The aim of this work was to investigate the Min-Cut algorithm for table identification in spreadsheets. The cells in spreadsheets are classified following the approach proposed by Koci on a KDIR’16 paper. Cells of the same class are grouped together to form coherent regions. These regions correspond to the nodes in the graph. The edges capture the spatial arrangement of the regions in relation to each other. Moreover, edges are weighted using metrics involving the distance and the alignment between layout regions. Once the graph representation is built, we make use of the minimum cut algorithm from Stoer-Wagner, to iteratively cut weak edges. A stopping criterion eventually terminates this process. The resulting sub-graphs are treated as candidate tables.