnatural resultant image. The experimental results show that our algorithm produces a better result than Reinhard’s. This is due to the fact that we solve the unnatural problem so that the result can be adopted to our visual experiences, always the algorithm’s effects. In spite of solving the drawback efficiently, our algorithm can also employ successful images shown in Reinhard’s algorithm, providing more varied-style results. In addition, the transformation techniques can also be used to images to balance their luminance distributions. Overall, our proposed algorithm retains the advantages of Reinhard’s, and eliminates the unnatural effects. The benefit of our algorithm is to provide an easy way to simulate varied scenes with different applications such as movie, photography, and astronomy.
Cheng-Chung, Chang, et 張正忠. « Color Transfer for Image and Video ». Thesis, 2009. http://ndltd.ncl.edu.tw/handle/23191949994783192759.
Texte intégral亞洲大學
資訊與設計學系碩士班
97
With the popularization of the digital photography equipments, it becomes more and more convenient to acquire digital images and videos. Owing to the characteristics of being easily corrected and edited, the demand of image processing rises continuously. In the domain of image processing, color transfer is a novel skill of color processing. As image transfer is concerned, this study introduces an easy and fast method on image transfer as well as two interesting ways of video transfer. The study aims at enhancing the color matching relationship between a target image and a reference image. Referring to video transfer, the first proposed method is Single Scene Color Transfer for Video Algorithm. This algorithm aims at proceeding to develop color style transfer in accordance with the scenery video of single scene. The said algorithm has advantages of simplicity and high efficiency as a result of deriving from Reinhard et al.’s method. The second proposed method is Adaptability Color Transfer for Video Algorithm. This algorithm aims at producing special effect of moderating the variation of color style with time. Finally, the results of the experiment provide the strong support for the proposed methods.
Hsieh, Chang-Hsi. « Multiple Color Transfer : Example-Based Photo Enhancement ». 2007. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0001-2607200710404200.
Texte intégralHsieh, Chang-Hsi, et 謝昌熹. « Multiple Color Transfer : Example-Based Photo Enhancement ». Thesis, 2007. http://ndltd.ncl.edu.tw/handle/22239749441668911443.
Texte intégral臺灣大學
資訊工程學研究所
95
One of the most common situations in photo editing is that users want some specific effects but don’t know how to achieve them. Nevertheless, they have an image in their mind about how the photo should be, which is derived from a better photo on similar subjects, or from their imagination. With this user motivation in mind, this thesis proposes a method for altering a photo’s color based on the coloring of another exemplary photo. Users simply set the requirement by drawing some pairs of brush strokes in corresponding regions and then the tool will perform the editing automatically. The goal of our tool is to enable the photo editor to easily alter the dissatisfied photo by referring the other acceptable photo. A suitable user interface have designed for drawing the corresponding regions between a source and one or more targets to transfer the desired color. Besides, in most general cases, users are just dissatisfied with a part of the photo, so our system allow users to edit their photo completely or partially by the same work flow, and our algorithm can preserve the satisfying or ex-editing region successfully. In this thesis, we find the region the user expect to edit by a graph cut optimization algorithm, and we have designed a new energy function which can consider the color and positional information simultaneously in this process. Additionally, a multiple color transfer method is developed to estimate the different influence of a set of transfer functions on a pixel and accumulate the influences to alter the pixel. Moreover, a image-guide optimization is used to increase the coherence in regions and eliminate the artifacts near edges in the result. We also display a variety application of our tool in this thesis, and Our system can produce accurate results that match users’ expectations. More importantly, the tool is very easy to learn; no photography or photo editing knowledge is required, and users don’t need to change their habit of taking photos.
Tung, Tzu-Chia, et 董子嘉. « Color Transfer Visual Cryptographic Scheme without Permutation Key ». Thesis, 2016. http://ndltd.ncl.edu.tw/handle/38611744522943146071.
Texte intégral國立東華大學
資訊工程學系
104
Visual cryptography scheme (VCS) is a kind of cryptography that can be directly decoded by human visual system when transparent films are stacked. It requires no computation for decryption. VCS is often implemented as a threshold (k, n) scheme, which a secret image is subdivided into n shadow images (called shadows). Any k shadows can be simply superimposed together to recover the secret image. However, (k1) or fewer shadows cannot obtain any secret information. This novel stacking-to-see property of VCS can be applied on various applications. Recently, Luo et al. introduced a notion of color transfer visual cryptographic scheme (CTVCS) by embedding the information of color channels R, G and B into the conventional (k, n)-VCS. Luo et al.’s (k, n)-CTVCS can visually decode the halftoned secret image by stacking any k shadow images like the conventional (k, n)-VCS, and meanwhile it can obtain a high-quality color image. These visual qualities are good enough to be used in commercial products, e.g., the ChLCD display of electronic paper book and advertising board. However, the information of color channels are represented explicitly on shadows, and thus a key is used to permute color pixels to achieve the security. Therefore, Luo et al.’s (k, n)-CTVCS is, strictly speaking, not a threshold scheme because the recovery of the information of color channels is based on a permutation key. Because a halftoned image is transformed from a gray-level image by digital halftoning technique, and the intensities of color channels can be converted to a grayscale. Therefore, there definitely exists a tight relation between the intensities of color channels and the pixel value of a halftoned image. By using an inherent property of digital image, we propose a (k, n)-CTVCS with perfect security, and do not need permuting pixels. We formally define contrast and security conditions of a (k, n) - CTVCS. Also, we theoretically prove that our CTVCSs satisfy these conditions. Experiment results demonstrate the feasibility of our constructions. Keywords: Visual cryptography, Secret Sharing, Threshold scheme, Color transfer VCS, halftoned image.
Lee, Hong-Chang, et 李鴻昌. « Efficient and Reversible Color Transfer Algorithms Between Images ». Thesis, 2005. http://ndltd.ncl.edu.tw/handle/12203353257068237056.
Texte intégral國立中興大學
資訊科學研究所
93
A color transfer algorithm changes colors of the source image by referring to the color of the target image. Previous color transfer algorithms suffered from intensive and laborious works to select an appropriate source image to make the resultant image with plausible visual appearance. This paper presents two color transfer algorithms to make color transfer more efficient and versatile. The first algorithm we present is an efficient color transfer algorithm. In this algorithm, we propose a fuzzy classification technique to achieve the efficiency in color transfer. This technique automatically calculates the total fuzzy values, given a source image. Then, M candidate target images are then selected which contain the largest M fuzzy values from an image database with L images. Given these candidate target images, a user can then perform a color transfer process as desired, generating N number of resultant images ( ). Each resultant image thus generated is guaranteed to demonstrate satisfactory color transfer effects with visually plausible image appearance. Given a source image, our system can efficiently produce 5 candidate target images (M=5) from an image bank with 1280 images (L=1280) within 3 seconds. In addition, our system can perform the color transfer computing and produce a resultant image (512x512) within 40 seconds. The proposed algorithm is feasible to produce a great diversity of resultant images with satisfactory qualities. The second algorithm we present is a reversible color transfer algorithm. In this algorithm, we propose a Steganography technique to embed 12 floating point values, representing as 468 bits, into the resultant images when performing the color transfer. These values include the means and variances of the source and target images in the l color space. We also utilize a spread spectrum technique so that more than one copy of the information is embedded into the resultant image. This technique ensures that the source and target image can be retrieved from the resultant image with a negligible visual appearance. The proposed algorithm has a benefit in saving the memory space by storing the resultant image. Also, the users can perform color transfer as many times as they desired, producing versatile and plausible visual image by using a single color transferred image together with an image database. In conclusion, we present two color transfer algorithms in this thesis. These algorithms are feasible to produce a great diversity of versatile color transfer images with satisfactory qualities.
Chang, Shiang-Chun, et 張翔竣. « A Novel Method For Color Transfer Using Histogram ». Thesis, 2009. http://ndltd.ncl.edu.tw/handle/58528826483086320800.
Texte intégral國立交通大學
多媒體工程研究所
97
In this thesis, we propose a novel method for color transfer using histogram. We can construct the histograms individually for both source and reference images based on the statistical analysis of them. After the construction of histograms, we perform segmentation in order to separate the histograms into multiple sections. According to the relationship of corresponding sections between the source and target images, we do color transfer from target to source. At the same time, there will be parameter interpolation between pairs of sections to solve the artifacts along the section boundary. In this way, we can transfer the color information from target image to source image and the result is better than the current methods.
Li, Long-Siang, et 李龍祥. « Example-based Color Transfer for Reversible Data Hiding ». Thesis, 2018. http://ndltd.ncl.edu.tw/handle/t78gah.
Texte intégral國立中興大學
資訊科學與工程學系
106
Histogram shifting or difference expansion were two popular schemes used for reversible data hiding. Color transfer changes color in a source image by referring to color of the target image to produce a visually plausible resultant image. Color transfer provides an alternative approach to achieving the reversibility. In this thesis, we combine color transfer and message embedding to become a reversible data hiding algorithm. Specifically, we conceal a secret message generated by a secret key when producing the resultant image simultaneously. This approach formulates the resultant image so that it offers the feature of reversibility. Then, the resultant image is regarded as a new cover image on which secret message can be conveyed to produce a marked image. In our study, we employ the weighted modulus algorithm to conceal secret message, which is controlled by the parameters (n, M), where n represents pixels in a pixel cluster and M denotes a secret digit in M-ary notational system. In the receiver part, the secret message is extracted using the weighted modulus scheme with the same parameters. Then, we conceal a particular secret message generated by the same secret key, accomplishing the cover image recovery. The combination of color transfer and reversible data hiding provides reversibility as well as steganographic benefits. In particular, if we conceal a real secret message instead of a secret message generated by the secret key, then we produce a stego image simultaneously when we produce the resultant image. Surely, it is difficult for a malicious eavesdropper to detect whether secret message is embedded in the resultant image. Experimental results demonstrate that our scheme is feasible to provide both steganographic and reversible features. In comparison of the current state-of-the-art reversible algorithms using contrast enhancement, our approach offers a much larger embedding rate, while producing a stego/marked image with a high visual quality.
Cheng, Chun-kai, et 程俊凱. « Color Image Segmentation Technique Using Wavelets Transform ». Thesis, 2003. http://ndltd.ncl.edu.tw/handle/07768809361511149516.
Texte intégral國立海洋大學
電機工程學系
91
Color images contain much homogenous regions information which can be divided into uniform regions by color characterization. There is no linear relationship among the color space transformations. In the previous, the color research, we found that most of researchers use gray level image segmentation methods to apply on color images. They totally ignore the color characterization. In recent years, some of them took the advantages of color to do segmentation in some device dependence color spaces. The goal of this research is to investigate an automatic image segmentation method which substitutes the traditional heuristic and intuited methods. We propose a color image segmentation technique using wavelet transform with multi-resolution technique. In accordance with the properties of color, we can segment color images in different color spaces to fulfill the functionality of color management. In segmentation process, we start from the toppest level, define the color of a pixel, and compare with the colors of neighboring pixels to decide the regions. After labeling the regions, we do inverse discrete wavelet to next level and label the regions level by level until reaching equal to original image. Then obtain a segmentation image with obvious boundary to achieve image segmentation. It is hoped that the research is much helpful in building a color management on the Internet, which is able to provide an automatic color management tool and standard for related industries. Keywords:Color Image、Segmentation、Wavelets、Multiresolution、Color Space
Le, Hoai-Nam, et 黎淮南. « Color to Grayscale Transform Preserving Maximum Information ». Thesis, 2010. http://ndltd.ncl.edu.tw/handle/19426495715898823556.
Texte intégral逢甲大學
通訊工程所
98
Color-to-gray conversion in many applications requires preserving the visual appearance and feature discrimination of color images. The existing methods are still need of improvement in this aspect. We propose two color-to-gray conversion algorithms. One is the global mapping based and the other is the local-global mapping based. The proposed methods convert accurately various categories of color images to grayscale images, including natural images, computational images, and painting images. The global mapping scheme is simple and fast, yet it preserves feature discrimination and appropriate color order of color images. The local-global mapping scheme not only retains the visual appearance of the color image but also compensates the global mapping method for possible loss of color information. Experimental results show that the proposed methods produced perceptually accurate and preferred images when they were compared with other schemes.