Author
 |
Pearson, Thomas |
|
Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal Publication Acceptance Date: 6/12/2009 Publication Date: 11/1/2009 Citation: Pearson, T.C. 2009. Hardware-based image processing for high-speed inspection of grains. Computers and Electronics in Agriculture. 69(1):12-18. Interpretive Summary: Electronic color sorters are widely used on many commodities to remove discolored and defective product. These systems are robust and can have high throughputs, as much as 2000 lb/hr of wheat can be processed in these machines. However, there are many defects, or attributes, that these color sorters cannot detect with necessary accuracy. This study resulted in the development of a prototype that enables sorting of many defects and attributes that current color sorters cannot is currently detect. The new system combines imaging technologies with advanced image sensors and processing hardware. Even though the system is more accurate than traditional electronic color sorters, the cost and throughput should be similar. The developed system was tested for its ability to separate red and white wheat and popcorn with blue-eye damage. The new, image based system was 10 to 20% more accurate than commercial color sorters for separating red and white wheat. For popcorn with blue-eye damage, the system had an overall accuracy of 83% whereas color sorters cannot detect this defect at all. The system should find uses for a variety of crops such as for separating fungal damaged grain, mottled durum, and various defects found in tree nuts. This will lead to higher quality and safer food products and possibly open international markets where quality is a key factor. Technical Abstract: A high-speed, low-cost, image-based sorting device was developed to detect and separate grains with slight color differences and small defects on grains The device directly combines a complementary metal–oxide–semiconductor (CMOS) color image sensor with a field-programmable gate array (FPGA) which was programmed to execute image processing in real-time, without the need of an external computer. Spatial resolution of the imaging system is approximately 16 pixels/mm. The system includes three image sensor/FPGA combinations placed around the perimeter of a single-file stream of kernels, so that the entire surface of each kernel can be inspected. A vibratory feeder was used to feed kernels into an inclined chute that kernels slide down in a single-file manner. Kernels are imaged immediately after dropping off the end of the chute and are diverted by activating an air valve. The system has a throughput rate of approximately 75 kernels/s per channel which is much higher than previously developed image inspection systems. This throughput rate corresponds to an inspection rate of approximately 8kg/hr of wheat and 40Kg/hr of popcorn. The system was initially developed to separate white wheat from red wheat, and to remove popcorn having blue-eye damage, which is indicated by a small blue discoloration in the germ of a popcorn kernel. Testing of the system resulted in accuracies of 88% for red wheat and 91% for white wheat. For popcorn, the system achieved 74% accuracy when removing popcorn with blue-eye damage and 91% accuracy at recognizing good popcorn. The sorter should find uses for removing other defects found in grain, such as insect-damaged grain, scab-damaged wheat, and bunted wheat. Parts for the system cost less than $2000, so it may be economical to run several systems in parallel to keep up with processing plant rates. |
