APPLICATION OF MACHINE VISION FOR DETECTION OF FOREIGN MATTER IN WHEAT GRAINS | ||||
| Arab Universities Journal of Agricultural Sciences | ||||
| Article 4, Volume 16, Issue 2, September 2008, Page 275-284 PDF (754.13 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ajs.2008.14692 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
| G.K Arafa; Elbatawi I.E. | ||||
| Agricultural Engineering Research Institute, P.O. Box 256, Nadi Elsaid St., Dokki, Giza, Egypt | ||||
| Abstract | ||||
| With the level of automation at every level of food production and the rates at which food is be-ing produced, it is becoming increasingly more important to have systems that can automatically detect foreign matter along the way. The color scheme could make a computer vision system very practical for foreign object detection and removal. Research at laboratory levels has demonstrated that machine vision is an effective method for clas-sification of cereal grains like wheat. Robust ma-chine vision algorithms have been developed and tested to extract morphological, color and textural features of wheat grains and dockage content. The samples used in this study were bulk images of Egyptian wheat (Sakha8) mixed with known quan-tities of barley, rice and stones (0.5%, 1.0%, 2.0% and 5%). Back propagation neural network (BPNN) and statistical classifiers were used for classifica-tion. Results of the study indicate that classification was reduced from about 97% for wheat mixed with stones to 96% for wheat mixed with rice and 93% for wheat mixed with barley (at 5.0% admix-ture).This trend indicates that the features of 1.0% foreign matter admixture started overlapping with other classes (of admixture). On the other hand, 94%, 95% and 97% of 5% barley, rice and stones admixtures (with wheat) were accurately classified using neural network classifier. Using machine vision system, the detection rate for foreign matter in otherwise clean wheat was 100% with no false positives. This detection scheme was based on a linear feature detector incorporating two orthogonal masks. | ||||
| Keywords | ||||
| Machine vision; Neural network; For-eign matter; detection; Wheat | ||||
|
Supplementary Files
|
||||
|
Statistics Article View: 296 PDF Download: 368 |
||||
