Skip to main content
main-content

Über dieses Buch

This book examines paintings using a computational and quantitative approach. Specifically, it compares paintings to photographs, addressing the strengths and limitations of both. Particular aesthetic practices are examined such as the vista, foreground to background organisation and the depth planes. These are analysed using a range of computational approaches and clear observations are made. New generations of image-capture devices such as Google goggles and the light field camera, promise a future in which the formal attributes of a photograph are made available for editing to a degree that has hitherto been the exclusive territory of painting. In this sense paintings and photographs are converging, and it therefore seems an opportune time to study the comparisons between them. In this context, the book includes cutting-edge work examining how some of the aesthetic attributes of a painting can be transferred to a photograph using the latest computational approaches.

Inhaltsverzeichnis

Frontmatter

Image Attributes and Aesthetic Aspects

Frontmatter

Chapter 1. The Portrait and Landscape Genres

Abstract
While contemporary paintings come in every conceivable form, pre-modern paintings were understood in terms of only five categories or ‘genres’, with some genres being more important than others. These genres, in descending order of importance, were: history painting (which were large multifigure compositions addressing significant topics), portrait, genre, landscape and still life. This book examines two of those genres: the landscape and the portrait. Paintings in general are supremely organised things, the function of this organisation being to create a memorable visual impact. For landscapes, this impact is achieved largely through accentuating the illusion of depth that they convey. For portraits, the face and the figure are of prime importance. This chapter introduces the histories of these genres and examines them for their functional differences.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 2. The Colour Attributes of Paintings

Abstract
In order to understand a phenomenon, one must be able to navigate it: to name its parts and to know its up from its down. Colour is a great challenge in this respect, being dimensionally very complex. This chapter examines the ways in which colour is understood in the visual art domain. Of particular focus is contrast and the many forms that it takes. Firstly, we examine RYB, HSL and other colour spaces and describe the role that they played in our work. We also detail the work of Johannes Itten (1888-1967) whose writings on colour contrast informed a lot of our research. A painter’s colour-thinking is high-level, addressing the structure-based contrast properties of a painting. This structure takes many forms: per region, per object, as a whole across the entire painting, between regions and objects, etc. These we describe and exemplify. We also address the role that they played in our research. The so-called colour harmony describes as high-level principles the difference between ‘good’ and ‘bad’ colour contrasts. We detail historical and contemporary ideas on the subject, much of which has its roots in the work of early twentieth-century mystics. Using this work as a starting point, and the work of the Impressionist painters as reference, we offer our own simple rules of hue harmony.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 3. Computational Models of Colour Contrast

Abstract
In the previous chapter, colour contrast was examined as phenomena within the art domain. In this chapter, we review computational models that might be employed to define these phenomena. In the engineering domain, there is not a standard measurement model of lightness, saturation or hue contrast. All existing models would probably be better regarded as application tools rather than as descriptions of basic visual function. Colour contrast is broadly understood as being one of two things: a relationship between two things (i.e. simple contrast) or the variance of a property within a single thing (i.e. complex contrast).
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 4. The Geometric Attributes of Paintings

Abstract
Within a painting, two forms of geometry can be identified: 2D and 3D. 2D geometry is defined by such things as the corner, the centre, the edge and the middle. 3D geometry is defined as simplified planes, such as foreground, middle ground and background and is particularly important in enhancing the depth of a landscape painting. These geometries function as structural scaffolding around which the painter builds their contrasts. The composition of a painting is covered by its 2D geometry. We examine the rule of thirds which, through an examination of its history, is shown to be more complex and interesting than its current form. We also look at the placement of the region of interest and of the horizon and find them to be governed by simple principles. A photographer’s vignette is simple: a darkening of the edges and corners, and perhaps also a lightening of the centre. In contrast, a painter’s vignette is complex and involves interplay between the 2D and 3D geometries of the painting.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Transfer of Aesthetic Values

Frontmatter

Chapter 5. Global Colour Style Transfer

Abstract
In this chapter, we examine the global chromatic and achromatic aspects of a painting. Their organisation is particular to each artist, with work by that artist showing consistency in its contrast organisation. This organisation forms a significant part of their ‘style’. Contrast can be broken down into its chromatic aspects (hue and saturation) and its achromatic aspect (lightness). We propose a method by which this style may be transferred from a painting to a photograph. The principle behind our method is to transfer the inherent structures of the contrast properties. This differentiates our method from a simple colour transfer, using which the hues of an image may be shifted, and in doing so damages the semantic properties of the photograph.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 6. Atmospheric Perspective Effect Transfer for Landscape Photographs

Abstract
The atmospheric perspective effect is a physical phenomenon relating to the effect that atmosphere has on distant objects, causing them to be lighter and less distinct. The exaggeration of this effect by artists in 2D images increases the illusion of depth, thereby making the image more appealing. This chapter addresses the enhancement of the atmospheric perspective effect in landscape photographs, by the manipulation of depth-aware lightness and saturation contrast values. The form of this manipulation follows the organisation of such contrast in landscape paintings. The rational behind this manipulation is based on a statistical study which has shown clearly that the saturation contrast and lightness contrast between and within the depth planes in paintings are more purposefully organised than those in photographs. This contrast organisation in paintings respects the existing contrast relationships within a natural scene governed by the atmospheric perspective effect, yet also exaggerates upon them. In our approach, the depth-aware lightness and saturation contrast revealed in landscape paintings guides the mapping of contrasts in photographs. This contrast mapping is formulated as an optimisation problem that simultaneously considers the desired inter-contrast, intra-contrast, and some gradient constraints. Experimental results demonstrate that by using this proposed method, both the visual appeal and the illusion of depth in the photographs are effectively improved.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 7. Regional Contrast Manipulation for Portrait Photograph Enhancement

Abstract
This chapter proposes a method to manipulate the regional contrast in snapshot style portrait photographs by using pre-modern portrait paintings as aesthetic examples: to improve the visual appeal and focus of attention of the photographs. The example portrait painting is selected based on a comparison of the existing contrast properties of the painting and those of the photograph. The contrast organisation in the selected example painting is transferred to the photograph by mapping the inter- and intra-regional contrast values of the regions, such as the face and skin areas of the foreground figure, the non-face/skin part of the foreground and the background region. A novel piecewise nonlinear transformation curve is used to achieve this contrast mapping. Finally, the transition boundary between regions is smoothed to achieve the final results. Experimental results demonstrate that, by using this proposed method, the visual appeal of portrait photographs is effectively improved and the face and the figure become more salient.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 8. Composition Improvement for Portrait Photographs

Abstract
Composition has a great impact upon the visual quality of a photograph. This chapter studies the composition in portrait paintings and proposes an algorithm to improve the composition of portrait photographs based on an example portrait painting. From a study of portrait painting, it can be shown that the placement of the face and the figure in portrait paintings is pose-related. Based on this observation, our algorithm improves the composition of a portrait photograph by referencing the placement of the face and the figure from an example portrait painting. The example portrait painting is selected based on the similarity of its figure pose to that of the input photograph. This similarity measure is modelled as a graph matching problem. Finally, space cropping is performed using an optimisation function to assign a similar location for each body part of the figure in the photograph with that in the example portrait painting. The experimental results demonstrate the effectiveness of the proposed method. A user study shows that the proposed pose-based composition improvement is preferred more than the rule-based methods.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 9. Vignetting Effect Transfer

Abstract
This chapter discusses how the vignetting effect of paintings may be transferred to photographs, with attention to centre-corner contrast. First, the lightness distribution of both is analysed. The results show that the painter’s vignette is more complex than that achieved using common digital post-processing methods. Specifically, it is shown to involve both the 2D geometry and 3D geometry of the scene. An algorithm is then developed to extract the lightness weighting from an example painting and transfer it to a photograph. Experiments show that the proposed algorithm can successfully perform this function. The resulting vignetting effect is more naturally presented with regard to aesthetic composition as compared with vignetting achieved with popular software tools and camera models.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 10. Defining Hue Contrast

Abstract
Quantifying the style of visual art has long been a challenging yet largely overlooked problem. Of key importance in the style of a painting is the manner in which the artist has employed hue. We propose a means to quantify global hue contrast as two values: hue variety and hue antagonism. These were derived from Johannes Itten’s work on colour contrast. Using our approach, the hue contrast of a single image can be visually expressed as a single point in a plot. For this reason, the approach is particularly suitable for the comparative analysis of groups of artworks, such as those by two or more artists or an artist at different times in their career. We describe two case studies of such an analysis, and the results agree with observations. We also include a user study that supports the validity of our proposed approach.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan

Chapter 11. Interactive Local Hue Contrast Manipulation

Abstract
The lightness and saturation of an image may be subject to adjustment for the purpose of aesthetic improvement. Normally, this is in the form of a contrast adjustment. Such an adjustment would work upon the maximum, minimum and mean values of the lightness and/or saturation. The third value in the colour triumvirate is hue, but existing image improvement approaches rarely manipulate this value for the reason of its importance to the semantic reading of an image. Looking to painters for inspiration, we propose a method by which a region of contiguous hue in an image may be subject to one of two contrast adjustments: hue spread and hue compression. These are broadly analogous to adjustments of the relative form of Itten’s contrast of temperature. We develop a tool, which employs superpixels, using which a user may segment regions of similar hue, at varying scales. This allows the user to quickly select semantically related regions. These local regions also provide the basic region of operation for three proposed hue operations: (1) hue spread, (2) hue compression and (3) hue shift. We show that when combined with superpixel segmentation, these operations are capable of increasing, decreasing and changing regions of local hue contrast in a manner that is aesthetically agreeable. We demonstrate our framework on a variety of input images and discuss its evaluation from the feedback of several expert users.
Xiaoyan Zhang, Martin Constable, Kap Luk Chan, Jinze Yu, Wang Junyan
Weitere Informationen