Nonuniform fragmented piece reconstruction method using a texture-based patch-matching algorithm

We present a fragmented piece reconstruction method that enables all non-overlapping and randomly placed fragmented pieces to be identified and gathered piece-by-piece to be placed in the corresponding position. The proposed method can be applied in many other fields such as industrial automation, robot vision, archeology, and art restoration.

[1]  Gabriel Taubin,et al.  PSQP: Puzzle Solving by Quadratic Programming. , 2017, IEEE transactions on pattern analysis and machine intelligence.

[2]  Jorge Stolfi,et al.  A Multiscale Method for the Reassembly of Two-Dimensional Fragmented Objects , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Luc Van Gool,et al.  SURF: Speeded Up Robust Features , 2006, ECCV.

[4]  Luc Van Gool,et al.  Speeded-Up Robust Features (SURF) , 2008, Comput. Vis. Image Underst..

[5]  D.B. Cooper,et al.  Computational reconstruction of ancient artifacts , 2008, IEEE Signal Processing Magazine.

[6]  Huang-Chia Shih,et al.  SPiraL Aggregation Map (SPLAM): A new descriptor for robust template matching with fast algorithm , 2015, Pattern Recognit..