Generally in rice mills, due to unavailability of continuous on-line measurement methods, quality rice grader of product is monitored visually by experienced operators at 1–2 h intervals (Yadav and Jindal 2007). This means that the operator, based on his experience and proficiency with the processing machinery, assesses the quality grade of the product by mere visual inspection of the machine output and making the required adjustments. Most of the time, this operation is neither carried out with enough accuracy nor performed in a short time. In this regard, development of automated systems which can work based on the operators’ expertise may be an efficacious method for fast and reliable quality grading of the product.
Sansomboonsuk and Afzulpurkar (2006) developed shrinkage algorithms to extract features of rice kernels in two forms of point and line touching kernels. Area, perimeter, circularity and shape compactness were used as criteria for classifying the broken rice and long grain rice. Fuzzy logic method was used to organize and classify the kernels. From the experiments, it was found that the algorithms perform satisfactorily in evaluating the percentage of broken rice with overall accuracy of 92 %. The time required by automated counting and measuring compared to manual counting and measuring was 70 % less. However, the required time (approximately 1 min) may not be suitable for real-time processing operations.
The rice destoner has the efficiency of 80% and mass flow rate of 2.10 kg/s which is equivalent to 7.50t/hr capacity. The design of the destoner was carried out economically. A machine of this nature can be manufactured for small entrepreneurs and rural level applications in the developing countries, due to its low cost of and easy production and maintenance, where rice is locally produced for better quality and quantity.