MIT scientists have learned to more accurately recognize images
A team of scientists from the Massachusetts Institute of Technology (MIT) Laboratory for Computing and Artificial Intelligence published an article with interim results from their work in the TechTalk institute. Experts led by Antonio Torralba have developed a new image indexing technology that will help you quickly and more accurately recognize objects in digital photographs and search for similar ones, for example, on the Internet.
The essence of the new method is in a more advanced, in comparison with modern algorithms, technique for compiling an image hash, due to which its size does not exceed 1 Kb. For clarity, in their experiments, scientists worked with a database describing almost 13 million photographs, the size of which was only 600 MB.
Despite the fact that the work is still far from being published, Torralba mentioned that a large role in pattern recognition is given to determining the shape of an object and its comparison with the base of samples. In any case, it seems that the fast compilation of such a miniature hash requires much more computing power than modern desktop PCs can provide.
The essence of the new method is in a more advanced, in comparison with modern algorithms, technique for compiling an image hash, due to which its size does not exceed 1 Kb. For clarity, in their experiments, scientists worked with a database describing almost 13 million photographs, the size of which was only 600 MB.
Despite the fact that the work is still far from being published, Torralba mentioned that a large role in pattern recognition is given to determining the shape of an object and its comparison with the base of samples. In any case, it seems that the fast compilation of such a miniature hash requires much more computing power than modern desktop PCs can provide.