ARS | Publication request: A hyperspectral imaging prototype for online quality evaluation of pickling cucumbers

Submitted to: Michigan State University Cucumber Reporting Session
Publication Type: Experiment Station
Publication Acceptance Date: January 9, 2008
Publication Date: January 10, 2008
Citation: Lu, R., Ariana, D. 2008. A hyperspectral imaging prototype for online quality evaluation of pickling cucumbers. Michigan State University Cucumber Reporting Session. p. 29-36.

Technical Abstract: A hyperspectral imaging prototype was developed for online evaluation of external and internal quality of pickling cucumbers. The prototype had several new, unique features including simultaneous reflectance and transmittance imaging and inline, real time calibration of hyperspectral images of each sample. Reflectance imaging in the visible region was intended for external quality evaluation (color and size), whereas transmittance imaging in the near infrared region was used for internal defect detection. Experiments performed on ‘Journey’ cucumbers in 2006 and 2007 showed that the new technique of simultaneous reflectance and transmittance imaging is advantageous over single sensing modes in achieving the goal of evaluating both external and internal quality of cucumbers. Algorithms were developed for predicting the surface quality characteristics and detecting internal defect of individual cucumbers. The prototype had good prediction of skin color, and its overall accuracy for internal defect detection was up to 99.0%. However, the prototype did not achieve an acceptable level of accuracy in firmness prediction. Further improvements in the hardware and software are needed, so that the prototype could provide faster and more accurate evaluation of individual cucumbers.