Abstract

This study was carried out to use hyperspectral imaging technique for determining color (L*, a* and b*) and eggshell strength and identifying cracked chicken eggs. Partial least squares (PLS) models based on full and selected wavelengths suggested by regression coefficient (RC) method were established to predict the four parameters, respectively. Partial least squares-discriminant analysis (PLS-DA) and RC-partial least squares-discriminant analysis (RC-PLS-DA) models were applied to identify cracked eggs. PLS models performed well with the correlation coefficient (rp) of 0.788 for L*, 0.810 for a*, 0.766 for b* and 0.835 for eggshell strength. RC-PLS models also obtained the rp of 0.771 for L*, 0.806 for a*, 0.767 for b* and 0.841 for eggshell strength. The classification results were 97.06% in PLS-DA model and 88.24% in RC-PLS-DA model. It demonstrated that hyperspectral imaging technique has the potential to be used to detect color and eggshell strength values and identify cracked chicken eggs.

Highlights

  • This study was carried out to use hyperspectral imaging technique for determining color (L*, a* and b*) and eggshell strength and identifying cracked chicken eggs

  • Cracked eggs can cause economic loss in two ways, one is that they cannot be sold at a high price, another is cracked eggs may raise the risk of bacterial contamination to intact eggs, which can even produce food quality and safety problems[5,6,7]

  • This study investigated the determination of egg color and eggshell strength values and detection of cracked eggs using hyperspectral imaging technique

Read more

Summary

Introduction

This study was carried out to use hyperspectral imaging technique for determining color (L*, a* and b*) and eggshell strength and identifying cracked chicken eggs. The classification results were 97.06% in PLS-DA model and 88.24% in RC-PLS-DA model It demonstrated that hyperspectral imaging technique has the potential to be used to detect color and eggshell strength values and identify cracked chicken eggs. By studying spectral features at different wavelengths, it may be possible for color and eggshell strength determination and cracked eggs identification, which can be seen in many previous studies. This study investigated the determination of egg color and eggshell strength values and detection of cracked eggs using hyperspectral imaging technique. Eggshell strength values by using spectral information; (2) to select significant wavelengths for predicting color and eggshell strength values and (3) to develop a technique to classify intact and cracked eggs based on full and selected wavelengths, respectively

Objectives
Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.