Search BYU 
Contact | Help
BYU - Electrical and Computer Engineering

Robotic Vision Lab

Research Lab

Department of Electrical and Computer Engineering
Room 430 CB
Provo, Utah 84602
Tel: 1 + 801-422-4119

MainRobotic VisionMachine VisionMedical ImagingClass Projects
Machine Vision Applications
news imageECO Features
A majority of consumers list flavor, unbruised and umblemished, and crispness as being the most important characteristics of apples. Considering the huge annual production and the fresh fruit consumer demand for crisp unblemished apples, it is required to create reliable automatic inspection processes to identify bruises and blemishes before allowing products to be sent to the fresh fruit market. Relevant research shows that distinguishing stem end and calyx from true defects is the main challenge for automatic apple blemish detection systems. Previous research methods for automated calyx and stem end classification have depended on a human expert to design the features the identification algorithm uses. We used our Evolution-COnstructed (ECO) features to automatically find features that are then used by Adaboost to correctly distinguish bruises and blemishes from the stem end and calyx of apples. We have also used this newly developed ECO Features to recognize and remove invasive fish species, detect human for surveillance applications, and evaluate quality of oyster and shrimp.
news imageColor Quality Analysis
Color grading is a crucial step in the processing of fruits and vegetables that directly affects profitability, because the quality of agricultural products is often associated with their color. We developed an effective and user-friendly color mapping concept for automated color grading that is well suited for commercial production. This color mapping method uses preselected colors of interest specific to a given application to calculate a unique set of coefficients for color space conversion. The three-dimensional RGB color space is converted into a small set of color indices unique to the application. In contrast with more complex color grading techniques, our method makes it easy for a human operator to specify and adjust color-preference settings. We used this method to determine the maturity level of tomatoes and dates.
news imageTurn Angle Distribution Analysis
Shape information can be used for object classification, recognition, and shape evaluation. Using shape information, we have been able to recognize fish species, detect human intrusion, and grade oyster shape quality. Measurements of the abundance, distribution, and movement of fish are critical to fishery management. On rivers in the western United States, migrating fish frequently encounter a variety of man-made barriers, including hydroelectric and diversion dams and associated reservoirs. The detrimental impact on fish stocks are substantial. Out FishID system helps monitoring fish migration patterns and measuring abundance. We have used the same shape analysis technique for oyster shell quality evaluation. We measure oyster size and separate shape quality into good, broken, banana, irregular shapes.
Maintained by The ECEn Web Team. Based on v. 3.8 of the ECEn web templates (view XML, see other formats).
Copyright 1994-2005. Brigham Young University. All Rights Reserved.