What’s the current procedure for finding a particular type of image on the Web? At present, the only way to search for images is based on text captions that people have entered by hand for each picture, and unfortunately many images lack such information.
Researchers have been desperately trying to discover an efficient way for such a search wherein a caption, or any information based on manually entered text is not required. The credit after all goes to MIT researcher ñ they have successfully done it. It takes surprisingly few pixels of informationto be able to identify the subject of an image. The discovery could lead to great advances in the automated identification of online images and, ultimately, provide a basis for computers to see like humans do. Read the rest of this entry »


Wall RSS Feed