Research Output
   

Intelligent Decision Support Systems

› French Fry

› Oat Kernal
 
Sensor Sensing Systems

› Quality of Beans

› Sunflower

› Wheat Protein

› Bacterial Contamination in Packaged Food

Quality Evaluation of Edible Beans

A sensing system was developed to evaluate the quality of beans. Some of the main characters of the system were to be able to detect.

  • Color difference
  • Cracks
  • Foreign objects
  • Broken beans
 
Crack Detection Techniques
 

Dyed bean with normal crack

Fluorescent bean image normal crack
Normal cracks and laser line shapes
Laser images for haivline cracks
 
Results
  • Overall accuracy of 94% for fluorescent techniques as compared to 71% obtained for dyed beans using conventional light imaging
  • Laser system provided 98% accuracy in detecting cracks
 
Color Image Segmentation of Edible Beans
 
Objective: To efficiently detect bean (acceptable, broken, small and damaged), highly undesirable foreign materials, and stones in a white background.
 
Results
A Kohonen layer of size 32x32 with a "rectangular" topology and a "bubble" neighborhood function, an average of 99.31% of the pixels of the six groups were correctly binarized. The spatial thresholding segmentation procedure provided an average PCMP (percentage of correctly matched pixels) of only 89.71%.
 
The Bioimaging and Sensing Center is a multi-disciplinary research facility in the College of Agriculture, Food Systems and Natural Resources at North Dakota State University, Fargo ND.
© 2009 Bioimaging and Sensing Center. All Rights Reserved.
NDSU Homepage