Non–destructive Detection of Hollow Heart in Potatoes Using Hyperspectral Imaging

Non-destructive detection of blackspot in potatoes by Vis-NIR and SWIR hyperspectral imaging

“…Hyperspectral imaging, a technique combining the principles of spectroscopy and imaging, has been applied to subsurface defect detection in fruit and vegetables, such as apples (ElMasry, Wang, Vigneault, Qiao, & ElSayed, 2008;Lu, 2003;Xing & De Baerdemaeker, 2005;Xing, Saeys, & De Baerdemaeker, 2007), pears (Zhao, Ouyang, Chen, & Wang, 2010) and mushrooms (Gowen et al, 2008). In the case of potatoes the usefulness of hyperspectral imaging has been reported for the discrimination between potato tubers and clods (Al-Mallahi, Kataoka, & Okamoto, 2008;Al-Mallahi, Kataoka, Okamoto, & Shibata, 2010), the detection of hollow heart (Dacal-Nieto, Formella, Carrión, Vazquez-Fernandez, & Fernández-Delgado, 2011b) and the detection of common scab (Dacal-Nieto, Formella, Carrión, Vazquez-Fernandez, & Fernández-Delgado, 2011a). Thybo, Jespersen, Laerke, and Stødkilde-Jørgensen (2004) were able to identify internal bruises in potato slices of cultivar Saturna by applying magnetic resonance imaging.…”

Farm biosecurity hot spots prediction using big data analytics

“…The current practice of the salad leaf disease detection is to use farming experience and judgement to collect already affected leaf samples and send those to a plant pathology laboratory to conduct further analysis and confirm. In this study we focus upon developing methodologies to detect the presence of a particular disease or pest infestation damage of 978-1-4799-8442-8/15/$31.00 © 2015 IEEE ICDE Workshops 2015 salad leaf through machine learning based analysis of spectral profiles recorded by a Spectroradiometer in the in-situ field environment [8][9][10][11][12][13][14][15][16][17][18][19][20]. The motivation behind this study was to demonstrate a proof of concept of the effectiveness of the hyperspectral sensing of salad leaf physiology to create ground truth data (Fig 2) along with the climatic data (temperature, rainfall, humidity, wind speed etc.…”

“…Soil moisture, soil surface temperature and NDVI values of each pixel were used to train a simple data driven model to train a supervised knowledge predictor. This predictive system was trained based on farm's historical records and hyperspectral ground truth data as training targets [1][2][13][14][15][16][17]]. …”

“…The main objective of this project is to identify one of the key challenges which are faced by the Biosecurity communities, discuss potential solutions and identify the opportunities emerging from cross-domain interactions among the experts from Biosecurity, Agriculture, Aquaculture, Health, Bioinformatics experts, and ICT experts. Therefore, we expect to gain from the cross-domain experts a mechanism of how they can apply modern big data and knowledge engineering techniques to provide state of the art solution for a biosecurity decision support system [11][12][13][14][15][16][17][18][19][20]. …”

A Review of Optical Nondestructive Visual and Near-Infrared Methods for Food Quality and Safety

“…The advantage of NIR is its cheapness. Dacal-Nieto et al [217] have recently used NIR multispectral imaging to detect the hollow heart of potato tubers. The camera used is sensitive from 900 nm to 1700 nm and used Specim Imspector N17E (Specim Oy, Oulu, Finland) spectrograph.…”