Big Data by Marr Bernard B

Author:Marr, Bernard B.
Language: eng
Format: epub
ISBN: 9781118965825
Publisher: Wiley
Published: 2014-12-15T00:00:00+00:00

Face recognition

Face recognition is a computer application that can automatically identify or verify a person from a digital image or video frame.

Traditionally, facial recognition algorithms would pick out facial features and analyse their relative position, size, shape, etc. Or the algorithm would take a gallery of face images, normalize them and only save the distinct elements for face recognition. Recognition algorithms are either geometric, which looks at distinguishing features, or photometric, which is a statistical approach that distills an image into values and compares the values with templates to eliminate variances.

Of course, human beings grow older and change and they can also change features through surgery, so the newer trend which claims far greater accuracy is 3D face recognition. Using 3D sensors to capture information about the shape and topography of a face, the information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose, and chin.

The advantages of 3D facial recognition is that it can identify a face from a number of different angles, it doesn't matter if it's day or night the system works. 3D matching technique can be sensitive to facial expression although it's only a matter of time before that's no longer as issue. Another emerging trend called skin texture analysis uses the visual details on someone's skin to identify them. This process turns the unique lines, patterns, and spots apparent in a person's skin into a mathematical statement.

For face recognition to work the technology needs large data sets, called an image gallery, that contains photographs or video stills of faces already identified by name. Software then automatically converts the topography of each face in the gallery into a unique mathematical code, called a faceprint. This faceprint can then be used elsewhere to indentify someone from existing or subsequent photos or when they are caught on CCTV doing their grocery shopping.

Unsurprisingly, considering their existing data sets, companies like Google and Facebook are already ahead of the curve when it comes to face recognition. Using the photographs users willingly upload to Facebook, for example, they are able to create a 3D image of their face and then scan the rest of the Internet to find other pictures of those people to see where else they appear and who else they might know. So, for example, if you upload pictures on Facebook they will be able to match that photo to your corporate website, online dating profile or find you in news articles or blog posts. This way companies are able to triangulate the data they have on you and find out even more.

Face recognition allows these companies to suggest name tags for the group photographs you upload without you even having to tag the photo yourself. Google has applied for a patent on a method that would allow them to identify faces in video and one that will allow people to log on to devices by winking or making some other form of facial expression.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.