Dual-wavelength filtering for the detection of blood-spotted eggs
This study developed an image-based dual-wavelength filter method for detecting blood-spotted white-shelled eggs based on transmission spectral analysis. The spectral results identified a pronounced absorption feature near 580 nm in blood-spotted eggs. Accordingly, 580 nm was selected as the blood-sensitive wavelength and 630 nm as the reference wavelength, and the dual-wavelength image intensity ratio was used for detection. Binary logistic regression models were constructed for both the image-based dual-wavelength filter method and the transmission spectroscopy method. The models were evaluated using artificially prepared blood-spotted white-shelled egg samples containing 0.025 and 0.05 mL of blood, together with commercially sourced blood-spotted white-shelled eggs. The retrained image-based dual-wavelength method achieved 84.9% overall accuracy and 83.8% sensitivity for the commercially sourced samples. These results indicate that the proposed method has potential for nondestructive screening of blood-spotted white-shelled eggs under static laboratory conditions.
Authors
- Chien‐Chung Jeng (ORCID: https://orcid.org/0000-0003-2047-4767)
- Cheng-Han Li (ORCID: https://orcid.org/0000-0002-1095-1593)
- Ming‐Kun Hsieh
- Chi-Yu Chen
Institutions
- National Taichung University of Science and Technology (TW)
- National Chung Hsing University (TW)
Publication Details
- Journal
- Journal of Food Measurement & Characterization
- Published
- 2026-08-14
- DOI
- https://doi.org/10.1007/s11694-026-04824-7
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Chung-Hsing University