Computer Aided Colorimetric Analysis of Fine Art Paintings
نویسندگان
چکیده
In order to analyse paintings, specialists use many different techniques exploring different parts of the electromagnetic spectrum: near infra-red, ultra-violet, X-rays, etc. But surprisingly, the visual domain has rarely been analysed, probably because colour perception is a very complex domain, being rather difficult to analyse adequately by means of automatic techniques. Our visual sensations are the results of three different processes: physical, neuro-physical and psychophysical. Colorimetry is based on the evidence of trichromacy and the definition of a reference observer. It allows the measure of colours as luminous stimuli. For fine arts, it provides a way to quantify the paintings and their reproduction. The colours of a fine art painting is indeed a very important property of the painting. Traditionally, the colours have mostly been evaluated qualitatively by observing the painting. Besides the obvious uncertainty steming from the qualitative analysis, another important drawback with such methods is that it requires the curator or art historian to be located physically close to the painting. To perform a quantitative analysis of the colours of a painting, colour measuring devices such as colorimeters and spectrophotometers can be used. But, such equipment have a very poor spatial resolution, making it difficult to analyse the painting as a whole. We propose thus to apply digital image processing techniques to analyse the painting [1, 2, 3, 4]. However, to analyse and evaluate the colours in a painting it is important to be able to quantify them properly, in particular to make sure that the analysis is independent of the image acquisition device. In the next section, we present briefly a methodology that enables us to capture high-quality colour-calibrated deviceindependent images. Then, in Section 3, we proceed to the colorimetric analysis of three paintings.
منابع مشابه
From Digital Imaging to Computer Image Analysis of Fine Art
An expanding range of techniques from computer vision, pattern recognition, image analysis, and computer graphics are being applied to problems in the history of art. The success of these efforts is enabled by the growing corpus of high-resolution multi-spectral digital images of art (primarily paintings and drawings), sophisticated computer vision methods, and most importantly the engagement o...
متن کاملComputer analysis of lighting style in fine art: Steps towards inter-artist studies
Stylometry in visual art—the mathematical description of artists’ styles—has been based on a number of properties of works, such as color, brush stroke shape, visual texture, and measures of contours’ curvatures. We introduce the concept of quantitative measures of lighting, such as statistical descriptions of spatial coherence, diffuseness, and so forth, as properties of artistic style. Some a...
متن کاملMathematical Analysis of Color Combination and Color Composition of Images
Pleasing color harmonies appeals to our sense of beauty. Our study is an attempt to explore such aesthetic aspect of color by scientific approach using mathematics and computer. Digital images of fine art, especially images of paintings, are significant resources for computational analysis of color aesthetics. We have developed a software system, specially designed for multilateral color analys...
متن کاملKnowledge Discovery of Artistic Influences
We approach the challenging problem of discovering influences between painters based on their fine-art paintings. In this work, we focus on comparing paintings of two painters in terms of visual similarity. This comparison is fully automatic and based on computer vision approaches and machine learning. We investigated different visual features and similarity measurements based on two different ...
متن کاملKnowledge Discovery of Artistic Influences: A Metric Learning Approach
We approach the challenging problem of discovering influences between painters based on their fine-art paintings. In this work, we focus on comparing paintings of two painters in terms of visual similarity. This comparison is fully automatic and based on computer vision approaches and machine learning. We investigated different visual features and similarity measurements based on two different ...
متن کامل