PDF files recognition system for an architectural bureau
Overview
To accurately prepare a bill of quantities and provide a price estimation, information like building and flood plan type, scale ratio, etc. needs to be extracted. Moreover, the objects present in the blueprint have to be counted to approximate the cost of construction of the building.
Ready-made solutions for optical character recognition (OCR) could not handle the task with enough accuracy or could not handle it at all due to the special characters used in the floor plans.
The system we have developed analyses the blueprints and automatically detects the building type, floor plan type, blueprint scale, as well as detects special symbols specified by the user.
The system also transforms complex PDF spreadsheets (that cannot be processed with ready-made solutions due to their complex structure) into editable Excel spreadsheets.