Page 1 Page 2 Page 3 Page 4 Page 5 Page 6 Page 7 Page 8 Page 9 Page 10 Page 11 Page 12 Page 13 Page 14 Page 15 Page 16 Page 17 Page 18 Page 19 Page 20 Page 21 Page 22 Page 23 Page 24 Page 25 Page 26 Page 27 Page 28 Page 29 Page 30 Page 31 Page 32 Page 33 Page 34 Page 35 Page 36 Page 37 Page 38 Page 39 Page 40 Page 41 Page 42 Page 43 Page 44 Page 45 Page 46 Page 47 Page 48 Page 49 Page 50 Page 51 Page 52 Page 53 Page 54 Page 55 Page 56 Page 57 Page 58 Page 59 Page 60 Page 61 Page 62 Page 63 Page 64 Page 65 Page 66 Page 67 Page 68 Page 69 Page 70 Page 71 Page 72 Page 73 Page 74 Page 75 Page 7660 IREC Farmers' Newsletter No. 195 ­ – Rice R&D 2016 manual visual assessment was slightly more accurate than the automated method. This might be a function of having just the one operator doing manual Hanasaki in this instance, which would be highly unlikely in a commercial setting. Although the automatic method is less accurate it is much quicker — once the images are acquired they can be processed without any human input, which saves time and salary. An example image processed through the analysis software is shown in Figure 2, labelled for cracked and non-cracked grains. The procedure also outputs the numbers of cracked grains. In this experiment, the manual Hanasaki required approximately 50 hours of a technician’s time in counting fissured grain. Although requiring the same preparation time, automatic analysis didn’t require any human input once the analysis procedure was started (about five minutes). Where to from here? The methodologies developed here will be routinely used in the quality evaluation program of the Australian Rice Partnership II to extend the knowledge on future varieties and their cracking potential in storage. These same techniques can also follow water absorption with time (Figure 3) of cracked and non-cracked grain, as surface fissures can actually be beneficial since l Figure 2. Example image of the automatic image analysis script. The original image of 100 grains soaking in water in a plastic petri dish has been overlaid with colours that indicate grains without cracks or with small cracks (blue) and cracked grains (yellow) with identified cracks (green). Not all grains are counted due to difficulties with grains touching the edge of the plate and separating some touching grains. Grains that are already broken are not counted (there are none in this image).