|
|
|
|
|
Latest Edition New capital injection at Cockerills No-one could accuse Martin Cockerill of lacking confidence in the potato industry. R. S. Cockerill (York) Ltd has put substantial sums of its own money into new equipment, a redesigned packhouse and additional refrigerated storage. Five years ago, when the current financial crisis was just becoming visible to anyone prepared to look, Martin Cockerill set about devising a development programme intended to re-equip his business to meet the needs of the modern discount multiple retailers. His aim is at all sections of the market but, in particular, the two major customers who are the leading discounters Aldi and Lidl. ‘We had been steadily expanding the packing side of the business and it became obvious that if we wanted to grow we had to be able to handle more tonnage,’ he explains. ‘On the packing side we are now around 1000 tonnes a week which means an intake total of around 1200 tonnes. That is split roughly into three sectors with Aldi and Lidl taking slightly less than a third each and a range of supermarkets and wholesalers taking the rest.’ To cope with the output the factory had four washers feeding five packing lines with a MAF electronic weight grader around 10 years old. The decision was taken to replace this with a faster machine and after some fairly extensive research in Europe Mr Cockerill settled on an Italian-built Sammo four-lane weight grader which would be built to his specification while the layout of the packhouse back at York would be designed around it. For the full article see January/February 2012
Managing variability in potatoes Simon Griffin, from Berkshire-based SOYL, speaking at the annual conference held by the Cambridge University Potato Growers Research Association, was given the task of explaining how technology can help im-prove yield and quality. ‘Precision farming is about measuring and managing variability,’ he began. ‘It’s an approach which is no different from what you are already doing every day – the right thing in the right place, at the right time. We’re not trying to reinvent agronomy but we can be much more accurate. ‘You first have to accept the premise that tuber size, dry matter and yield will vary across the field,’ explained Mr Griffin. ‘If we make the assumption that what we want is a uniform crop, we need to see if we can remove some of that variation.’ He ran through the options, starting with the now familiar soil mapping which aims to tailor applications of nutrients such as P & K. He went on discuss conductivity measurements which can be used to relate moisture content and water holding capacity of different soil types with irrigation recommendations. He also pointed out that satellite imagery had come a long way in the last few years and was now cheap enough to be used to good advantage. ‘I am quite confident that this can show variation in canopy size across the field and we might be able to use it to recommend variable inputs ac-cording to the vigour of the crop.’ He suggested that satellite images could help with irrigation scheduling while the clearly visible differences in crop cover can alert growers to the early signs of stress or disease. "We have got the methodologies to identify variation and to come up with a management plan that will turn the pretty pictures into something useful. For the full article see January/February 2012
Sorting can be digitally enhanced The authors of a paper to be delivered at Crop Protection in Northern Britain 2012* point out that clear unblemished skin is a significant selling point and that potatoes with surface defects caused by ‘otherwise benign infections’ are strongly avoided by consumers. With most of the crop graded by sight, however, there are inevitable mistakes and wastage. Tom Duckett and co-workers have developed an inexpensive system for automatic identification of skin defects using what they describe as ‘off-the-shelf hardware’ comprising a low-cost sensor and standard desktop computer equipped with a graphics processing unit (GPU). The software has been designed to detect and quantify a range of common defects, using image processing and ‘machine learning’ techniques to differentiate between them based on their visual characteristics. It also has an intuitive graphical user interface (GUI) to allow easy set-up by quality control staff. The system can be programmed to process individual tubers or to produce aggregate data for a sample, summarising the proportions of potatoes carrying common scab, black dot, silver scurf or greening, for example. Potatoes are placed in a light box equipped with a 10 mega-pixel web-cam. Selected tubers are used to ‘mark-up’ defective and clean areas to train the system, with output displayed as a colour-coded computer screen image along with a summary report giving the percentage area for each of the defect types. To train the software the operator simply hits the buttons for ‘capture image’ and ‘remove background’. This highlights the tubers after first recording an image of the empty tray. ‘Mark-up’ is performed by selecting a user-defined class or category which will correspond to a particular type of defect. The pixel area which relates to that defect is selected to provide the ‘training data’. Pressing the ‘train classifier’ button completes the process but the system can be quickly re-calibrated for different potato varieties or different skin conditions. For the full article see January/February 2012
|
|
 |
|
|
