Method and system of determining shape of a table in a document

A system of determining shape of a table in a document, comprising:

• one or more processors;
• a memory communicatively coupled to the processors, wherein the memory stores a plurality of processor-executable instructions, which, upon execution, cause the processors to:
• determine a binarized image of the document;
• detect at least one region of interest (ROI) corresponding to the table based on detection of a plurality of lines,
• wherein the plurality of lines are detected based on a morphological operation;
• determine boundary lines of the at least one ROI from the plurality of lines based on neighbourhood connectivity of pixels of the boundary lines;
• extract at least one ROI based on a minimum height threshold and a minimum width threshold of the document image;
• determine a cluster of points corresponding to each corner of the at least one ROI based on a height of the ROI and contour detection;
• wherein the cluster of points corresponding to each corner is determined in case a successive Euclidean distance between each consecutive points of the cluster of points is less than 15% of the height of the ROI;
• determine a corner type of each of the corner to be one of a pointed corner or a curved corner based on determination of one or more parameters corresponding to an arc formed by the cluster of points of each of the corner;
• and
• determine the shape of the table to be a rounded corner structure in case the corner type of least two corners is determined as the curved corner.

A non-transitory computer-readable medium storing computer-executable instructions for determining shape of a table in a document, the stored computer-executable instructions, when executed by a processor, cause the processor to perform the steps of:

• determining binarized image of the document;
• detecting at least one region of interest (ROI) corresponding to the table based on detection of a plurality of lines,
• wherein the plurality of lines are detected based on a morphological operation;
• determining boundary lines of the at least one ROI from the plurality of lines based on neighbourhood connectivity of pixels of the boundary lines;
• extracting the at least one ROI based on a minimum height threshold and a minimum width threshold of the document;
• determining a cluster of points corresponding to each corner of the at least one ROI based on a height of the ROI and contour detection;
• wherein the cluster of points corresponding to each corner is determined in case a successive Euclidean distance between each consecutive points of the cluster of points is less than 15% of the height of the ROI;
• determining a corner type of each of the corner to be one of a pointed corner or a curved corner based on determination of one or more parameters corresponding to an arc formed by the cluster of points of each of the corner;
• and
• determining the shape of the table to be a rounded corner structure in case the corner type of least two of the corners is determined as the curved corner.