Reconstructing shredded documents through feature matching

Reconstructing shredded documentsthrough feature matching

Authors: Edson Justino, Luiz S. Oliveira, Cinthia FreitasSource: Forensic Science International 160 (2006), pp. 140–147

Date: 2012.12.19Speaker: Meng-Jing Tsai

2

Different Kinds of Shredding

3

Outline

҉� Introductions҉� Proposed Method҉� Experimental Result҉� Conclusions

4

Introductions

• The amount of time necessary to reconstruct a document depends on the size and the number of fragments, and it can be measured in days or even weeks.

• Traditional puzzle solving algorithms usually take into account smooth edges and well defined corners.

• The act of shredding a piece of paper by hand often produces some irregularities in the boundaries.

5

Proposed Method

• The block diagram of the proposed methodology

1.

2.

3.

6

Proposed Method

• Pre-processing– In order to overcome this kind of problem, we

have tested different algorithms, and the one that brought the best results was the well-known Douglas–Peucker (DP) algorithm.

7

Proposed Method• Douglas-Peucker Algorithm

8

Proposed Method

• Pre-processing

9

Proposed Method

• Feature extraction

Fig. 1 Angle features extracted from the polygon

(180,110)

(180,0)

(10,110)

(10,70) (55,67)

(67,25)

45

43.6120°

vuuv

cos

10

Proposed Method

• Matching

– Computing the similarity between polygons

– Global search

11

Proposed Method

• Computing the similarity between polygons– If the complementarity is verified like in Fig. 2,

then Wangles=1.

Fig. 2 Similarity between angles

12

Proposed Method

• Computing the similarity between polygons

Fig. 3 Distance features extracted from the polygon

13

Proposed Method

• We consider the relevance of the matching regarding the perimeter of the fragment using the following rules:– If the contour matched represents more than 1/5 of the

perimeter of the fragment, then Wmatching = Wmatching+2.– If the contour matched represents more than 1/10 of

the perimeter of the fragment, then Wmatching = Wmatching+1.

– Otherwise, Wmatching is not increased.

14

Proposed Method

• Global search– Let us consider a shredded document D ={F1, F2,..., Fn} composed of n fragments.

– The algorithm compares the fragment F1 with all the other fragments searching for the best matching.

Fig. 4 Best matching (a) fragments i and j and (b) new fragment Fij where three vertices were removed

15

Proposed Method

• Steps of the document reconstruction

16

Experimental Result

• Examples of a document totally reconstructed: (a) fragments and (b) document reconstructed.

17

Experimental Result

• Performance of the proposed methodology in reconstructing documents shredded by hand.

The fragments size range from 1cm × 1cm to 5cm × 5cm.

18

Conclusions

• This paper proposed a method for document reconstruction based on feature matching.

• It can be addressed by choosing the most important aspects for the application.

19

Thank youfor your listening.