At Evolution Robotics Retail, we focus our research and development efforts around improving our object recognition and computer
vision capabilities. We are fortunate to have on staff some of the leading computer vision experts in the world, many
of whom were part of Caltech's Vision Lab.
ViPR® – Giving Products the Ability to See
Our ViPR (visual pattern recognition) technology provides a reliable and robust vision solution that truly gives electronic
devices the ability to detect and recognize complex visual patterns – in effect, to see.
The patented ViPR® image recognition technology illustrated above is used in our LaneHawk and ShelfHawk retail systems to detect and recognize items without having to read the UPC code.
How it Works
The combination of several key elements allows ViPR to achieve a high level of performance.
Example of a recognized image with the
features highlighted.
|
First, is the choice of descriptors it uses to encode unique visual patterns such as the corner of an object or the
print on a label. As the most distinct regions (called features) are localized in the image, unique descriptors are
computed for each of them. Several hundred such features are automatically extracted and stored
in a database to describe the unique patterns in each image. |
Second, is the ability to analyze a new image to collect sufficient evidence to reliably find a match within an extremely
large set of possible candidates. The algorithm that ViPR uses to select the correct candidate is similar to a voting
mechanism: each feature votes for the candidate which includes a similar feature (e.g., a corner feature in the
new image that matches a corner feature in a trained image). The correct candidate will receive the largest
number of votes since most of the features will be in agreement; however, a single or a few votes might be
incorrectly cast on wrong candidates. The likelihood that a large number of votes are cast on the wrong candidate
is small, demonstrating that the algorithm is very reliable in selecting the correct match.
Recognition with partial occlusion |
Recognition with different position |
Recognition at a distance |
Recognition at an angle with partial
occlusion |
Third, is the ability to do all this computation in an extremely efficient manner: recognition happens
in a fraction of a second when searching a database of several hundred patterns.
Using ViPR Technology
| A ViPR-enabled device can automatically detect and recognize visual patterns using low- or high-end camera sensors. The algorithms that make up the technology are
particularly robust and provide an unprecedented level of reliability even with heavy distortions that can be introduced by the imaging device, a
wide range of lighting conditions, and pattern occlusions. |
LaneHawk Intelligent Lighting and Camera Unit
|
LaneHawk® uses ViPR technology to recognize grocery items by analyzing the printed patterns on their box, instead of using the barcode.
Evolution Robotics Retail has future plans for the integration of our ViPR technology into additional products for the global retail market.
