earticle

영어

In this paper, we conduct a novel research on assembling paper fragments with kernel sparse representation and regular edge geometry analysis using the traditional example of rectangular pieces. At the initial stage, we adopt the methodology of image sparse presentation technique to overcome the influence of noise. During the process of assembling, we make good use of MATLAB and C++ to extract the core visual information from the fragments’ digitally to capture the matrix in the grey value scale. Edge characteristics are derived and regarded as the basic unit to find out fragments which belong in the first column. According to the similarity characteristic, adjacent rows are found and matched accordingly, annealing algorithm is used to gather the fragments. From the perspective of practical use, we find out the robustness and effectiveness of our proposed approach. Compare with some state-of-the-art algorithms, our methodology shows the better accuracy, it’s of great importance to the community of fragment assembly.