Unexpected item in the bagging area

Anyone who has been grocery shopping recently can't have failed to notice the numerous self-checkout lanes that many grocery stores are now installing in their premises as an alternative to traditional cashier-staffed checkouts.

The reason for this is quite simple. By enabling consumers to scan the barcodes on their own items, and manually identify items such as fruits and vegetables which are then weighed, stores can man a six station check out with just a single person, cutting down on costs considerably.

But by doing so, many stores have left themselves open to unscrupulous individuals who may either attempt to hoodwink such systems into believing that they are purchasing a lovely bunch of coconuts instead of a pack of somewhat more expensive sirloin steaks, or simply bag the items at the checkout without bothering to scan them at all.

Apparently, things have got so bad on the pilfery front, that New England-based Big Y (Springfield, MA, USA) has abandoned any more self-checkout ideas it had planned, citing both customer service as well as shoplifting behind its decision.

Fortunately, however, one company now believes it can offer a solution to the knotty problem -- a solution that is, of course, based around an intelligent vision analysis system.

That company, StopLift Checkout Vision Systems (Cambridge, MA, USA) has developed a computer vision system that can interpret the behavior of the customer by analyzing and understanding body motions at the checkout.

By analyzing the digitized video, the so-called “ScanItAll system” scrutinizes how each item is handled to determine whether or not it was properly scanned. The patented system is capable of understanding fraudulent behavior, including when a bar code is covered up by hand.

Of course, there are alternative approaches to cutting down fraud. One such approach which has been tested out by grocery retail giant Kroger (Cincinnati, OH, USA) involves the deployment of a tunnel called the Advantage Checkout. This system incorporates a battery of imaging scanners that read bar codes and letters and numbers on goods to identify them as they travel through the tunnel.

Eliminating the need for customers to scan their own goods could prove equally as effective, if not more so, at cutting down on theft as analyzing customers' movements from video footage. Combining the two approaches could mean that thieves are faced with a much tougher time should they try to purloin the sirloin in the future.

References:

Method and apparatus for detecting suspicious activity using video analysis
Self-Checkout, Too Easy to Steal?
Self-checkout lanes boost convenience, theft risk
New Kroger Bar Code Scan Tunnel Could Revolutionize Retail Checkout

Sent to Coventry

This week, I dispatched our European editor Dave Wilson off to the Photonex trade show in Coventry in the UK to discover what novel machine-vision systems might be under development in Europe.

Starting off early to beat the traffic jams on the motorway, he arrived at the Ricoh show grounds at the ungodly hour of eight in the morning. But that gave him a good two hours to plan the day ahead before the doors of the show opened -- which is exactly what he did.

Whilst browsing through the technical seminar program organized by the UK Industrial Vision Association (UKIVA) over a breakfast of Mexican food, one presentation in particular caught his eye.

Entitled “3D imaging in action,” it promised to reveal how a Sony smart camera and a GigE camera could be used together to create a 3-D image-processing system that could analyze the characteristics of parts on a rotating table.

The demonstration by Paul Wilson, managing director of Scorpion Vision (Lymington, UK; www.scorpionvision.co.uk), would illustrate the very techniques that had been used by a system integrator who had developed a robotic vision system that could first identify -- and then manipulate -- car wheels of different sizes and heights.

And indeed it did. During the short presentation, Wilson explained how the Scorpion Vision software developed by Tordivel (Oslo, Norway; www.tordivel.no) had been used to create the application which was first capturing three-dimensional images of the parts and then making measurements on them. The entire application ran under an embedded version of Windows XP on the Sony smart camera.

Interestingly enough, software such as Tordivel’s allows applications such as this to be developed by a user with few, if any, programming skills. Instead, they are created through a graphical user interface from which a user chooses a number of different tools to perform whatever image-analysis tasks are required.

The ease by which such software allows system integrators to build systems runs in stark contrast to other more traditional forms of programming, or even more contemporary ones that make use of graphical development environments. Both of these require a greater level of software expertise and training than such non-programmed graphical user interfaces.

Even so, the more sophisticated and easier the software is to use, the more expensive it is likely to be, a fact that was not lost on Scorpion Vision’s managing director as he spoke to our man Dave at the show.

Nevertheless, he also argued that higher initial software costs can often be quickly offset by the greater number of systems that can be developed by a user in any given period of time -- an equally important consideration to be taken into account when considering which package to use to develop your own 3-D vision system.