210 likes | 375 Views
Date: 2012.12.19 Speaker : Meng -Jing Tsai. Reconstructing shredded documents through feature matching. Authors: Edson Justino, Luiz S. Oliveira, Cinthia Freitas Source: Forensic Science International 160 (2006), pp. 140–147. Different Kinds of Shredding. Outline. Introductions
E N D
Date: 2012.12.19 Speaker: Meng-Jing Tsai Reconstructing shredded documentsthrough feature matching Authors: Edson Justino, Luiz S. Oliveira, Cinthia Freitas Source: Forensic Science International 160 (2006), pp. 140–147
Outline • Introductions • Proposed Method • Experimental Result • Conclusions
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.
Proposed Method • The block diagram of the proposed methodology 1. 2. 3.
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.
Proposed Method • Douglas-Peucker Algorithm
Proposed Method • Pre-processing
Proposed Method • Feature extraction (10,110) (180,110) 45 (55,67) (10,70) 120° 43.6 (67,25) (180,0) Fig. 1 Angle features extracted from the polygon
Proposed Method • Matching • Computing the similarity between polygons • Global search
Proposed Method • Computing the similarity between polygons • If the complementarity is verified like in Fig. 2, then Wangles=1. Fig. 2 Similarity between angles
Proposed Method • Computing the similarity between polygons Fig. 3 Distance features extracted from the polygon
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.
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 iand j and (b) new • fragment Fijwhere three vertices were removed
Proposed Method • Steps of the document reconstruction
ExperimentalResult • Examples of a document totally reconstructed: (a) fragments and (b) document reconstructed.
Experimental Result • Performance of the proposed methodology in reconstructing documents shredded by hand. The fragments size range from 1cm × 1cm to 5cm × 5cm.
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.