Document aesthetics measures are key to automated document composition. Recently we presented a probabilistic document model (PDM) which is a micro-model for document aesthetics based on a probabilistic modeling of designer choice in document design. The PDM model comes with efficient layout synthesis algorithms once the aesthetic model is defined. A key element of this approach is an aesthetic prior on the parameters of a template encoding aesthetic preferences for template parameters. Parameters of the prior were required to be chosen empirically by designers. In this work we show how probabilistic template models (and hence the PDM cost function) can be learnt directly by observing a designer making design choices in composing sample documents. From such training data our learning approach can learn a quality measure that can mimic some of the design tradeoffs a designer makes in practice.
In this paper, we propose a system for automatic design of magazine covers that quantifies a number of concepts from
art and aesthetics. Our solution to automatic design of this type of media has been shaped by input from professional
designers, magazine art directors and editorial boards, and journalists. Consequently, a number of principles in design
and rules in designing magazine covers are delineated. Several techniques are derived and employed in order to quantify
and implement these principles and rules in the format of a software framework. At this stage, our framework divides the
task of design into three main modules: layout of magazine cover elements, choice of color for masthead and cover lines,
and typography of cover lines. Feedback from professional designers on our designs suggests that our results are
congruent with their intuition.
Managing large document databases is an important task today. Being able to automatically com-
pare document layouts and classify and search documents with respect to their visual appearance
proves to be desirable in many applications. We measure single page documents' similarity with
respect to distance functions between three document components: background, text, and saliency.
Each document component is represented as a Gaussian mixture distribution; and distances between
dierent documents' components are calculated as probabilistic similarities between corresponding
distributions. The similarity measure between documents is represented as a weighted sum of the
components' distances. Using this document similarity measure, we propose a browsing mechanism
operating on a document dataset. For these purposes, we use a hierarchical browsing environment
which we call the document similarity pyramid. It allows the user to browse a large document dataset
and to search for documents in the dataset that are similar to the query. The user can browse the
dataset on dierent levels of the pyramid, and zoom into the documents that are of interest.
Even though technology has allowed us to measure many different aspects of images, it is still a challenge to
objectively measure their aesthetic appeal. A more complex challenge is presented when an arrangement of
images is to be analyzed, such as in a photo-book page. Several approaches have been proposed to measure the
appeal of a document layout that, in general, make use of geometric features such as the position and size of a
single object relative to the overall layout. Fewer efforts have been made to include in a metric the influence of
the content and composition of images in the layout. Many of the aesthetic characteristics that graphic designers
and artists use in their daily work have been either left out of the analysis or only roughly approximated in an
effort to materialize the concepts.
Moreover, graphic design tools such as transparency and layering play an important role in the professional
creation of layouts for documents such as posters and flyers. The main goal of our study is to apply similar
techniques within an automated photo-layout generation tool. Among other design techniques, the tool makes
use of layering and transparency in the layout to produce a professional-looking arrangement of the pictures.
Two series of experiments with people from different levels of expertise with graphic design provided us with the
tools to make the results of our system more appealing. In this paper, we discuss the results of our experiments
in the context of distinct graphic design concepts.
We present a general framework for the modeling and optimization of scalable large format 3-D displays using multiple
projectors. Based on this framework, we derive algorithms that can robustly optimize the visual quality of an arbitrary
combination of projectors (e.g. tiled, superimposed, combinations of the two) without manual adjustment. The
framework creates for the first time a new unified paradigm that is agnostic to a particular configuration of projectors yet
robustly optimizes for the brightness, contrast, and resolution of that configuration. In addition, we demonstrate that our
algorithms support high resolution stereoscopic video at real-time interactive frame rates achieved on commodity
graphics hardware. Through complementary polarization, the framework creates high quality multi-projector 3-D
displays at low hardware and operational cost for a variety of applications including digital cinema, visualization, and
Businesses have traditionally relied on different types of media to communicate with existing and potential customers.
With the emergence of the Web, the relation between the use of print and electronic media has continually evolved. In
this paper, we investigate one possible scenario that combines the use of the Web and print. Specifically, we consider the
scenario where a small- or medium-sized business (SMB) has an existing web site from which they wish to pull content
to create a print piece. Our assumption is that the web site was developed by a professional designer, working in
conjunction with the business owner or marketing team, and that it contains a rich assembly of content that is presented
in an aesthetically pleasing manner. Our goal is to understand the process that a designer would follow to create an
effective and aesthetically pleasing print piece. We are particularly interested to understand the choices made by the
designer with respect to placement and size of the text and graphic elements on the page. Toward this end, we conducted
an experiment in which professional designers worked with SMBs to create print pieces from their respective web pages.
In this paper, we report our findings from this experiment, and examine the underlying conclusions regarding the
resulting document aesthetics in the context of the existing design, and engineering and computer science literatures that
address this topic
We consider two physical systems where overlapped displays are employed: (1) Wobulation -a single projector that
rapidly shifts the entire display in time by a subpixel amount; (2) Several projector displays overlaid in space with a
complex array of space-varying subpixel offsets. In this work we focus on quantifying the resolution increase of these
approaches over that of a single projector. Because of the nature of overlapping projections with different degrees of
prospective distortion, overlaid pixels have space-varying offsets in both dimensions. Our simulator employs the
perspective transformation or homography associated with the particular projector geometry for each subframe. The
resulting simulated displays are stunningly accurate. We use "grill" patterns to assess the resolution performance that
vary in period, phase, and orientation. A new Fourier-based test procedure is introduced that generates repeatable results
that eliminate problems due to phase and spatial variation. We report on results for 2 and 4 position wobulation, and for
1, 2, 4, and 10 overlaid projectors using the frequency-domain based contrast modulation metric. The effects of subpixel
phase are illustrated for various grill periods. The results clearly show that resolution performance is indeed improved
for overlapped displays.
In this paper we introduce a class of linear filters called 'donut filters' for the design of halftone screens that enable robust printing with stochastic0 clustered dots. The donut filter approach is a simple, yet efficient method to produce pleasing stochastic clustered-dot halftone patterns (a.k.a AM-FM halftones) suitable for systems with poor isolated dot reproduction and/or significant dot-gain. The radial profile of a donut filter resembles the radial cross section of a donut shape, with low impulse response at the center that rises to a peak and drops off rapidly as the pixel distance from the center is increased. A simple extension for the joint design of any number of colorant screens is given. This extension makes use of several optimal linear filters that may be treated as a single donut multi-filter having matrix-valued coefficients. A key contribution of this paper is the design of the parametric donut filters to be used at each graylevel. We show that given a desired spatial pair-correlation profile (a.k.a. spatial halftone statistics), optimum donut filters may be generated, such that the donut filter based screen design produces patterns possessing the desired profile in the maximum-likelihood sense. In fact, 'optimal green-noise' halftone screens having the spatial statistics described by Lau, Arce and Gallagher may be produced as a special case of our design. We will also demonstrate donut filter designs that do not use an 'optimum green-noise' target profile in the design and yet produce excellent stochastic clustered-dot halftone screens.
Conventional grayscale error diffusion halftoning produces worms and other objectionable artifacts. Tone dependent error diffusion (Li and Allebach) reduces these artifacts by controlling the diffusion of quantization errors based on the input graylevel. Li and Allebach optimize error filter weights and thresholds for each (input)
graylevel based on a human visual system model. This paper extends tone dependent error diffusion to color. In color error diffusion, what color to render becomes a major concern in addition to finding optimal dot patterns. We present a visually optimum design approach for input level (tone) dependent error filters (for each color plane).
The resulting halftones reduce traditional error diffusion artifacts and achieve greater accuracy in color rendition.
A Visually significant two-dimensional barcode (VSB) developed by Shaked et. al. is a method used to design an information carrying two-dimensional barcode, which has the appearance of a given graphical entity such as a company logo. The encoding and decoding of information using the VSB, uses a base image with very few graylevels (typically only two). This typically requires the image histogram to be bi-modal. For continuous-tone images such as digital photographs of individuals, the representation of tone or "shades of gray" is not only important to obtain a pleasing rendition of the face, but in most cases, the VSB renders these images unrecognizable due to its inability to represent true gray-tone variations. This paper extends the concept of a VSB to an image bar code (IBC). We enable the encoding and subsequent decoding of information embedded in the hardcopy version of continuous-tone base-images such as those acquired with a digital camera. The encoding-decoding process is modeled by robust data transmission through a noisy print-scan channel that is explicitly modeled. The IBC supports a high information capacity that differentiates it from common hardcopy watermarks. The reason for the improved image quality over the VSB is a joint encoding/halftoning strategy based on a modified version of block error diffusion. Encoder stability, image quality vs. information capacity tradeoffs and decoding issues with and without explicit knowledge of the base-image are discussed.
We analyze color error diffusion with memory constraints. Color error diffusion requires the storage of error terms in an error buffer. We explore memory reduction by representing the error buffer in the YIQ space and allocating a finite number of bits to each channel. The error buffer is represented in a packed-bit format. This constrains the error buffer to a desired bit-width. However such a constraint degrades performance. The degradation is observed as an
increase in perceived color quantization noise. We derive an optimal solution for the error filter coefficients which minimize the visual effect of the memory constraint. Our formulation allows the filter coefficients to be matrix-valued allowing cross-channel diffusion of color errors. The optimal filter depends on the color characteristics of the device, viewing distance and the specific bit allocations used for the error buffer and the the rendering frame buffer.
Grayscale error diffusion introduces nonlinear distortion (directional artifacts and false textures), linear distortion (sharpening), and additive noise. Since error diffusion is 2-D sigma-delta modulation (Anastassiou, 1989), Kite et al. linearize error diffusion by replacing the thresholding quantizer with a scalar gain plus additive noise. Sharpening is proportional to the scalar gain. Kite et al. derive the sharpness control parameter value in threshold modulation (Eschbach and Knox, 1991) to compensate linear distortion. These unsharpened halftones are particularly useful in perceptually weighted SNR measures. False textures at mid-gray (Fan and Eschbach, 1994) are due to limit cycles, which can be broken up by using a deterministic bit flipping quantizer (Damera-Venkata and Evans, 2001). We review other variations on grayscale error diffusion to reduce false textures in shadow and highlight regions, including green noise halftoning Levien, 1993) and tone-dependent error diffusion (Li and Allebach, 2002). We then discuss color error diffusion in several forms: color plane separable (Kolpatzik and Bouman, 1992); vector quantization (Shaked et al. 1996); green noise extensions (Lau et al. 2000); and matrix-valued error filters (Damera-Venkata and Evans, 2001). We conclude with open research problems.