Fiber Chopping Board (FCB) was designed and developed to track people’s fresh food preparation activities in a domestic kitchen. The FCB was compactly designed “as normal a chopping board as possible” (i.e. with technology that is effectively invisible to users). It adapts FiberBoard‘s technology and is a custom-made chopping board that is augmented with fibre optics for visible light sensing, a camera, and a microphone (all of which are completely embedded).
Food ingredient recognition takes place in two stages: (i) before being chopped (when the food is placed on the board), and (ii) while the the food is being chopped on the board. In stage (i), the image of food ingredient placed on the chopping board is sensed using fibre optics. The image is then segmented, noise is removed using various morphological operators, and finally colour and other features are computed from the segmented regions and then fed into a classification algorithm. In stage (ii), audio from the embedded microphone and (optionally) acceleration data from the knife being used, are processed using a different classification algorithm. A combination of the image and audio classification results are enough for the FCB to reliably classify the type of the food item prepared on the chopping board.
Part of the Balance@Home project.