Licensing opportunity
Researchers at the Computer Vision Centre at Universitat Autònoma de Barcelona have developed a new method for reading ancient, damaged, or difficult to read manuscripts, handwritten scores and architectural drawings.
The Blurred Shape Model (BSM) could be applied to automatically reproduce documents while they are being written or drawn also.
The researchers created description and classification models of handwritten symbols that can detect variations, elastic deformations and uneven distortions that can appear when manually reproducing any type of symbol. BSM divides image regions into sub regions and saves the information from each grid square, while registering even the smallest of differences.
The researchers tested the system by creating one database of musical notes and another of architectural symbols. The first held a collection of modern and ancient musical scores from the 18th and 19th centuries, with a total of 2,128 examples of three types of musical notes drawn by 24 different people. The second included 2,762 examples of handwritten architectural symbols belonging to 14 different groups. Each group contained about 200 types of symbols drawn by 13 different people.
The BSM correctly recognised over 98 per cent of musical notes and 90 percent of architectural symbols.
Receive the Funding Newswire each Tuesday, our Policy Bulletin each Thursday, and news about bridging Europe’s east-west innovation gap twice a month in The Widening. 
A unique international forum for public research organisations and companies to connect their external engagement with strategic interests around their R&D system.
