I hope this short summary watered your mouths and I will see all of you in Istanbul in April. Of course the networking will be great as always, and the pre-conference reception, the Friday evening event and the sightseeing tour on Saturday afternoon will make for a brilliant framework. More information can be found at www.emva.org.

Gabriele Jansen

This proposal was not very well received by some of the software suppliers back then. There was talk of the difficulty to come up with a distinct specification and of the necessity to distinguish oneself from competition especially by the differences in the software and the resulting impossibility to provide a direct comparability.

However, a couple of weeks ago Dr. Wolfgang Eckstein from MVTec delivered a public and concrete proposal on how such a benchmark could be designed and executed. He, as well, suggests to define performance criteria for typical vision applications like barcode identification or pattern matching, to establish a uniform fixed framework for the benchmark, and then to execute the comparison on selected, standardized and well-described image data.

There is a very similar approach already established in other industries, BTW. The British Home Office Security Development Branch (HOSDB), e.g., provides libraries (i-LIDS) with video footage to companies from the video analytics area for a benchmark of their software in applications like people tracking covering several cameras, perimeter surveillance or detection of abandoned luggage. This gives the suppliers the opportunity to test the capabilities of their products in a well-defined scenario and based on relevant input data while the potential customer has the chance to compare the performance of the different software packages.

The challenge, here and there, is of course in the sensible choice of application relevant image data and this gets even more demanding the more complex the vision tasks becomes. May it be even relatively straightforward to decide upon images and testing scenarios for the determination of a barcode identification performance, it ventures into the indefinite complex to do this for a surface inspection.

But there is yet another aspect, not taken care of with a pure performance benchmark of algorithms, for the value rating by the user however at the same level of importance: the usability of the software. How laborious is the parameter set-up of the tool, how transparent is the result extraction, and how coherent are system and result messages and reports? The answer to these questions can determine the success or failure of the application, independent from the performance of the algorithms employed. While following the goal to accomplish transparency and to provide impartial decision criteria to the user, this latter aspect of vision software performance needs to be included in any benchmark.

All aspects considered a benchmark of vision software is by no means a small feat, but definitely one that is worth the effort. One can only hope that Dr. Eckstein´s advance will be taken on by other players in the industry. The real benefit will be achieved only when the definition of the performance criteria and the description of the benchmark scenarios as well as the design of the image data basis are derived from the input, the know-how and the experience of many experts and the procedure and the results will then be supported by many of the suppliers.

Gabriele Jansen

Financial crisis, recession, economic uncertainty – the consequence: lay-offs. Is that the necessary, sensible, businesswise responsible decision?

Daimler, Opel, Arcelor, SAP, but also Google and Microsoft lay off their employees. For the United States the biggest reduction of jobs since 1945 is already forecasted.

Costs need to be cut in difficult times, the belt needs to be tightened. The company as a whole needs to be protected, last but not least in the interest of the majority of employees (which were not let go). This is the usual and also the ethical correct argumentation. But is it economically sound? Is the short-term benefit really bigger than the potential damage?

Reducing costs, shedding cushions accumulated in fat years, making the company lean and agile, is not a bad idea, generally speaking. It might have been more clever, though, to accomplish that already during the good times and thus be better armed for the upcoming difficult months. But: Better late than never!, as the saying goes. Now it is up to the smart company leader to decide where the dispensable costs are located.

In our companies from the „developed countries” the block of labor cost ranges very highly in the cost categories. That makes cost cutting here so attractive. However, one of the reasons for this is the fact that our people are so highly qualified. They bring exactly the skill set to the table that is not only required for their demanding tasks – all other tasks are long since outsourced anyway -, but that was build up and financed heavily by the companies themselves. All the investments in these so called human resources – intensive recruiting, tedious selection processes, company internal training, additional education, specialization – are lost with the lay-off. As well as the know how of the people about the products, markets, competition, internal processes of their company. That is first and foremost a bleeding. Bloodletting was common practice in the middle-ages and was prescribed almost always no matter what the ailment was, but today we know that this lead more often than not to the early demise of the patient instead of his recovery. This is the danger that also the company faces when reacting to experienced or expected difficulties foremost with lay-offs and thus with decimation of their own strength.

A diet for the company can be reasonable, with love-handles too prominent fast movements are becoming difficult. But “lean” must not turn into anorexia. To hold one´s ground, not only but especially in times of crisis, requires strength. Strength in innovation capability to bind the customers to the company by better, not cheaper, products and services. Strength not to lose sight of the long-term strategic goals and thus stay a reliable partner for the customers. Strength to develop new markets, products and sales channels, i.e. to conquer the recession in the old markets with investment into new ones. Investment into the future in addition to coping with the not so easy presence is only possible with qualified and motivated people on board. A team that is spread too thin is lacking both, power and creativity.

BTW future. All current doomsaying put aside: the recession ultimately will end, there will be a rebound. First signs for this rebound are expected by the experts around mid 2009. In most European countries, with the respective labour laws, this will be about the time when the employees given notice today will actually leave the company. The necessary resources then required, will need to be searched for, found and trained and it will take quite some time before they can be as proficient as the experienced staff from the past.

Would it not be better to rise with the economic upturn with innovations, improved products and processes and motivated people on board, empowered by their own company?

This, in any case, is my point of view.

Before either one of both sides can leverage these advantages, however, much time, effort and a good measure of enthusiasm has to be invested. A successful industry standard naturally requires that the technical details are worked out by the industry itself and that the result is accepted and put into action by at least the major part of this industry. For Machine Vision, this work is executed today in standardization working groups surpassing the barriers of companies, countries and languages, supported by the three major Machine Vision associations: EMVA; AIA and JIIA. The current status of the standards has been presented during the Vision trade show with lectures as part of the Industrial Vision Days but also at the special exhibition „Vision Standards“. Organized by the EMVA and the trade show all three associations presented here the standards they host: GigE Vision, CameraLink, GenICam, EMVA 1288 and Lens Mount. This exhibition has been highly informative, well presented – one could even say sexy. 

Machine vision is generally understood as image processing for industrial applications, as opposed to the so-called non-industrial applications of for example medicine, surveillance, traffic, entertainment, to name only a few. However, also these areas are in fact industries, only not production oriented ones. And the term Machine Vision could also be understood as “machines that see”, whatever they see in whichever industry or application as long as it is an automated process. This broadening of a definition would directly lead to a huge broadening of what is today considered the Machine Vision Market and a large group of additional players could be suddenly seen on the field.

Is this useful or not ? For a trade journal ? For an association ?

Let´s face the question by taking a closer look into these other areas of application for the technologies we usually cover with INSPECT (www.inspect-online.com).

The INSPECT magazine 03/08 is focused on a wide range of different applications beyond production. Besides the target of generating profit quite a few of these applications directly or indirectly provide for a safer world, a cleaner environment or improved medical treatment. The combination of fast 3D stereo tracking in combination with tissue simulation in virtual reality for example allows for the first time ever to practice eye surgery until proficiency is reached like pilots practice mastering the airplane before their first real take-off. With the increase of age-related eye problems if only by the shift in the age pyramid, millions of us will be very happy about this in the future.

A totally different and yet machine vision empowered tool to make our world a safer place is the equally respected and loathed speed control. Speed measurement, number plate recognition and driver face capturing are all optical and machine vision tasks. As much as these curbside boxes cost us frequent drivers and as much as we might curse it for again getting us in the one moment of lowered attention, I think we still agree that thousands of lives are saved because of the presence of these speed cameras.

Recycling is one way to get our energy balance back on track and glass recycling yields especially high potential. Did you know that with each ton of recycled glass the emission of greenhouse gasses is reduced by 200 kilograms ? This, however, is only made possible by very fast and highly accurate optical sorting of the secondary raw material.

These and many more equally important equally interesting applications are covered with the magazine. Among them also the meanwhile famous Stasi (i.e. Ministry for State Security, German Democratic Republic) puzzle, the vision empowered reconstruction of 45 Million torn or shredded Stasi documents. A topic very intertwined with our country´s recent history, yet not as German as one could think at first glance.

So coming back to the question: does the definition of Machine Vision need to be extended? Why don´t you share your thoughts on this and other “vision related” matters with other experts either here or in our newly established INSPECT community at http://network.inspect-online.com.

Looking forward to meet you there,

Gabriele Jansen