US 11,899,704 B2
Systems and methods for extracting, digitizing, and using engineering drawing data
Robin Tommy Kulangara Muriyil, Thiruvananthapuram (IN); Athira Krishnan Remadevi, Thiruvananthapuram (IN); Aswathy Sreelekha Krishna, Thiruvananthapuram (IN); Ajithkumar Manaparampil, Thiruvananthapuram (IN); and Anand Gopinath, Thiruvananthapuram (IN)
Assigned to Tata Consultancy Services Limited, Mumbai (IN)
Filed by Tata Consultancy Services Limited, Mumbai (IN)
Filed on Jul. 15, 2022, as Appl. No. 17/812,895.
Claims priority of application No. 202121040056 (IN), filed on Sep. 3, 2021.
Prior Publication US 2023/0109144 A1, Apr. 6, 2023
Int. Cl. G06F 16/35 (2019.01); G06V 30/422 (2022.01); G06V 30/412 (2022.01)
CPC G06F 16/35 (2019.01) [G06V 30/412 (2022.01); G06V 30/422 (2022.01)] 19 Claims
OG exemplary drawing
 
1. A processor implemented method, comprising:
receiving, by an engineering drawing data extraction and management system (DDEMS) via one or more hardware processors, an engineering drawing document and a template information associated with the engineering drawing document from a data creator device associated with a data creator, the engineering drawing document comprising one or more engineering drawing views associated with an engineering drawing image of an object and one or more tables;
identifying, by the DDEMS via the one or more hardware processors, table location of a table of the one or more tables in the engineering drawing document based on the template information, the table comprising one or more cells;
extracting, by the DDEMS via the one or more hardware processors, text data present in each cell of the one or more cells of the table in the table location as table data using a data extraction algorithm;
identifying, by the DDEMS via the one or more hardware processors, one or more isometric views from the one or more engineering drawing views present in the engineering drawing document as one or more primary views using a color masking and an image area property technique;
identifying, by the DDEMS via the one or more hardware processors, one or more secondary views from the one or more engineering drawing views using a pretrained machine learning based model;
extracting, by the DDEMS via the one or more hardware processors, view labels and view coordinate information from one or more primary views and one or more secondary views using a view label extraction technique; and
displaying, by the DDEMS via the one or more hardware processors, the table data, the one or more primary views, the one or more secondary views, the view labels and the view coordinate information as an engineering drawing data for the engineering drawing document on the data creator device.