Image Morphing by Spatial Thin-Plate Spline Transformation

スポンサーリンク

概要

• 論文の詳細を見る

• This paper presents a new morphing technique using a computationally efficient, globally valid spatial transformation method. The transformation employed is developed on a most general paradigm of a minimum norm of higher order derivatives of displacement squared, of which the thin-plate spline transformation of a minimum bending energy is the best known and is extensively used in deformation of 2D curves and 3D parametric curved surfaces. Compared with the other morphing techniques, the present algorithm is efficient not only in time complexity but also in reproducing descriptive, and yet smoothly interpolated morphed images with only a remarkably small number of feature points specified. The improved efficiency comes in part from the small number of feature points needed in the transformation thus requiring only a nominal time in matrix inversion and also from the block region based image reconstruction scheme used rather than a pixel by pixel based scheme where the image is reconstructed by linear interpolation within the block rather than going through summations over all feature points. We demonstrate that a considerable saving can be achieved in time complexity without sacrificing the quality of the image reconstructed. The method also has a capability of localizing distortions due to morphing, an important feature in animation applications by simply adding constraining feature points along a region of localization. We have applied the 2D Version of the present transformation to a 2. 5-D application of a relief surface deformation. Taking an advantage of a generalized norm approach in the formulation, we have applied the present method to three-dimensional volume morphing. A preliminary result suggests that the method applies as long as the shape involved is sufficiently smooth. A possibility is sought for extension to general shapes.

• 一般社団法人情報処理学会の論文
• 1996-01-15

著者

• TOKUDA Naoyuki

  SunFlare Research and Development Center

• Tokuda N

  Sunflare Research And Development Center

• Tokuda Naoyuki

  Computer Science Department Utsunomiya University Utsunomiya Japan

• Tokuda Naoyuki

  Faculty Of General Education Utsunomiya University

• MIYAMICHI Juichi

  Computer Science Department, Faculty of Engineering, Utsunomiya University

• YAN Ronghua

  Computer Science Department, Faculty of Engineering, Utsunomiya University

• Ni Yongmao

  Faculty of International Studies, Utsunomiya University

• Miyamichi J

  Faculty Of Engineering Utsunomiya University

• Ni Yongmao

  Faculty Of International Studies Utsunomiya University

• Yan Ronghua

  Computer Science Department Faculty Of Engineering Utsunomiya Univesity

関連論文

• Instantaneously Reversible Golomb-Rice Codes for Robust Image Coding
• Compound Image Compression Using Adaptive Wavelet Transform
• A Shrinking Method for Dithered Images
• Capacity analysis for a two-level decoupled Hamming network for associative memory under a noisy environment
• Probabilistic Information Retrieval Method Based on Differential Latent Semantic Index Space
• A Constructive Compound Neural Networks. II Application to Artificial Life in a Competitive Environment
• A New Constructive Compound Neural Networks Using Fuzzy Logic and Genetic Algorithm 1 Application to Artificial Life
• A Model-Based Active Landmarks Tracking Method
• Image Morphing by Spatial Thin-Plate Spline Transformation
• A Finite-Difference Solution of a Crystal Growth Stefan Problem
• Stokes Solutions for Flow Near Corners in Three-Dimensions
• A Syntactical Approach to Diagnosing Multiple Bugs in an Intelligent Tutoring System
• A Convection Stefan Problem by Lagrange-Burmann Expansions.I.Small Time Solution

もっと見る 閉じる

スポンサーリンク