Methods, systems, and apparatus are provided for detecting and extracting data from a nested table. A contour image of a first table disposed within a cell of a second table from an input image is identified. The first table on the input image is masked to generate a masked image of the second table that omits the first table. Cells of the first table and the second table are detected by identifying a plurality of regions of interest (ROIs), determining a row of a plurality of cells based on a common y-coordinate among of the plurality of ROIs, and generating cell parameter information for each of the plurality of cells that identifies the y-coordinate, a size, and a relative position of each determined cell. An output file is generated based on the cell parameter information of the plurality of cells.