Illumination Color and Intrinsic Surface Properties : Physics-based Color Analyses from a Single Image(<Special Issue>Excellent Theses for a Doctorate and a Graduation)

スポンサーリンク

概要

• 論文の詳細を見る

• In the real world, the color appearances of objects are generally not consistent. It depends principally on two factors: illumination spectral power distribution (illumination color) and intrinsic surface properties. Consequently, to obtain objects' consistent color descriptors, we have to deal with those two factors. The former is commonly referred to as color constancy: a capability to estimate and discount the illumination color, while the latter is identical to the problem of recovering body color from highlights. This recovery is crucial because highlights emitted from opaque inhomogeneous objects can cause the surface colors to be inconsistent with regard to the change of viewing and illuminant directions. We base our color constancy methods on analyzing highlights or specularities emitted from opaque inhomogeneous objects. We have successfully derived a linear correlation between image chromaticity and illumination chromaticity. This linear correlation is clearly described in inverse-intensity chromaticity space, a novel two-dimensional space we introduce. Through this space, we become able to effectively estimate illumination chromaticity (illumination color) from both uniformly colored surfaces and highly textured surfaces in a single integrated framework, thereby making our method significantly advanced over the existing methods. Meanwhile, for separating reflection components, we propose an approach that is based on an iterative framework and a specular-free image. The specular-free image is an image that is free from specularities yet has different body color from the input image. In general, the approach relies principally on image intensity and color. All methods of color constancy and reflection-components separation proposed in this paper are analyzed based on physical phenomena of the real world, making the estimation more accurate, and have strong basics of analysis. In addition, all methods require only a single input image. This is not only practical, but also challenging in term of complexity.

• 一般社団法人情報処理学会の論文
• 2005-06-15

著者

• IKEUCHI Katsushi

  The University of Tokyo

• Tan Robby

  Australian National University

• Ikeuchi Katsushi

  Univ. Tokyo

関連論文

• Task Recognition and Person Identification in Cyclic Dance Sequences with Multi Factor Tensor Analysis
• Illumination Color and Intrinsic Surface Properties : Physics-based Color Analyses from a Single Image(Excellent Theses for a Doctorate and a Graduation)
• Fast Shading and Shadowing and Handling Occlusions for Asuka-Kyo MR Contents
• Registration and Deformation of 3D Shape Data through Parameterized Formulation(Special Section Theses for a Doctorate and a Graduation)
• Keypose and Style Analysis Based on Low-dimensional Representation
• Intraclass Identifiable Region Detection
• Improvements of IP Representation, Fitting and Registration
• Registration and Deformation of 3D Shape Data through Parameterized Formulation
• Registration and Deformation of 3D Shape Data through Parameterized Formulation

スポンサーリンク