Wednesday, August 16, 2006

Google buys Neven Vision

So I haven't been able to post for some time for which I apologize.

Big news today is that Google has bought Neven Vision and immediately after buying it, Neven Vision has virtually shut down their site. Upon visiting the site the following message is displayed:

"Thank you for your interest. Neven Vision was recently acquired by Google Inc. and Neven Vision product information is no longer available on this site. Click here to learn more."

However a search for cached pages revealed the information that Google is trying to hide:

So what exactly does this company do:

Computer Vision, also known as Machine Vision, is a field of technology engaged in teaching computers to "see" and understand visual imagery. Neven Vision is primarily focused on the subset of computer vision known as visual sensing, which is the automated extraction of information about objects or scenes in one or more images.

Neven Vision's computer vision technology is the fastest in the industry and represents leading accomplishments in this field. Several U.S. patents have been granted to Neven Vision for its unique inventions. U.S. government and independent observers have recognized the underlying technology as most advanced with respect to accuracy, speed and efficiency.

The core building blocks of the company's vision-enabled products and services are our patented face and object recognition engines. Below is a simple representation of how each of these engines work.



1. Faces in an image are automatically detected by a robust face finder component that determines the position and size of the face in real world conditions (varying illumination, pose and expression).
2. A second processing stage determines the position of local features on the face, called “landmark finding”.
3. Then a Gabor Wavelet transformation takes place to compute the “face
4. -template” from the local features by extracting the template from an image that contains the essential, condensed facial information needed to determine a person's identity (a “face-template” is only about 1kByte in size;


The company has the following patents


EP1072018

Wavelet-Based Facial Motion Capture for Avatar Animation
1072014

Face Recognition from Video Images
EP1072018

Wavelet-Based Facial Motion Capture for Avatar Animation
218457

Face Recognition from Video Images
218458

Wavelet-Based Facial Motion Capture for Avatar Animation
EP1072018

Wavelet-Based Facial Motion Capture for Avatar Animation
1072014

Face Recognition from Video Images
6714661

Method & System for Customizing Facial Feature Tracking Using Precise Landmark
6222939

Labeled Bunch Graphs for Image Analysis (EYEM1160/ NE01)
6356659

Labeled Bunch Graphs for Image Analysis
6563950

Labeled Bunch Graphs for Image Analysis
6466695

Procedure for Automatic Analysis of Images & Image Sequences Based on Two Dimensional Shape Primitives
6272231

Wavelet-Based Facial Motion Capture for Avatar Animation
6580811

Wavelet-Based Facial Motion Capture for Avatar Animation
6301370

Face Recognition from Video Images


From this page:

 Field Identification Tool for Law Enforcement and Security Teams

The Mobile Identifier™ platform provides effective identification resources in the palm of your hand. The compact, ruggedized Mobile Identifier™ handheld employs industry-leading face recognition and fingerprint matching technology. Additional recognition engines provide the ability to recognize and compare other identifiers such as tattoos or license plates.

Efficiency and Productivity
Using the Mobile Identifier™ face images and fingerprints can be scanned and checked against the on-board databases on-the-spot, saving valuable man hours and expediting investigations.

Management and Reporting
Easily import, synchronize, and manage existing image galleries through a secure web interface. Daily event logs provide detailed activity tracking and reporting.

Advantages

* A force multiplier: Saves law enforcement personnel time
* Helps prevent human errors in identification
* Expedites investigations
* Alerts instances of false identity/assumed identity
* Compatible with existing databases
* Accelerates learning curve
* Equips all officers with the latest field intelligence


More on how the technology is being used by the Law Enforcement:
02-JAN-2006 || eWEEK.COM
LAPD Systems Keep an Eye on Crime
Case Study: Video surveillance and criminal recognition software are put to the test on the streets of Los Angeles.

A drug deal is happening right now in Los Angeles' MacArthur Park, and there are no cops around. But that hasn't been such a problem since the Los Angeles Police Department installed 12 surveillance cameras, said Sgt. Dan Gomez of the LAPD's Tactical Technology Unit, Office of Operations.

From a remote location, Gomez, an officer with 13 years' experience, watches the monitors: "All of a sudden, you see a drug dealer going back and forth. [You can see] where he's hiding his stash, where he's hiding his rocks of cocaine."

"In the past, you would never be able to see [all the details of a crime] because you couldn't get close enough. Now I can see it," Gomez said.

When Gomez sees a crime going down, he calls in officers and remotely guides them, step by step: "Hey, this individual just put that in his right pocket. Oh, he just saw you; he's turning. I saw him. He dropped it right by that bench."


The question I leave you with is that why does Google feel the need to hide this from us by taking down Neven Vision's site?

About one of the company's products called iScout:
iScout allows camera phone users to simply snap photos to initiate a search process and get relevant information or content sent to their phone. Shoot the CD cover of your favorite artist and get a sample MP3 or ring tone or enter to win concert tickets. Shoot an ad in the newspaper and get a coupon or product information. Traditional print media and packaging can become visually hyperlinked and provide a rich interactive experience for both consumers and marketers.

Brands, studios, publications, and content providers can setup iScout enabled campaigns through a simple web interface. First, input the images to be recognized, then the content to send to the user, and it's done.

The iScout client application can be installed on most camera phones. To run iScout, the user only requires a data plan. Once installed, look for the iScout icon and start shooting.




And a FAQ
  

+ iScout FAQ's

What is iScout?
iScout is an object recognition platform that enables camera phones to “recognize” objects and provide relevant content to the user.

What type of phone do I need to use iScout?
Virtually any device having a camera and network connection is compatible. iScout interaction can be accomplished via MMS or by using a downloadable Java or BREW application.

What are the benefits of an iScout mobile marketing campaign?
Visual/printed media is one of the largest industries in the world, but the value has been difficult to exactly quantify. iScout-enabled campaigns provide a rich customer experience with instant gratification, while gathering superior market data, qualification and quantifiable feedback. As with online pay-per-click advertising, user costs are only incurred when interested parties click on an image.

What types of images will iScout recognize?
Any still image can be used, including print media, camera photos, or TV/Video screen capture. With its ability to recognize most any image, iScout reinforces your brands, images and logos. Barcodes/symbols can be used as well, but are not necessary.

What technologies does iScout use to send requests?
iScout image requests can be sent via MMS, HTTP, or email, depending on the cellular network, phone, service, etc.
  post to Del.icio.us

eXTReMe Tracker