Friday, April 27, 2012

Navigating through the underground

Getting to grips with the machinations of European underground transportation networks can be notoriously difficult for those from foreign parts, partly due to the fact that they employ systems that many visitors may be unfamiliar with.

And so it was when our industrious European Editor paid a recent visit to the beautiful city of Lisbon in Portugal to attend the European Machine Vision Association’s (EMVA) annual get-together at the resplendent Hotel Tivoli on behalf of Vision Systems Design.

After putting in a hard day's work listening to a variety of speakers describe the status of the image processing market in Europe, he decided to take a little trip on the local underground system to take in the sights of the city.

Sadly, however, his attempts to buy a ticket for the Lisbon underground proved somewhat unsuccessful, until, that is, a rather attractive young Portuguese woman came to his aid. Having helped our hapless European Editor purchase a pass for the train, the two then became engaged in a brief conversation, during which it transpired that the lady was planning a new life in Australia due to the lack of opportunity in her own country.

The decline of the PIGS (Portugal, Ireland, Greece and Spain) has been widely covered by the media. But gaining a first hand insight into the plight of a single individual really brought the problem home to our European Editor.

Unsurprisingly, the data presented at the conference by Gabriele Jansen, the CEO of Vision Ventures and a member of the EMVA Executive Board, confirmed that the growth in gross domestic product in that neck of the European woods is predicted to be decidedly negative for the coming year.

Indeed, while most European countries look set to enjoy a modest growth of between +0-2.5%, Spain and Italy will be facing a growth of between -0-2.5%, while poor old Portugal will fare worst of all with a growth of less than -2.5% this year.

On the machine vision front, however, things aren't as gloomy. According to the preliminary data from the EMVA, European machine vision companies saw an increase in sales of 16% in 2011 compared with the year before.

As for 2012, it looks like there is more good news on the horizon. The VDMA (Verband Deutscher Maschinen- und Anlagenbau) -- one of the key industrial associations in Europe -- expects total turnover of machine vision products to be up 5% in 2012 over 2011, a year which itself saw a 20% rise in turnover from both the domestic and export market.

Germany, naturally enough, looks set to remain the number one market for machine vision systems in Europe, a fact that will undoubtedly mean that many bright individuals from the less successful regions such as Portugal will be attracted there to find their fortunes.

Those considering moving from the economically bereft European states to a destination somewhat further afield -- such as the lady that helped our European Editor on the Lisbon underground -- might be interested to note that the Australian economy is still on the uptick too.

Friday, April 20, 2012

A wonderful life remembered

This January marked the passing of Norman Wilson Edmund, one of the true visionaries in the imaging business and the founder of Edmund Optics (Barrington, NJ, USA).

Norman Wilson Edmund was known as the creator and entrepreneurial spirit behind Edmund Scientific, which later became Edmund Optics, and is accredited with inspiring many generations of youngsters to become interested in science and engineering.

Now, to honor the contributions that he made to advance the science of optics, the company he founded has launched a new award. The Norman Edmund Inspiration Award will consist of an additional $5000 in product donations that will be presented to one of the three 2012 first-place prize recipients of the company's worldwide Higher Education Grant program, which is currently running in the Americas, Asia, and Europe.

The Norman Edmund Inspiration Award will be given to the college or university optics program in science, technology, engineering or mathematics that best embodies the legacy of Norman Edmund.

Announcing the award, Robert Edmund, CEO of Edmund Optics, recalled that his father had a lifelong commitment to motivating and inspiring young people to become involved in science, and the award would carry on his desire to excite another generation about innovation and discovery.

The beneficiary of the product award will be chosen from the three previously selected 2012 first prize recipients, from the Americas, Europe, and Asia respectively. The award recipient will be determined by the Edmund Optics board of directors committee led by Joan Husted, daughter of Norman Edmund and an Edmund Optics board member.

The prize recipients of the 2012 Higher Education Grant Program and the 2012 European Research and Innovation Award will be announced on Sept. 14, 2012. Product donations totaling $80,000 will be distributed to the award recipients in the three geographic locations. The winner of the Norman Edmund Inspiration Award will be announced on Oct. 10, 2012.

Surely, there could be no better way to remember a man with such a love of science. And if you'd like to enter the awards, there's still time. Applications are being accepted until June 30, 2012. More information can be found on the Edmund Optics web site here.

Tuesday, April 17, 2012

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

Friday, April 13, 2012

A vision of ripe fruit

Over the past few years, researchers have developed numerous robotic systems that can detect when fruits such as strawberries or tomatoes are ripe.

For the most part, such systems work by locating a fruit on the plant and then analyzing its color with a vision system. Having determined that fruit is ripe, a robotic gripper is then used to pick them off the plant.

Now, of course, vision is just one of the ways that human beings determine whether fruit is ready to eat. However, while vision is an important sense, we also rely upon a number of other senses to perform the same task -- notably, smell, touch and hearing.


So it is hardly surprising then that there are a number of folks who are also working to develop systems that can provide an automated alternative to those senses.

Many researchers, for example, are working to develop, perfect and test “electronic noses” that can determine how mature a particular fruit is. Most of these electronic noses use sensor arrays that react to volatile compounds: the adsorption of volatile compounds on the sensor surface causes a physical change of the sensor which can then be detected.

Aside from sniffing fruit, human beings often give their produce a good squeeze to see if it is ripe enough to eat. That is especially true for fruit like avocados and mangos, which we squeeze to determine their hardness or softness.

Now squeezing fruit is a pretty straightforward task for a robot, especially one that might be equipped with capacitive-based pressure sensors on its grippers. Such sensors could be calibrated so that the system they are interfaced to could be able to ascertain the ripeness of a fruit. What is more, they could potentially be used in conjunction with both the aforementioned vision and electronic nose on a future agricultural robotic harvester to great effect.

Lastly of course, let us not forget that some fruits have a characteristic sound when they are ripe, and so it is not uncommon to see some individuals tapping fruits like melons to determine whether they are ready to eat. So it is obvious that by analyzing the sound made by a reverberating melon hit by an actuator, software could tell you whether the melon is ripe or not.

Clearly, while robotic harvesting systems of the future might well deploy a vision system, they might also host a plethora of other sensory devices. For that reason, system integrators in the vision business might do worse than to take a few refresher courses on olfaction, tactile sensing and audio engineering before embarking on any new design!

References:

1. Japanese robots to harvest ripe fruits with super vision and efficiency
2. Send in the robots to pick the ripest fruit
3. Clever robots for crops
4. Intelligent harvesting robot
5. There's an app for that: test how ripe a melon is with iWatermelon for iPhone

More from Vision Systems Design:

1.  Vision system helps sort carrots
2.  Machine-vision-based inspector sorts oranges and mandarins
3.  Hyperspectral imaging sorts blueberries
4.  Weeding system uses x-rays to detect tomato stems
5.  X-ray imaging checks cherry pits
6.  Vision system sorts strawberry plants
7.  Neya Systems awarded contract for produce classification
8.  Student app helps farmers to measure quality of rice
9.  Robotic image-processing system analyzes plant growth
10.Vision system sorts out the plants

Wednesday, April 11, 2012

A distinct lack of vision

Like many folks today, I'm often looking for ways to save a buck or a dime. And one perfect way to save a few pennies, of course, is to use that highly popular piece of computer software called Skype.

Now for those of you that may have been living on Mars for the past few years, Skype is a program that you can download onto your PC to enable you to engage in either voice or video conversations with other Skype users over the Interweb, saving you both vast sums of money on telephone calls - especially international ones.

For my part, I have been using Skype to discuss all things related to machine vision systems design with our European Editor, checking in with him on a regular basis to discover all the vision-related news that's coming out of hotbeds of innovation in such far flung places as Stuttgart, Germany and Cambridge, England.

But the other night, the course of the conversation turned away from vision systems and onto the subject of house renovation. You see, our European Editor has recently had his house extensively refurbished and I was keen to see what the results looked like as we chatted on his webcam.

Sadly, however, the webcam was not connected to his laptop. Rather, it had been plugged into a heavy PC tower which could not be carried around the house. But I was so keen to see the results of the work that I instructed the wretched Editor to download Skype onto his notebook and to plug the webcam into that, so that he could move around while I gazed in awe at his freshly painted rooms.

Unwilling to disobey orders, the Editor did indeed attempt to download the Skype software onto his notebook. In fact, he attempted to do so several times before finally giving up. As he tried the download time and time again with no apparent luck, his language became extremely colorful - so much so that if his comments were to be repeated here they would surely offend the sensibilities of many of our readers.

The poor European editor, it appeared, was having a great deal of problem actually registering to download the program. All because it required him to input a “Captcha” code that would enable the program to ensure that the registration screen was actually being filled out by a real human being.


This particular Captcha test required our dejected Editor to retype a series of rather warped and crowded letters that were displayed on the screen into a field below them. But the trouble was that the images were so exceptionally mangled that our Editor had little chance of recognizing any of them. Even when the system presented new Captchas after his failures, he failed to identify any of the letters.

Clearly, there's an opportunity here for anyone involved in the vision systems business to develop some vision recognition software that would enable folks like our Editor to simply point his webcam at the screen and automatically read out those codes in an accurate fashion.

Some academics at Stanford University (Stanford, CA, USA) have already taken a crack at the problem, employing machine vision algorithms to successfully crack 66 percent of Visa's Captchas, 70 percent of Blizzard's, and 25 percent of Wikipedia's. Apparently, a 1 percent successful cracking rate is regarded as grounds for the Captcha's immediate discontinuation.

Reference:Stanford Boffins on the Brink of Breaking Captcha Codes

Wednesday, April 4, 2012

A distinct lack of communication

Because of the highly application-specific nature of many vision systems, small to medium sized enterprises must often bring together teams of engineers with highly-specialized knowledge to create new bespoke designs for their customers.

Not only must these individuals have extensive experience in selecting the appropriate vision hardware for the job, but also be able to choose - and use - the appropriate tools to program the system.

Most importantly, however, it is often the mechanical or optical engineer working at such companies who can make or break the design of a new vision system. Working with their hardware and software counterparts, these individuals can make vitally important suggestions as to how test and inspection fixtures should be rigged to optimise the visual inspection processes.



Indeed, as smarter off-the-shelf hardware and sophisticated software relieves engineers from the encumbrance of developing their own bespoke image processing products, it is the optical or mechanical engineer that can often make the ultimate contribution to the success of a project.

Sadly, however, the teams of mechanically-minded individuals employed by such companies often work in isolation, unaware of what sorts of mechanical or optical marvels may have been whipped up by their rivals - or even customers - to address similar issues to the ones that they are working on.

That's hardly surprising, since many of such companies' customers force them to sign lengthy Non Disclosure Agreements (NDAs) before even embarking on the development work. Some customers even purchase the rights to the design after the machine has been built to prevent their rivals from developing similar equipment at their own facilities.

But while this unbridled protectionism is understandable from the customer's perspective, preventing such information from being disseminated in the literature or on the Interweb actually does a complete disservice to the engineers working at the companies that are building the equipment.

That's because, rather than being able to gain any sort of education from reading about how other engineers may have solved similar problems to their own - especially those in the all important field of mechanics and optics - they are effectively trapped in an secluded world where they can only call upon their own experience and ingenuity, which may, or may not be enough for the job.

Is it time then for systems integrators to politely ask their customers to forgo the signing of such NDAs so that such mechanical and optical information can be made more widespread for the benefit of us all? Perhaps it is. But I'd be a fool to think that it will ever happen.