Alignment of 3D woodblock geometrical models and 2D orthographic projection image

TL;DR

A unified image processing algorithm is proposed, enhancing the registration quality between 3D woodblock models and their 2D representations, offering an effective normalization scheme for digital heritage preservation.

Abstract

The accurate alignment of 3D woodblock geometrical models with 2D orthographic projection images presents a significant challenge in the digital preservation of Vietnamese cultural heritage. This paper proposes a unified image processing algorithm to address this issue, enhancing the registration quality between 3D woodblock models and their 2D representations. The method includes determining the plane of the 3D character model, establishing a transformation matrix to align this plane with the 2D printed image plane, and creating a parallel-projected depth map for precise alignment. This process minimizes disocclusions and ensures that character shapes and strokes are correctly positioned. Experimental results highlight the importance of structure-based comparisons to optimize alignment for large-scale Han-Nom character datasets. The proposed approach, combining density-based and structure-based methods, demonstrates improved registration performance, offering an effective normalization scheme for digital heritage preservation.

Figures (7)

• Figure 1: Overview of 2D-3D alignment pipeline
• Figure 2: Show the results of some steps of the algorithm. (a) Result step \ref{['step_1_1']} (b) step \ref{['step_1_2']} + step \ref{['step_1_3']}: Bluepoint corresponds to the upper set, red corresponds to the lower point. (c) Step \ref{['step_1_5']} of the algorithm, the blue dots are selected points on the surface. (d) Step \ref{['step_2']}.
• Figure 3: Parallel projection to generate depth-map image
• Figure 4: Example of the most appropriate threshold for depth image estimation.
• Figure 5: Example of final best threshold estimation.