Solving archaeological puzzles

Derech, Niv; Tal, Ayellet; Shimshoni, Ilan

doi:10.1016/j.patcog.2021.108065

Cited by 24 publications

(9 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, some techniques exploit both the fragments shapes and content [25,1]. Zhang and Li [25] introduce a method based on both fragment shapes and patterns.…”

Section: Archaeological Puzzlesmentioning

confidence: 99%

See 1 more Smart Citation

Deepzzle: Solving Visual Jigsaw Puzzles With Deep Learning and Shortest Path Optimization

Paumard

Picard²,

Tabia

2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

We tackle the image reassembly problem with wide space between the fragments, in such a way that the patterns and colors continuity is mostly unusable. The spacing emulates the erosion of which the archaeological fragments suffer. We crop-square the fragments borders to compel our algorithm to learn from the content of the fragments. We also complicate the image reassembly by removing fragments and adding pieces from other sources. We use a two-step method to obtain the reassemblies: 1) a neural network predicts the positions of the fragments despite the gaps between them; 2) a graph that leads to the best reassemblies is made from these predictions. In this paper, we notably investigate the effect of branch-cut in the graph of reassemblies. We also provide a comparison with the literature, solve complex images reassemblies, explore at length the dataset, and propose a new metric that suits its specificities.

show abstract

“…Finally, some techniques exploit both the fragments shapes and content [25,1]. Zhang and Li [25] introduce a method based on both fragment shapes and patterns.…”

Section: Archaeological Puzzlesmentioning

confidence: 99%

“…In [1], the authors propose to examine the overlapping of extrapolated fragments rather than searching for valid continuations. They solve the puzzle one piece after another: they use the current reassembly to place the next fragment.…”

Section: Archaeological Puzzlesmentioning

confidence: 99%

Deepzzle: Solving Visual Jigsaw Puzzles With Deep Learning and Shortest Path Optimization

Paumard

Picard²,

Tabia

2020

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…The jigsaw puzzle is a well-known game where small (and often irregular) pieces must be fitted together to reconstruct the complete image or shape. Despite its entertaining and educational origins, solving a puzzle has numerous applications in different fields, such as image editing, reconstruction of broken artifacts [9], shredded documents [7], genome biology [27]. In its simplest version, which is known as the square jigsaw puzzle, the square pieces should be reordered on a 2D grid to form a coherent image.…”

Section: Introductionmentioning

confidence: 99%

“…A more complex task concerns finding a solution when pieces are missing or eroded. Many real-world problems, such as recovering of ancient documents and broken artifacts [9], can be seen as jigsaw puzzles with missing information (boundaries or entire pieces). This task has been only partially explored in the last year due to its complexity [4,18].…”

Section: Introductionmentioning

confidence: 99%

Relaxation Labeling Meets GANs: Solving Jigsaw Puzzles with Missing Borders

Khoroshiltseva¹,

Traviglia²,

Pelillo³

et al. 2022

Preprint

View full text Add to dashboard Cite

This paper proposes JiGAN, a GAN-based method for solving Jigsaw puzzles with eroded or missing borders. Missing borders is a common real-world situation, for example, when dealing with the reconstruction of broken artifacts or ruined frescoes. In this particular condition, the puzzle's pieces do not align perfectly due to the borders' gaps; in this situation, the patches' direct match is unfeasible due to the lack of color and line continuations. JiGAN, is a two-steps procedure that tackles this issue: first, we repair the eroded borders with a GAN-based image extension model and measure the alignment affinity between pieces; then, we solve the puzzle with the relaxation labeling algorithm to enforce consistency in pieces positioning, hence, reconstructing the puzzle. We test the method on a large dataset of small puzzles and on three commonly used benchmark datasets to demonstrate the feasibility of the proposed approach.

show abstract

“…It has been nevertheless already acknowledged that archaeology exposes the limits of current computer vision techniques. Since artefacts are highly degraded and with large missing visual content, archaeology is a very challenging application area for artificial vision [4]. The current paper appoints deep learning (DL) to specifically visually reconstruct the content of textile artefacts with traditional Romanian motifs.…”

Section: Introductionmentioning

confidence: 99%

On Using Perceptual Loss within the U-Net Architecture for the Semantic Inpainting of Textile Artefacts with Traditional Motifs

Stoean

Bačanin

Stoean

et al. 2022

2022 24th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)

View full text Add to dashboard Cite

It is impressive when one gets to see a hundreds or thousands years old artefact exhibited in the museum, whose appearance seems to have been untouched by centuries. Its restoration had been in the hands of a multidisciplinary team of experts and it had undergone a series of complex procedures. To this end, computational approaches that can support in deciding the most visually appropriate inpainting for very degraded historical items would be helpful as a second objective opinion for the restorers. The present paper thus attempts to put forward a U-Net approach with a perceptual loss for the semantic inpainting of traditional Romanian vests. Images taken of pieces from the collection of the Oltenia Museum in Craiova, along with such images with garments from the Internet, have been given to the deep learning model. The resulting numerical error for inpainting the corrupted parts is adequately low, however the visual similarity still has to be improved by considering further possibilities for finer tuning.

show abstract

Solving archaeological puzzles

Cited by 24 publications

References 27 publications

Deepzzle: Solving Visual Jigsaw Puzzles With Deep Learning and Shortest Path Optimization

Deepzzle: Solving Visual Jigsaw Puzzles With Deep Learning and Shortest Path Optimization

Relaxation Labeling Meets GANs: Solving Jigsaw Puzzles with Missing Borders

On Using Perceptual Loss within the U-Net Architecture for the Semantic Inpainting of Textile Artefacts with Traditional Motifs

Contact Info

Product

Resources

About