In this work we study the varying importance of faces in images. Face importance is found to be affected by the size and number of faces present. We collected a dataset of 152 face images with faces in different size and number of faces. We conducted a crowdsourcing experiment where we asked people to label the important regions of the images. Analyzing the results from the experiment, we propose a simple face-importance model, which is a 2D Gaussian function, to quantitatively represent the influence of the size and number of faces on the perceived importance of faces. The face-importance model is then tested for the application of salient-object detection. For this application, we create a new salient-objects dataset, consisting of both face images and non-face images, and also through crowdsourcing we collect the ground truth. We demonstrate that our face-importance model helps us to better locate the important, thus salient, objects in the images and outperforms state-of-the-art salient-object detection algorithms.
Printing appearance effects beyond colour - such as gloss - is an active research topic in the scope of multi-layer printing (2.5D or 3D printing). Such techniques may enable a perceptually more accurate reproduction of optical material properties and are required to avoid appearance related artefacts sometimes observed in regular colour printing - such as bronzing and differential gloss. In addition to technical challenges of printing such effects, a perceptual space that describes the related visual attributes is crucial; particularly to define perceptually meaningful tolerances and for appearance gamut mapping. In this paper, we focus on spatially-varying gloss created by varnish-halftones. This enables us to print specular gloss effects covering a large portion of the NCS gloss scale from full matte to high gloss. We then conduct a psychophysical experiment to find the relationship between measured specular gloss and a perceptually uniform gloss scale. Our results show that this relationship can be well described by a power function according to Stevens Power Law.
The studies regarding fine art reproduction mainly focus on the accuracy of colour and the recreation of surface texture
properties. Since reflection properties other than colour are neglected, important details of the artwork are lost. For
instance, gloss properties, often characteristic to painters and particular movements in the history of art, are not well
reproduced. The inadequate reproduction of the different gloss levels of a piece of fine art leads to a specular reflection
mismatch in printed copies with respect to the original works that affects the perceptual quality of the printout. We used
different print parameters of a 3D high resolution printing setup to control the gloss level on a printout locally. Our
method can be used to control gloss automatically and in crucial applications such as fine art reproduction.
Relief printing technology developed by Océ allows the superposition of several layers of colorant on different types of
media which creates a variation of the surface height defined by the input to the printer. Evaluating the reproduction
accuracy of distinct surface characteristics is of great importance to the application of the relief printing system. Therefore,
it is necessary to develop quality metrics to evaluate the relief process. In this paper, we focus on the third dimension of
relief printing, i.e. height information. To achieve this goal, we define metrics and develop models that aim to evaluate relief
prints in two aspects: overall fidelity and surface finish. To characterize the overall fidelity, three metrics are calculated:
Modulation Transfer Function (MTF), difference and root-mean-squared error (RMSE) between the input height map and
scanned height map, and print surface angle accuracy. For the surface finish property, we measure the surface roughness,
generate surface normal maps and develop a light reflection model that serves as a simulation of the differences between
ideal prints and real prints that may be perceived by human observers. Three sets of test targets are designed and printed by
the Océ relief printer prototypes for the calculation of the above metrics: (i) twisted target, (ii) sinusoidal wave target, and
(iii) ramp target. The results provide quantitative evaluations of the printing quality in the third dimension, and demonstrate
that the height of relief prints is reproduced accurately with respect to the input design. The factors that affect the printing
quality include: printing direction, frequency and amplitude of the input signal, shape of relief prints. Besides the above
factors, there are two additional aspects that influence the viewing experience of relief prints: lighting condition and
viewing angle.
Commonly known lenticular prints use a lens-like system superimposed on a standard 2D print to control the
light sent into each direction. Thanks to our 2.5D or relief printing system, we are capable of creating a lenticular
effect embedded directly on the prints that does not require the use of a system of lenses. On a zigzag-shaped
surface composed of continuous small triangles two source images are interlaced and printed on the sides of
the triangular structures, each side corresponding to one of the two intended views. The effect of crosstalk or
ghosting is often encountered in lenticular prints. Ghosting occurs when some parts of one source image remain
visible for the illumination or viewing direction corresponding to the other source image. In this work, we use an
image-content-driven technique that identifies the regions in the source images that are prone to cause ghosting
for a given set of viewing angles. For the purpose of eliminating this artefact, a model of the ghosting effect
appearance is implemented and used for compensation. We have observed improvements in the quality of the
lenticular effect, however the impact on the quality of the prints still needs to be evaluated.
An important aspect for print quality assessment is the perceived gloss level across the printout. There exists a strong
relationship between the surface roughness of a printout and the amount of specular reflection which is perceived as
gloss variations. Different print parameters influence the surface roughness of the printouts such as the paper substrate,
the type of inks and the print method. The lack of control over the print’s surface roughness may result in artefacts such
as bronzing and differential gloss.
Employing a 2.5D or relief printing system, we are able to control the printout roughness by manipulating the way the
ink is deposited in a layer-by-layer basis. By changing the deposition time in between two layers of white ink and the
order on which the pixels are printed, we achieve different gloss levels from a matte to a glossy appearance that can be
controlled locally. Understanding the relationship between different printing parameters and the resulting gloss level
allows us: to solve differential gloss artefacts (to obtain a print with a full gloss or matte finish) and to use the local gloss
variations to create reflection effects in the printouts. Applications related to security printing have also been explored.
Our results showed a reduced level of gloss toward a matte appearance as the ink deposition time between the layers was
increased, allowing more time for the ink to dry between passes. We measured the gloss levels using a gloss meter and a
psychophysical experiment was conducted to validate our measurements and observations.
Ink-saving strategies for CMYK printers have evolved from their earlier stages where the 'draft' print mode was
the main option available to control ink usage. The savings were achieved by printing alternate dots in an image
at the expense of reducing print quality considerably. Nowadays, customers are not only unwilling to compromise
quality but have higher expectations regarding both visual print quality and ink reduction solutions. Therefore,
the need for more intricate ink-saving solutions with lower impact on print quality is evident. Printing-related
factors such as the way the printer places the dots on the paper and the ink-substrate interaction play important
and complex roles in the characterization and modeling of the printing process that make the ink reduction
topic a challenging problem. In our study, we are interested in benchmarking ink-saving algorithms to find
the connections between different ink reduction levels of a given ink-saving method and a set of print quality
attributes. This study is mostly related to CMYK printers that use dispersed dot halftoning algorithms. The
results of our efforts to develop such an evaluation scheme are presented in this paper.
Common ink-saving techniques usually restrict the ink consumption when printing a document by replacing
a percentage of cyan, magenta, and yellow, by black ink. Even though such methods achieve a considerable
reduction in the amount of ink used in a page, the visual quality of the print is affected and unpleasing effects
in pastels and skin tones are observed. On the other hand, the quality of the print is not only affected by
the ink-saving algorithm, but also by the way the color halftoning algorithm arranges the dots in the print.
Therefore, the relationship between the contents of the document to be printed and the printing process needs to
be addressed by the ink-saving strategy. A color direct binary search halftoning method that strives to minimize
both the ink usage and the perceived error between the continuous-tone color image and the color halftone image
is proposed. Our goals are to estimate the effects of the ink-saving module of a printing workflow in individual
regions of the document, and to determine the dot arrangement and ink combination that consumes the least
amount of ink while preserving printing quality.
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.
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
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.