Computerized treatment of manuscripts

Researchers at the UAB Computer Vision Centre working on the automatic recognition of manuscript documents have designed a new system that is more efficient and reliable than currently existing ones.

The BSM (acronym for "Blurred Shape Model") has been designed to work with ancient, damaged or difficult to read manuscripts, handwritten scores and architectural drawings. It represents at the same time an effective human machine interface in automatically reproducing documents while they are being written or drawn.

Researchers based their work on the biological process of the human mind and its ability to see and interpret all types of images (recognition of shapes, structures, dimensions, etc.) to create description and classification models of handwritten symbols. However, this computerised system differs from others since it can detect variations, elastic deformations and uneven distortions that can appear when manually reproducing any type of symbol (letters, signs, drawings, etc.). Another advantage is the possibility to work in real time, only a few seconds after the document has been introduced into the computer.

The BSM differs from other existing systems which follow the same process when deciphering different types of symbols, since a standard process makes it more difficult to recognise the symbols after they have been introduced. In contrast, the methodology developed by the Computer Vision Centre can be adapted to each of the areas it is applied to. To be able to analyse and recognise symbols, the system divides image regions into sub regions - with the help of a grid - and saves the information from each grid square, while registering even the smallest of differences (e.g. between p and b). Depending on the shape introduced, the system undergoes a process to distinguish the shape and also any possible deformations (the letter P for example would be registered as being rounder or having a shorter or longer stem, etc.). It then stores this information and classifies it automatically.

Researchers decided to test the efficiency of the system by experimenting with two application areas. They created a database of musical notes and a database of architectural symbols. The first was created from a collection of modern and ancient musical scores (from the 18th and 19th centuries) from the archives of the Barcelona Seminary, which included a total of 2,128 examples of three types of musical notes drawn by 24 different people. The second database included 2,762 examples of handwritten architectural symbols belonging to 14 different groups. Each group contained approximately 200 types of symbols drawn by 13 different people.

In order to compare the performance and reliability of the BSM, the same data was introduced into other similar systems. The BSM was capable of recognising musical notes with an exactness of over 98% and architectural symbols with an exactness of 90%.

Researchers at the Computer Vision Centre who developed the BSM were awarded the first prize in the third edition of the Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA) which took place last June.

Source: Universitat Autonoma de Barcelona

Related stories:

Musicians use both sides of their brains more frequently than average people
Supporting what many of us who are not musically talented have often felt, new research reveals that trained musicians really do think differently than the rest of us. Vanderbilt University psychologists have found that professionally trained musicians more effectively use a creative technique called divergent thinking, and also use both the left and the right sides of their frontal cortex more heavily than the average person.
Displays that give a clear view
Displays made of organic LEDs are brightly lit but tend to be mostly opaque. Making them transparent opens up a whole new world of applications: OLEDs can be wedded with conventional LCDs and transform laminated glass into a display panel.
Gluttons, drunks and fools
(PhysOrg.com) -- An academic from the University of St Andrews has delved into the Bible to provide food for thought on the subject of eating and drinking.
Bison roam prairie at renowned physics laboratory
The herd appeared docile, grazing quietly on the lush prairie and flicking away flies with their tails. But John Plese knew better. He dared not get out of his truck, parked just feet from a 1,500-pound bull. If there's one thing he's learned as Fermilab's chief herdsman, it's this: Never let your guard down around a bison.
Unraveling 'math dyslexia'
Although school has been back for less than a month, it is likely that many children are already experiencing frustration and confusion in math class. Research at The University of Western Ontario in London, Canada could change the way we view math difficulties and how we assist children who face those problems.
Not buying it: Marketing messages may not work in uncommon situations
Marketers like to talk about "priming" goals -- or sending subtle messages to encourage consumption. For example, thirsty people who encounter ads related to thirst tend to buy more beverages.
Infovell's 'research engine' finds deep Web pages that Google, Yahoo miss
According to a study by the University of California at Berkeley, traditional search engines such as Google and Yahoo index only about 0.2% of the Internet. The remaining 99.8%, known as the "deep Web," is a vast body of public and subscription-based information that traditional search engines can't access.
Prehistoric funerary precinct excavated in northern Israel
Hebrew University excavations in the north of Israel have revealed a prehistoric funerary precinct dating back to 6,750-8,500 BCE.

News discussion:

Technology news