by clicking on the page. A slider will appear, allowing you to adjust your zoom level. Return to the original size by clicking on the page again.
the page around when zoomed in by dragging it.
the zoom using the slider on the top right.
by clicking on the zoomed-in page.
by entering text in the search field and click on "In This Issue" or "All Issues" to search the current issue or the archive of back issues respectively.
by clicking on thumbnails to select pages, and then press the print button.
this publication and page.
displays a table of sections with thumbnails and descriptions.
displays thumbnails of every page in the issue. Click on a page to jump.
allows you to browse through every available issue.
FCW : July 15, 2013
July 15, 2013 FCW.COM 19 train such large networks but want to show that it can be done. They trained their neural network on a dataset of 10 million unlabeled YouTube video thumbnails. They then used the network to distinguish 13,152 faces from 48,000 distractor images. It succeeded 86.5 percent of the time. Again, that performance is not yet at a level that is of much practical use. But the remarkable thing is that Ng and his team achieved it on a dataset that wasn t labeled in any way. They devised a program that could, on its own, gure out what a face looks like. Current commercial facial recogni- tion systems include NEC s NeoFace, which won a competition run by the National Institute of Standards and Technology in 2010. NeoFace matches pictures of faces against large data- bases of images taken from close up and under controlled lighting condi- tions. NeoFace can work with images taken at very low resolution, with as few as 24 pixels between the subject s eyes, according to NEC. In the NIST evaluation, it identi ed 95 percent of the sample images given to it. In a May 2013 paper, Anil Jain and Joshua Klontz of Michigan State University used NeoFace to search through a database of 1.6 million law enforcement booking images, along with pictures of Dzhokhar and Tamerlan Tsarnaev, who are accused of setting off the bombs at the Bos- ton Marathon in April. Using the pub- licly released images of the Tsarnaev brothers, NeoFace was able to match Dzhokhar s high school graduation photo from the database of millions of images. It was less successful with Tamerlan because he was wearing sunglasses. Jain and Klontz make the point that, even today, facial recognition algorithms are good enough to be use- ful in a real-world context. The meth- ods for automatically detecting faces, though, are likely to get much better with machine learning. NeoFace and other commercial tools work in part by deconstructing faces into charac- teristic constituents, called eigenfaces, in a way roughly analogous to the grid coordinates of a point. A picture of a face can then be described as a dis- tinct combination of eigenfaces, just as any physical movement in the real world can be broken down into the components of up-down, left-right and forward-backward. But that approach is not very adapt- able to changes in lighting and pos- ture. The same face breaks down into very different eigenfaces if it is lit differently or photographed from another angle. However, it is easy for a person to recognize that, say, Angelina Jolie is the same person in pro le as she is when photographed from the front. Honglak Lee, an assistant profes- sor at the University of Michigan in Ann Arbor, wrote recently with col- leagues from the University of Mas- sachusetts that deep neural networks are now being applied to the prob- lem of facial recognition in a way that doesn t require any explicit informa- tion about lighting or pose. Lee and his colleagues were able to get 86 percent accuracy on a 5,749-image database called Labeled Faces in the Wild, which now contains more than 13,000 images. Their results compared favorably to the 87 percent that the best handcrafted systems achieved. But deep learning systems remain computationally demanding. Lee and his colleagues had to scale down their images to 150 by 150 pixels to make the problem computationally trac- table. As computing power grows, there is reason to believe that machine learning applied on a larger scale will become still more effective. Today's facial recognition tools were good enough to match one of the Tsarnaev brothers to his high-school yearbook photo, but they are often fooled by lighting and camera angle. The same machine learning that "teaches" cars to drive is freeing new systems from such dependencies. TOP PHOTO--- BOB LEONARD, AP IMAGES
June 30, 2013
July 30, 2013