Technology

Attrasoft Core Technology:

1. Find an image in a billion images in 3 seconds.

2. Find a video in 1 million videos in 3 seconds.

3. Tag images automatically using software. Download demo.

Attrasoft detects images and videos on the Internet.

Our approach is similar to law enforcement’s use of fingerprinting to find and match identities.

The unique attributes of a video clip – its “video fingerprint” - are compared against a library of video fingerprints that have been taken from the media vault.

The content recognition algorithms that create and match the fingerprints are our strength.

The patent-pending Attrasoft technologies provide a fundamental building block in image and video search capabilities. The below provides an overview of these capabilities (more technical information is available upon request).

Overall, Attrasoft technologies allow fast, scalable, and accurate image searches. The technology allows for:

1. THE ABILITY TO EFFICENTLY CREATE FINGERPRINTS AMONG A DATABASE OF IMAGES. The efficient creation of digital fingerprints of all images and videos on the Internet (the “Fingerprint Pool”). These fingerprints are stored in a central database.

2. THE ABILITY TO QUICKLY CREATE A FINGERPRINT OF THE SEARCHED IMAGE. The efficient creation of a digital fingerprint of an image or video provided by the user (the “Subject Image”).

3. THE ABILITY TO MATCH THE SEARCHED IMAGE WITH EXACT OR SIMILAR IMAGES IN THE “FINGERPRINTED” DATABASE. The efficient matching of the Subject Image to exact (or similar) images in the database of images that had been previously “fingerprinted”.

4. DISPLAY STAGE. Providing the user the site locations (and images) of “matched images” to the searched image.

Our approach

Our algorithms create a “numerical fingerprint” that represents the attributes of an individual frame of a video. Then, the algorithm matches the fingerprint with similar fingerprints in the content library.

What constitutes a match? Well, it depends. This is what happens behind the scenes to deal with the subjective nature of determining a match. Attrasoft’s neural network is taught what a match is by feeding in a sample set of image pairs. An image pair is two images of the same thing but the images differ slightly. By feeding the neural network filter with a series of image pairs, the filter learns the similarities and differences so it can come to understand what you mean by a match.

Because our algorithms reduce the large amount of data in a video into a small numerical fingerprint – the image is represented by a string of numbers – the video matching process can be performed in RAM. This makes the matching process very fast.

The algorithms have been refined in large scale implementations with TNS Media Intelligence since 2005, which dominate 90% US print media intelligence market. As a result, we can achieve levels of accuracy that are unmatched in the industry.

Speed, accuracy, and scalability, that’s what sets our approach apart.

How it works

For you deep math folks, our algorithms are based on Markov Chain Theory and Neural Network Theory. Images are classified by a distribution function that describes the invariant distribution that the Markov chain settles on.

Summary,

Proven Core Technology
Searching with Images can be More Relevant and Faster
Large scale system in production with TNS Media Intelligence (sold to WPP for $2.2 billion dollars)
Searching via Images is cool!