For a customer in the agricultural sector, a computer vision system will be developed which observes an organic product on a conveyor belt and produces a qualitative description of the product.

• Preliminary study of the effect of different types of (visible, IR, UV) lighting which helps the detection of small blemishes/deceases.
• 3D object modeling to produce an accurate size/weight estimation
• Texture and color analysis
• Hardware integration, allowing a robotic arm to grab the product from a fast-moving conveyor belt.
• Feedback from a weight sensor in combination with a self-learning algorithm to produce accurate weight estimates.

For a union of oyster mushroom cultivators and suppliers, a website is developed which allows both cultivators and their suppliers to register online the essential details regarding their production process and production yield. This allows the union to work closer together, trace back problems in the final harvest to process changes earlier on and provide easy and transparent statistical feedback to all members of the branche.

• User requirement analysis and knowledge modeling
• Database design – ready for the foreseeable and unforeseeable future
• Interface design – one click navigation to all frequently used components
• Data analysis and visualization – visualization as graphs, easy export options to Excel, PDF
• SaaS – delivered as fully functional solution, running on a server maintained by VanAI

VanAI has a new sister-company: Advanced Mushroom Research B.V. (AMR). This new company has come forth from the succes of projects completed in the mushroom cultivation sector. Together VanAI and AMR will offer AI and computer vision technology to mushroom cultivators and product suppliers with the aim of improving harvest yield and quality.

www.advancedmushroomresearch.com (under construction)

Please have a look at our new website ( www.vanai.nl – you’re probably already there!). We have updated our look, but more importantly there are some interesting new features that may be of interested to our (potential) customers and partners:

• News section which will be regularly updated with information on new projects, company news and general news from the world of AI that may open up new possibilities for your business.
• Customer login: existing customers can now log in to the website and access live information on their own projects, share files and provide feedback.

P.s. Expect to see our new logo and style in future communications.

In cooperation with Innovattic, we are creating a mobile application for the Dutch Police which will be part of the Stop Heling project. This project aims to decrease the sales of stolen goods by allowing people to register the serial numbers of their (electronic) belongings. When police officers come across goods of unknown origin, it will be easy for them to see whether these goods have been reported stolen and to return them to their owners.

VanAI will be developing the image analysis part of an app that will allow people to automatically scan serial numbers of their belongings using barcodes or through OCR (text recognition) on the actual serial number. The app needs to be available for the iPhone, Android and BlackBerry, posing several developent challenges.

All code on the iPhone needs to be written in its own Objective-C language; Android supports C++ code (through Java Native Interfaces), while the BlackBerry gives you no other choice but to develop in plain Java. Through rapid prototyping in all environments, contant thorough unit testing and frequent code refactoring we will ensure that a single base code set will be easily portable to all three environments.

The second reason why this project is interesting is the fact that a typical OCR algorithm (which works by segmenting characters and applying a battery of classifiers (like neural networks) to classify each character) requires a lot of CPU, more than is available on a mobile phone. We will thus have to rethink the entire approach and create our own proprietary OCR implementation.

For VanAI this project will be a first venture into the domain of mobile applications. This has till now been a semi-deliberate choice based on my own believe that in the (near) future we’ll be moving towards a more interconnected way of computations; I believe that apps will at some point not run on your phone anymore, but on some advanced computational “grid” (you’ve probably heard the term “Cloud computing” before). Unfortunately it’s still going to take a few years before we can enjoy WIFI quality internet access anywhere we go, so at the moment we’re forced to bring the intelligence to the phones rather than connecting the phones to an intelligence grid.