More Recognition
As we all know, Biometrics has to do with recognition of unique features of ourselves, whether it is from a physiological or behavioral standpoint. In this regard, hand geometry scanning and fingerprint scanning have long been the dominant technologies, no matter what the application might be. But lately, at least from my viewpoint as a tech writer, it seems like that there has been an uptick for the demand with regards to confirming the identity of an individual based from their behavior, whether it is the way they sign their name, or even the way they may type on a keyboard.
Well, there is now a newer behavioral way of doing things that is coming upon on the horizon-and it is known as “object recognition”. A Biometrics Vendor known as “Neurotechnology” (actually based out of Lithuania) has come out with a new software solution with regards to object recognition. The details of this: “SentiSight 3.0 provides enhanced 2D and 3D object recognition quality using still or video images from most digital cameras, including Webcams. It can detect and recognize whether a particular rigid object, such as a product, logo or building, is in a scene and identify its specific location in that scene. It can also count the number of specific identified objects in a scene and can compare two photographic images to provide place recognition, based on objects within the picture . . . The new shape-based algorithm in SentiSight 3.0 is suitable for localization and recognition with objects that have distinguishable external or internal edges. The algorithm is fully tolerant of in-plane rotation, up to 15-20 degrees of out-of-plane rotation (such as from frontal to profile) and a wide range of changes in scale. It can handle occlusion of up to 50% as long as enough unique edges of the object are still visible. Multiple views can be added to the object model to provide even more reliable recognition or better out-of-plane rotation tolerance. The shape-based algorithm offers enhanced recognition at near real-time performance in many conditions.” (SOURCE: http://www.findbiometrics.com/industry-news/i/9203/).
My Take
Object recognition can actually be a very complex process, involving actually, quite a bit of high level mathematics. There is really nothing new about object recognition, it is a branch of computer science which has been around for a long time. In fact, my uncle who is now 70, first worked in this area when he got started out in IT. Object recognition is in fact a subfield of what is known as “computer vision”, in which a computer tries to mimick the visual process of the human being. But just like everything else over time, advances have been made, and processes and scientific principles have been now brought to a point where everything can be done with a click of the mouse.
As described in this Posting, I believe that object recognition is being used here when an individual computer is trying to recognize a particular object. But however, the same concepts can be applied to the world of Biometrics as well. For example, instead of having to use a fingerprint to login, perhaps there can be a Behavioral Biometric in which an end user can be verified and logged by the way they recognize particular objects in a particular field of view. Note that this is not a Physical Biometric, but rather, it would be a Behavioral Biometric, because it would be the unique patterns upon the keyboard or the mouse in which the end user tries to recognize the particular objects which would be captured and examined.
To the best of my knowledge, I think there are features out there which resemble object recognition, but I don’t think it is available as a complete solution yet in verifying the identity of an individual, just like the other Biometric Technologies of today. I know for sure it has been used in gauging customer response to potential TV and online advertisements.
But just based upon this Posting, object recognition can open up the avenues to a tremendous number of other types and kinds of Biometric applications which can include the “ . . . Recognition of documents, stamps, labels, packaging and other items for sorting, logo masking, usage monitoring and similar applications . . . [as well as] . . . Object counting and inspection for assembly lines and other industrial applications . . . applications such as: smart toys for children that recognize cards, images, pictograms, etc.; recognition of places based on photographs and recognition of products such as beverages, foods and other consumer goods . . . Robotic vision for navigation and manipulation . . . Law enforcement applications for identification, such as tattoo recognition.” (SOURCE: http://www.findbiometrics.com/industry-news/i/9203/).
And the list goes on and on and on . . . who knows, the day when computers can perfectly mimick the brain and vision may soon be a reality.
i went to the same school as patrick. i remeber those girls from my school who wrote in. they were white trash...i always felt so bad for them.
Posted by: Belstaff Jacket | April 01, 2012 at 03:29 AM