IMAGE ANALYSIS TECHNIQUES FOR EVALUATION OF SUGAR CRYSTALS SIZE DISTRIBUTION

Abstract

Sugar crystal size distribution is an important prerequisite to evaluate the quality of the product. The digital image processing (DIP) was used to determine the size of the raw sugar crystals (SC) by using a camera together with microscope. Crystal size distribution, including mean aperture (MA) and coefficient of variation (CV) were used to determine the quality of crystals. The images were captured by digital camera connected to the microscope using reflected light of microscope. Three algorithms (distance transformation, ultimate erosion and foreground and background) ware developed to segment the crystals which are touching each other's and overlapping individual. The results obtained using these algorithms were compared with each other and with a manually clicked measurement. Totally 30 dry sugar samples were taken from Metehara sugar factory, every sample of the image frame contains approximately 70 individual grains. The size of the crystals was calculated with the percentage of error within 13%. The mean aperture of the crystals was measured by a percentage error 12.85%, 4.03% and 5.64% for foreground and background (FB), ultimate erosion (UE) and distance transform (DT) respectively. The mechanical sieving technique compared with manual clicking gave percentage errors of 6.069% and 27.12% for MA and CV respectively. The imaging technique is faster, more reliable than sieving and can be used to measure the full crystal size distributions of sugar crystals.