Brush Strokes Research Articles

Image hatching for visual cryptography

Image hatching (or nonphotorealistic line-art) is a technique widely used in the printing or engraving of currency. Diverse styles of brush strokes have previously been adopted for different areas of an image to create aesthetically pleasing textures and shading. Because there is no continuous tone within these types of images, a multilevel scheme is proposed, which uses different textures based on a threshold level. These textures are then applied to the different levels and are then combined to build up the final hatched image. The proposed technique allows a secret to be hidden using Visual Cryptography (VC) within the hatched images. Visual cryptography provides a very powerful means by which one secret can be distributed into two or more pieces known as shares. When the shares are superimposed exactly together, the original secret can be recovered without computation. Also provided is a comparison between the original grayscale images and the resulting hatched images that are generated by the proposed algorithm. This reinforces that the overall quality of the hatched scheme is sufficient. The Structural SIMilarity index (SSIM) is used to perform this comparison.

Influence of prophylaxis paste treatment on the abrasive wear of surface sealants

Objective. To investigate the abrasive wear of surface sealants (Seal&Protect and K-0184 (experimental sealant)) and the influence of pre-treatment with mineral deposit forming prophylaxis pastes (NUPRO Sensodyne and NUPRO) on this wear. Methods. One hundred and eight bovine dentine samples were randomly allocated to nine groups (1–9). Pre-treatment (10 s): groups 1–3: untreated, groups 4–6: NUPRO, groups 7–9: NUPRO Sensodyne. Sealing: groups 1, 4 and 7: unsealed, groups 2, 5 and 8: Seal&Protect, groups 3, 6 and 9: K-0184 (experimental sealer). Samples were then brushed with 12 000 brushing strokes (BS) with toothpaste slurry in an automatic brushing machine (120 BS/min; F = 2.5 N). Surface profiles were recorded at baseline, after pre-treatment and sealing and after each 2000 BS. Results. Total profile change (wear or gain due to pre-treatment, treatment and 12 000 BS): groups 1, 4 and 7 (no surface sealant) showed a not significantly different wear of 18.48 ± 2.63 µm, 24.98 ± 3.02 µm and 21.50 ± 5.47 µm, respectively. Remaining groups (sealed) showed a gain in height with no significant difference among each other. Wear in sealed groups (2, 3, 5, 6, 8 and 9) were not significantly different at all numbers of brushing strokes. Starting with 4000 BS, the wear in unsealed groups (1, 4 and 7) was statistically significantly higher compared to all other groups. Conclusion. Stability and wear resistance of surface sealants are not affected by pre-treatment of dentine with NUPRO Sensodyne. The surface sealants tested provide a stable protective surface layer on dentine, which lasts for at least 12 000 brushing strokes.

Pete the Cat and His Four Groovy Buttons by E. Litwin

Litwin, Eric. Pete the Cat and His Four Groovy Buttons. Illus. James Dean. New York: Harper, 2012. Print. Pete, the laid back, imperturbable puss is back and this time author and children’s performer Eric Litwin incorporates math into the story. Pete puts on his favourite shirt and begins to sing about his buttons. There is lots of repetition to help kids learn about numbers and subtraction. First Pete thinks about the total number of buttons and the numeral is displayed. Then the word “four” appears twice in the refrain: “My buttons my buttons, my four groovy buttons”. One by one the buttons pop-off and each time the resulting equation is displayed: “How many buttons are left? 4-1=3”. This sequence repeats until he is down to his belly button! As with the other Pete books, there is also a very important underlying message: don’t sweat the small stuff. Each time he loses another button, the author asks: “Did Pete cry? Goodness, no! Buttons come and buttons go”. This is reinforced in the conclusion: “I guess it simply goes to show that stuff will come and stuff will go. But do we cry? Goodness, No! We keep on singing”. Artist James Dean first painted an image of Pete in 1999 and the little bluish-black cat with the big yellow eyes is still going strong. His images are composed of bright, high-contrast colours. The visible brush strokes and thick black outlines create lots of interesting textures and highlights. Of particular note are the buttons that leave long spirals of black trailing behind them and look as if they are popping right off the page. Again, as with previous Pete books, ( I Love my White Shoes and Rockin’ My School Shoes), there is a free downloadable song available from the Harper Collins Web site (http://www.harpercollinschildrens.com/feature/petethecat/). The book is certainly engaging enough to be enjoyed on its own. However, there is also a substantial amount of bonus material on the web site that can be incorporated into school lessons or enjoyed at home: the song, links to a YouTube video that pairs animated images from the book with the song, printable activities and a link to a “School Jam” ipad/iphone app featuring Pete. A clever fusion of music and math sprinkled with a life lesson in resilience, this book would make a groovy addition to school and home libraries for preschool to early elementary school-aged children. Highly Recommended: 4 out 4 starsReviewer: Kim Frail Kim is a Public Services Librarian at the H.T. Coutts Education Library at the University of Alberta. Children’s literature is a big part of her world at work and at home. She also enjoys gardening, renovating and keeping up with her two-year old.

Interactive semiautomatic contour delineation using statistical conditional random fields framework

Contouring a normal anatomical structure during radiation treatment planning requires significant time and effort. The authors present a fast and accurate semiautomatic contour delineation method to reduce the time and effort required of expert users. Following an initial segmentation on one CT slice, the user marks the target organ and nontarget pixels with a few simple brush strokes. The algorithm calculates statistics from this information that, in turn, determines the parameters of an energy function containing both boundary and regional components. The method uses a conditional random field graphical model to define the energy function to be minimized for obtaining an estimated optimal segmentation, and a graph partition algorithm to efficiently solve the energy function minimization. Organ boundary statistics are estimated from the segmentation and propagated to subsequent images; regional statistics are estimated from the simple brush strokes that are either propagated or redrawn as needed on subsequent images. This greatly reduces the user input needed and speeds up segmentations. The proposed method can be further accelerated with graph-based interpolation of alternating slices in place of user-guided segmentation. CT images from phantom and patients were used to evaluate this method. The authors determined the sensitivity and specificity of organ segmentations using physician-drawn contours as ground truth, as well as the predicted-to-ground truth surface distances. Finally, three physicians evaluated the contours for subjective acceptability. Interobserver and intraobserver analysis was also performed and Bland-Altman plots were used to evaluate agreement. Liver and kidney segmentations in patient volumetric CT images show that boundary samples provided on a single CT slice can be reused through the entire 3D stack of images to obtain accurate segmentation. In liver, our method has better sensitivity and specificity (0.925 and 0.995) than region growing (0.897 and 0.995) and level set methods (0.912 and 0.985) as well as shorter mean predicted-to-ground truth distance (2.13 mm) compared to regional growing (4.58 mm) and level set methods (8.55 mm and 4.74 mm). Similar results are observed in kidney segmentation. Physician evaluation of ten liver cases showed that 83% of contours did not need any modification, while 6% of contours needed modifications as assessed by two or more evaluators. In interobserver and intraobserver analysis, Bland-Altman plots showed our method to have better repeatability than the manual method while the delineation time was 15% faster on average. Our method achieves high accuracy in liver and kidney segmentation and considerably reduces the time and labor required for contour delineation. Since it extracts purely statistical information from the samples interactively specified by expert users, the method avoids heuristic assumptions commonly used by other methods. In addition, the method can be expanded to 3D directly without modification because the underlying graphical framework and graph partition optimization method fit naturally with the image grid structure.

HelpingHand

Digital painters commonly use a tablet and stylus to drive software like Adobe Photoshop. A high quality stylus with 6 degrees of freedom (DOFs: 2D position, pressure, 2D tilt, and 1D rotation) coupled to a virtual brush simulation engine allows skilled users to produce expressive strokes in their own style. However, such devices are difficult for novices to control, and many people draw with less expensive (lower DOF) input devices. This paper presents a data-driven approach for synthesizing the 6D hand gesture data for users of low-quality input devices. Offline, we collect a library of strokes with 6D data created by trained artists. Online, given a query stroke as a series of 2D positions, we synthesize the 4D hand pose data at each sample based on samples from the library that locally match the query. This framework optionally can also modify the stroke trajectory to match characteristic shapes in the style of the library. Our algorithm outputs a 6D trajectory that can be fed into any virtual brush stroke engine to make expressive strokes for novices or users of limited hardware.

Abstract LB-46: Advocacy & Action

Abstract These powerful core statements communicate our purpose and express the heart and soul of all we do, and why we do it. Mission Rooted in God's love; we treat illness and promote wellness for all people. Vision Our vision is to set the standards of excellence in delivery of health care throughout the regions we serve. Values The following values are represented by the six brush strokes preceding our name in the logo. They serve as a reminder to ourselves and our community that our values precede-literally and figuratively-everything we do. - Compassion: Showing empathy and concern for everyone and responding with kindness, and sensitivity. - Quality: Optimizing talents, skills and abilities to achieve excellence in meeting and exceeding our patients’ expectations - Integrity: Adhering without compromise to high moral principles of honest, loyalty, sincerity and fairness - Courtesy: Demonstrating polite, cooperative and respectful behavior; showing consideration and care for each person - Accountability: Using material good wisely; being conscious of the environment; being accountable for prudent use of our talents and financial resources. -Team Work: Working together to accomplish task and goals; recognizing the interdependence of one another and cache person's unique gifts. Navigators Three patient navigators are employed at Lewis Cancer & Research Pavilion. The LCRP also employs patient resource navigators (social workers). Citation Format: {Authors}. {Abstract title} [abstract]. In: Proceedings of the 103rd Annual Meeting of the American Association for Cancer Research; 2012 Mar 31-Apr 4; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2012;72(8 Suppl):Abstract nr LB-46. doi:1538-7445.AM2012-LB-46

A multi-level depiction method for painterly rendering based on visual perception cue

Increasing the level of detail (LOD) in brushstrokes within areas of interest improved the realism of painterly rendering. Using a modified quad-tree, we segmented an image into areas with similar levels of saliency; each of these segments was then used to control the brush strokes during rendering. We could also simulate real oil painting steps based on saliency information. Our method runs in a reasonable fine and produces results that are visually appealing and competitive with previous techniques.

Inferior Alveolar Nerve Deficits and Recovery Following Surgical Removal of Impacted Mandibular Third Molars

(1) To determine the incidence of inferior alveolar nerve (IAN) deficits following surgical extraction of mandibular third molar. (2) To document recovery of IAN injuries. A total of 400 lower third molars were extracted, 205 male patients and 195 females. All underwent extraction by the prescribed buccal approach. All cases were examined by one examiner preoperatively and postoperatively, at 7days, one month, two months and six months. Two-point discrimination test (2-pd), brush stroke direction (BSD), contact detection, pin prick and thermal testing was carried out. One patient presented with IAN injury (0.25%). This single case of nerve injury was mesioangular, Level B, Class 2, impaction with a difficulty rating of 5. Levels A and B tests (2PD, BSD, Contact detection) were altered. In these tests, the IAN did not show any signs of recovery by six months. Level C tests (pin prick test, sharp blunt detection) showed that the nerve had recovered completely by two months.

Human computer interactions for converting color images to gray

A classical image processing problem is converting color images to gray. This paper presents a Virtual Luminance Axis (VLA) to provide users a friendly interface to control the conversion process. The user selects several interesting color regions by drawing a few brush strokes, and then tunes the maximum and minimum of the corresponding band for each kind of color on the VLA. Our algorithm derives global mapping of the color space onto the VLA as close as possible. In this way, the user can “tune” the resulting image to produce the ideal effects he desires. Quantization and interpolating techniques are employed to accelerate the computation. The experiments show that the final gray is transferred as user defines.

Toothbrush Abrasion of Resin Composites with Different Filler Concepts

ABSTRACT Purpose To investigate the effect of tooth brushing wear with and without calcium carbonate slurry on four commercial resin composites based on different filler concepts. Materials and methods One nanofiller composite MI FIL (MFI, GC), one conventional hybrid type Venus (VEN) and two nanohybrid composites Venus Diamond (VED) and Venus Pearl (VEP) all from Heraeus Kulzer were examined. Forty beam-shaped specimens (12 × 3 × 3 mm) from each product were prepared and subdivided in two equal groups for pregrinding on SiC paper #600 and #4000 respectively. Ten specimens of each pre-ground group were subjected to toothbrush abrasion with calcium carbonate slurry, and 10 to toothbrushing with water only. The samples were submitted to five subsequent runs of 10,000 brushing strokes. Depth of wear and surface roughness (Ra) were measured with a profilometer after each 10 k strokes. Specimens after 50 k strokes were assessed by SEM. Additionally, the KHN (0.25 N/15 s) and the degree of conversion (DC) were determined. Data analysis was done by linear regression and ANOVA followed by Tukey's post-hoc test (p ≤ 0.05). Results Toothbrushing with abrasive slurry produced significantly different wear depths: VEN > MIF > VEP > VED. Linear relationships between depth of wear and number of cycles (r2 ≥ 0.94) were established for each material. Pregrinding with SiC #4000 resulted in less wear than pregrinding with #600. Ra figures were much higher for VED than for the other materials tested. MIF and VEN were uniformly abraded, whereas the largest glass fillers in VED protruded from the surroundings and the prepolymer particles in VEP were deeper abraded than the bulk of the material. Toothbrushing with water only revealed not measurable wear. Roughness Ra was practically unchanged when compared with the preground samples before challenging with toothbrushes. Ranking by KHN was: MIF < VEN, VEP < VED, by DC: MIF < VEN < VEP < VED. Conclusion Filler concepts and monomer compositions affect wear and roughness of resin composites when tooth brushed with abrasive slurry. Toothbrushing without abrasive medium produced neither wear nor roughness. Careful polishing of resin composite restorations is an important determinant of wear and surface roughness. How to cite this article Suzuki T, Kyoizumi H, Araki Y, Finger WJ, Kanehira M. Toothbrush Abrasion of Resin Composites with Different Filler Concepts. World J Dent 2012;3(2):184-193.

Does any relationship exist between self reported gingival bleeding, oral health perception, practices and concerns?

Background:The objective was to determine the relationship between self-reported gingival bleeding, oral health perception, practices and concerns.Materials and Methods:This cross-sectional survey among undergraduates of University of Benin, Benin City, Nigeria was conducted between April and May, 2011 using a self-administered 21-item structured questionnaire. Data analysis was done using Statistical Packages for the Social Sciences and P<0.05 was considered significant.Results:Out of the 400 questionnaires that were distributed, 338 were returned filled giving a retrieval rate of 84.5%. About three-quarters (71.3%) of the respondents were younger than 22 years. Males constituted 65.1% while the remaining 34.9% were females. The prevalence of self-reported gingival bleeding among respondents in this study was 12.7%. Individuals with gingival bleeding were significantly more likely to rate their dental and gingival health as fair/poor, use strong brushing stroke during tooth brushing and report worsening condition of teeth despite daily tooth brushing, express worry about the gingival color and less likely to be satisfied about the appearance of their teeth and to have received professional instruction on tooth brushing.Conclusion:Data from this survey revealed an established relationship between gingival bleeding, perceived dental and gingival health, tooth brushing force, professional instruction on tooth brushing, perception of the condition of teeth in relation to daily tooth brushing, worry about the color of gingiva, and satisfaction with the appearance of the teeth.

“Th’eternal Brood of Glorie Excellent”: Infants and the Battle for the Future in The Faerie Queene

Given the prominence of infants in The Faerie Queene—both literal children and questing “infant” scions of distinguished families—disappointingly little criticism has had anything to say about them. Even more disconcerting, most scholarship on the subject has focused almost exclusively on readings of separation anxiety and alienation; more extreme examples paint generation and reproduction themselves with broad brush strokes the color of disdain. Childhood becomes a tragicomic parallel to Hobbes’s memorable specter of the chaotic condition of humanity before establishing a government: “solitary, poor, nasty, brutish, and [of course] short.” It is now high time for a balanced reading of reproduction and children in The Faerie Queene. While Spenser’s infants may suffer from alienation and what contemporary psychoanalysis calls separation anxiety, those developmental struggles are crucial steps in the transformative process of the quest. The next generation is born into grave conflict, but generation itself is a good and necessary thing that imbues progeny with the power of their ancestors and recalls the necessity of future (re)generation in the constant imperative of dynastic renaissance. Spenser’s foundling children and infant knights are avatars of “th’eternal brood of glorie excellent” that will continue the allegorical struggle for the triumph of virtue when the current generation is dead and gone.

Intoning the Male and Female Voices in a Novel by Eva Figes

AMY CHRISTINE PARKER University of Manitoba The book Light, with Monet at Giverny: A Novel is a story that imaginatively describes a day in the life of the Monet family. It is written by one of the feminist writers of the first wave which ended in the seventies, ‘‘Simone de Beauvoir, Betty Friedan, Eva Figes, Germaine Greer, Shulamith Firestone, and Kate Millett’’, as described by Susan Watkins in Twentieth Century Women Novelists: Feminist Theory into Practice. Watkins’ book describes these women as being opposed to contemporary interpretations of Freudian theory, and in particular to certain aspects of his description of the Oedipus complex which they see as patriarchal and arising from capitalist values and the hypothesis that hysteria is self-motived rather than a problem of sexuality. Yet what Sally Robinson recognizes in Engendering the Subject: Gender and Self-representation in Contemporary Women’s Fiction as the refreshing plurality of the voices of these feminist authors is characteristic as well of those who remain faithful to religion or Christianity, which are traditionally feminine voices. This paper searches for the developing voice of women in this work of fiction by Eva Figes and recognizes as well the presence of the continuing male voices. A positive aspect of Figes’ novels is the fact that she often finds a way for a character to thrive despite harsh conditions. Throughout the novel, exterior sounds such as a clock counting the hours, a nearby passing train, singing birds and galloping horses create some sonorous effects. As the land lies amongst hills and a river, echoes can also be heard. These sounds punctuate the dialogues and silences within which much of the meaning of the story is contained. In this novel about an artistic family, the auditory effects are enhanced by visual motifs of light and color. In another of her novels, The Knot, there is a similar recurrence of ‘[n]ot

Influence of Light-Curing Mode on the Erosion Preventive Effect of Three Different Resin-Based Surface Sealants

Objectives. To investigate if reducing the light-curing time (while maintaining similar energy density) of resin-based surface sealants influences their erosion-preventive potential and mechanical stability after thermomechanical loading. Methods. Dentine samples were treated as follows: group 1—untreated, groups 2–4—Seal&Protect, groups 5–7—experimental sealer, and groups 8–10—Syntac Classic system. Groups 2, 5 and 8 were light-cured for 10 s (1000 mW/cm2), groups 3, 6 and 9 for 7 s (1400 mW/cm2), and groups 4, 7, and 10 for 3 s (3200 mW/cm2). After water storage (7 d), first measurement was performed to evaluate baseline permeability of the sealants. After a thermomechanical loading (5000 cycles, 50/5°C, 12000 brushing strokes) a second evaluation of permeability was conducted (measurement 2). Permeability was tested by storing the samples in HCl (pH 2.3; 24 h) and measuring the dentine calcium release by atomic absorption spectroscopy. Results. For the first and second measurements, no influence of light-exposure time on permeability was observed (ANOVA: P > 0.05). No significant difference in the stability of the respective sealants was observed when light-cured for different durations. Conclusion. Shortening the light-curing time, while maintaining energy density constant, has no influence on permeability and stability of the investigated sealants.

Evaluation of Trend Localization with Multi-Variate Visualizations

Multi-valued data sets are increasingly common, with the number of dimensions growing. A number of multi-variate visualization techniques have been presented to display such data. However, evaluating the utility of such techniques for general data sets remains difficult. Thus most techniques are studied on only one data set. Another criticism that could be levied against previous evaluations of multi-variate visualizations is that the task doesn't require the presence of multiple variables. At the same time, the taxonomy of tasks that users may perform visually is extensive. We designed a task, trend localization, that required comparison of multiple data values in a multi-variate visualization. We then conducted a user study with this task, evaluating five multivariate visualization techniques from the literature (Brush Strokes, Data-Driven Spots, Oriented Slivers, Color Blending, Dimensional Stacking) and juxtaposed grayscale maps. We report the results and discuss the implications for both the techniques and the task.

Mixed-order compositing for 3D paintings

We present a method for rendering 3D paintings by compositing brush strokes embedded in space. The challenge in compositing 3D brush strokes is reconciling conflicts between their z -order in 3D and the order in which the strokes were painted, while maintaining temporal and spatial coherence. Our algorithm smoothly transitions between compositing closer strokes over those farther away and compositing strokes painted later over those painted earlier. It is efficient, running in O ( n log n ) time, and simple to implement. We demonstrate its effectiveness on a variety of 3D paintings.

Brain mechanisms for processing affective touch.

Despite the crucial role of touch in social development, there is very little functional magnetic resonance imaging (fMRI) research on brain mechanisms underlying social touch processing. The "skin as a social organ" hypothesis is supported by the discovery of C-tactile (CT) nerves that are present in hairy skin and project to the insular cortex. CT-fibers respond specifically well to slow, gentle touch such as that which occurs during close social interactions. Given the social significance of such touch researchers have proposed that the CT-system represents an evolutionarily conserved mechanism important for normative social development. However, it is currently unknown whether brain regions other than the insula are involved in processing CT-targeted touch. In the current fMRI study, we sought to characterize the brain regions involved in the perception of CT-supported affective touch. Twenty-two healthy adults received manual brush strokes to either the arm or palm. A direct contrast of the blood-oxygenation-level-dependent (BOLD) response to gentle brushing of the arm and palm revealed the involvement of a network of brain regions, in addition to the posterior insula, during CT-targeted affective touch to the arm. This network included areas known to be involved in social perception and social cognition, including the right posterior superior temporal sulcus and the medial prefrontal cortex (mPFC)/dorso anterior cingulate cortex (dACC). Connectivity analyses with an mPFC/dACC seed revealed coactivation with the left insula and amygdala during arm touch. These findings characterize a network of brain regions beyond the insula involved in coding CT-targeted affective touch.

Comparison of Current Perception Threshold Electrical Testing to Clinical Sensory Testing for Lingual Nerve Injuries

We performed a retrospective study of lingual nerve injury assessment comparing the techniques of current perception threshold testing versus clinical sensory testing. We designed and implemented a cross-sectional study and enrolled a patient sample with lingual nerve injuries presenting for treatment to the principal investigator. The predictor variables were clinical sensory testing modalities (ie, temperature, nocioception, vibration, 2-point discrimination, brush stroke, and von Frey monofilament perception). The primary outcome variable was the electrical current perception thresholds of the tongue dorsum (neurometer measurements at 5, 250, and 2,000 Hz). Comparisons were established with the ipsilateral affected and contralateral unaffected lingual nerve distributions. The associations between the clinical sensory testing and current perception threshold measurements were assessed using correlation coefficients, with the level of statistical significance set at P < .05. A total of 40 patients (13 males and 27 females) were included in the present study. The average age of these patients was 34 years (range 13 to 66). Significant correlations were observed between the electrical stimulation thresholds at 2,000 Hz and the 2-point discrimination, reaction to brushing, reaction to vibration, and von Frey fiber thresholds, between the electrical stimulation thresholds at 250 Hz to the nociceptive and thermal thresholds, and between the electrical stimulation thresholds at 5 Hz to thermal stimuli. The significant correlations observed in the present study indicate that current perception threshold can be a complementary or alternative tool in the assessment and evaluation of lingual nerve injuries.

High-quality tactile paintings

The aim of this work is to bring the cultural heritage of two-dimensional art closer to being accessible by blind and visually impaired people. We present a computer-assisted workflow for the creation of tactile representations of paintings, suitable to be used as a learning tool in the context of guided tours in museums or galleries. Starting from high-resolution images of original paintings, our process allows an artist to quickly design the desired form, and generate data suitable for rapid prototyping machines to produce the physical touch tools. Laser-cut layered depth diagrams convey not only the individual objects in the painting and their spatial layout, but also augment their depth relations. CNC-milled textured reliefs additionally render fine details like brush strokes and texture suitable for the sense of touch. Our methods mimic aspects of the visual sense, make sure that the haptic output is quite faithful to the original paintings, and do not require special manual abilities like sculpting skills.

A Framework for content-adaptive photo manipulation macros

We present a framework for generating content-adaptive macros that can transfer complex photo manipulations to new target images. We demonstrate applications of our framework to face, landscape, and global manipulations. To create a content-adaptive macro, we make use of multiple training demonstrations. Specifically, we use automated image labeling and machine learning techniques to learn the dependencies between image features and the parameters of each selection, brush stroke, and image processing operation in the macro. Although our approach is limited to learning manipulations where there is a direct dependency between image features and operation parameters, we show that our framework is able to learn a large class of the most commonly used manipulations using as few as 20 training demonstrations. Our framework also provides interactive controls to help macro authors and users generate training demonstrations and correct errors due to incorrect labeling or poor parameter estimation. We ask viewers to compare images generated using our content-adaptive macros with and without corrections to manually generated ground-truth images and find that they consistently rate both our automatic and corrected results as close in appearance to the ground truth. We also evaluate the utility of our proposed macro generation workflow via a small informal lab study with professional photographers. The study suggests that our workflow is effective and practical in the context of real-world photo editing.