The question to be answered by this research is how would a fine artist working in South Africa, identify and use the correct digital printing techniques to accurately print their work?

No description available.

Thesis (Ph.D)--Computing, Georgia Institute of Technology, 2010. / Committee Chair: Guzdial, Mark; Committee Member: Abowd, Gregory; Committee Member: Mynatt, Elizabeth; Committee Member: Smith, Michael; Committee Member: Thomas, John. Part of the SMARTech Electronic Thesis and Dissertation Collection.

published_or_final_version / abstract / Electrical and Electronic Engineering / Master / Master of Philosophy

Photo enhancement is an important and practical problem in computer vision. In real-word applications, there are massive needs for photo quality enhancement. Image cropping and image color enhancement are two common operations used to improve the visual quality of photographs. By learning from human examples, we propose automatic photo enhancement method which implements these two fundamental operations. / For image cropping, we present an automatic cropping technique that accounts for the two primary considerations of people when they crop: removal of distracting content, and enhancement of overall composition. Our approach utilizes a large training set consisting of photos before and after cropping by expert photographers to learn how to evaluate these two factors in a crop. In contrast to the many methods that exist for general assessment of image quality, ours specifically examines differences between the original and cropped photo in solving for the crop parameters. To this end, several novel image features are proposed to model the changes in image content and composition when a crop is applied. The effectiveness of each feature is empirically analyzed in determining a final feature set for crop computation. Our experiments demonstrate improvements of our method over recent cropping algorithms on a broad range of images. / We also present a machine-learned ranking approach for automatically enhancing the color of a photograph. Unlike previous techniques that train on pairs of images before and after adjustment by a human user, our method takes into account the intermediate steps taken in the enhancement process, which provide detailed information on the person's color preferences. To make use of this data, we formulate the color enhancement task as a learning-to-rank problem in which ordered pairs of images are used for training, and then various color enhancements of a novel input image can be evaluated from their corresponding rank values. From the parallels between the decision tree structures we use for ranking and the decisions made by a human during the editing process, we posit that breaking a full enhancement sequence into individual steps can facilitate training. Our experiments show that this approach compares well to existing methods for automatic color enhancement. / Yan, Jianzhou. / Thesis (Ph.D.)--Chinese University of Hong Kong, 2014. / Includes bibliographical references (leaves 105-115). / Title from PDF title page (viewed on 30, November, 2016).

Luo, Yiwen. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2008. / Includes bibliographical references (p. 38-41). / Abstracts in English and Chinese. / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Image Search by Multi-Class Query --- p.1 / Chapter 1.1.1 --- Related Work --- p.2 / Chapter 1.1.2 --- Our Method --- p.4 / Chapter 1.2 --- Image and Video Quality Assessment --- p.5 / Chapter 1.2.1 --- Related Work --- p.6 / Chapter 1.2.2 --- Our Method --- p.6 / Chapter 2 --- Multi-Class Query Image Search System --- p.8 / Chapter 2.1 --- System Description --- p.8 / Chapter 2.1.1 --- Multi-Query Search --- p.8 / Chapter 2.1.2 --- Image Annotation --- p.9 / Chapter 2.1.3 --- Image Re-ranking --- p.10 / Chapter 2.2 --- Algorithm Description --- p.10 / Chapter 2.3 --- Evaluation and Results --- p.12 / Chapter 3 --- Image and Video Quality Assessment --- p.15 / Chapter 3.1 --- Criteria for Assessing Photo Quality --- p.15 / Chapter 3.1.1 --- Composition --- p.15 / Chapter 3.1.2 --- Lighting --- p.16 / Chapter 3.1.3 --- Focus Controlling --- p.16 / Chapter 3.1.4 --- Color --- p.17 / Chapter 3.2 --- Features for Photo Quality Assessment --- p.18 / Chapter 3.2.1 --- Subject Region Extraction --- p.18 / Chapter 3.2.2 --- Clarity Contrast Feature --- p.20 / Chapter 3.2.3 --- Lighting Feature --- p.21 / Chapter 3.2.4 --- Simplicity Feature --- p.22 / Chapter 3.2.5 --- Composition Geometry Feature --- p.22 / Chapter 3.2.6 --- Color Harmony Feature --- p.23 / Chapter 3.3 --- Features for Video Quality Assessment --- p.24 / Chapter 3.3.1 --- Length of Subject Region Motion --- p.24 / Chapter 3.3.2 --- Motion Stability --- p.26 / Chapter 3.4 --- Classification --- p.26 / Chapter 3.5 --- Experiments --- p.27 / Chapter 3.5.1 --- Photo Assessment --- p.27 / Chapter 3.5.2 --- Video Assessment --- p.28 / Chapter 3.5.3 --- Web Image Ranking --- p.31 / Chapter 4 --- Conclusion --- p.36 / Bibliography --- p.38 / Chapter A --- Supplementary Materials of Photo Quality Assessment --- p.42 / Chapter A.l --- Photo Database --- p.42 / Chapter A.2 --- Web Image Ranking

An abstract of the thesis of Ben Huang for the Master of Science in Electric and Computer Science presented [August 12nd, 2010]. Title: Removing textured artifacts from digital photos by using spatial frequency filtering Virtually all image processing is now done with digital images. These images, captured with digital cameras, can be readily processed with various types of editing software to serve a multitude of personal and commercial purposes. But not all images are directly captured and even of those that are directly captured many are not of sufficiently high quality. Digital images are also acquired by scanning old paper images. The result is often a digital image of poor quality. Textured artifacts on some old paper pictures were designed to help protect pictures from discoloration. However, after scanning, these textured artifacts exhibit annoying textured noise in the digital image, highly degrading the visual definition of images on electronic screens. This kind of image noise is academically called global periodic noise. It is in a spurious and repetitive pattern that exists consistently throughout the image. There does not appear to be any commercial graphic software with a tool box to directly resolve this global periodic noise. Even Photoshop, considered to be the most powerful and authoritative graphic software, does not have an effective function to reduce textured noise. This thesis addresses this problem by proposing the use of an alternative graphic filter to what is currently available. To achieve the best image quality in photographic editing, spatial frequency domain filtering is utilized instead of spatial domain filtering. In frequency domain images, the consistent periodicity of the textured noise leads to well defined spikes in the frequency transform of the noisy image. When the noise spikes are at a sufficient distance from the image spectrum, they can be removed by reducing their frequency amplitudes. The filtered spectrum may then yield a noise reduced image through inverse frequency transforming. This thesis proposes a method to reduce periodic noise in the spatial frequency domain; summarizes the difference between DFT and DCT, FFT and fast DCT in image processing applications; uses fast DCT as the frequency transform to solve the problem in order to improve both computational load and filtered image quality; and develops software that can be implemented as a plug in for large graphic software to remove textured artifacts from digital images.

Not available / text

South African photojournalists’ perception of digital technology’s impact on the credibility of news photographs is investigated in this study. Digital technology has the capabilities to produce “manipulated” photographs that appear realistic and credible. Credibility is dependent on a variety of factors including codes of realism and codes of production, which fit conventional codes of photographic representation. Manipulation is the act of deviating from accepted codes of photographic representation that may jeopardise the credibility of news photography. This thesis proposes a new theoretical framework that encompasses existing theories of semiotics, ideology, naturalism, realism and credibility. These theories underpin the definitions and discussion on manipulation and credibility. A descriptive survey is used which attempts to discover photojournalists’ views towards credibility. This research draws on qualitative research methods using a largely qualitative questionnaire, which generates both qualitative and quantitative data. The questions are formulated around two case studies of digitally manipulated photographs. The trends and responses in the research data are connected and discussed. The findings of this study are discussed in terms of credibility, awareness of the digital changes, the reason for the changes, the role of a caption, deletion techniques and background changes. The empirical situation is analysed in relation to the theoretical discussions and this study’s theorisation of photographic representation.

No description available.