Create artificial images for lack of data

The latest developments in technology Artificial intelligence They do it every time More related to the world of medicine and health. Although it has come true Automate difficult tasksRequire current technologies big Databases to learn from.

In many cases, it is difficult to collect databases using thousands of Pictures Of everything the method to be developed needs to know, either because of the difficulty of obtaining images or because of the need for an expert Spend a lot of time categorizing them.[banner-DFP_1]

In this regard, a study was conducted by researchers from a group Visilab . searchof the Higher Technical School of Industrial Engineering of the University of Castilla-La Mancha (UCLM) and published in the journal Computer methods and programs in biomedicine.Through applications based on Computer vision and image processing For diagnosis, he proposed a method that would improve biomedicine.

They created a new system for creating new images by mixing two of those already available in a small database

to solve a problem There are no data in medicine or biology By creating artificial images, they have created a new system for Create new images by mixing two of those already available in a small database.

Work written by responsible researchers Noelia Valles, Gloria Bueno and Oscar Denizmembers of the Visilab group and professors from the Higher Technical School of Industrial Engineering; s Saul Blanco Lanzafrom the Institute of Environment, Natural Resources and Biodiversity at the University of Lyon, shows a developed method inspired by In the life cycle followed by diatomsMicroscopic algae found in rivers and seas.[banner-DFP_4]

The researchers provided an example to understand this new discovery: It is easy for a person to learn what a chair is by seeing two or three chairsbut for a the computer Learn the same thing, you need to see pictures of thousands of different chairs and someone “teach” you and let you know that these are chairs.

When using augmented databases in the suggested manner, based on turn and image recording, the results obtained with artificial intelligence techniques show a clear improvement in accuracy

“It would be like taking Two pictures we know contain chairs and we mix them For a chair of medium size and shape,” says researcher Vallis.

The work shows that When using augmented databases in the suggested mannerBased on turn and record photosThe results obtained by artificial intelligence techniques Show a clear improvement in accuracy.

In this way, the improvement in different databases related to medicine And biology to prove it Applicability in various fields and problems.

Because health we all need… ConSalud.es