Egg Freshness Evaluation Using Transmission and Reflection of NIR Spectroscopy Coupled Multivariate Analysis

This work presents a novel work for the detection of the freshness of eggs stored at room temperature and refrigerated conditions by the near-infrared (NIR) spectroscopy and multivariate models. The NIR spectroscopy of diffuse transmission and reflection modes was used to compare the quantitative and qualitative investigation of egg freshness. It was found that diffuse transmission is more conducive to the judgment of egg freshness. The linear discriminant analysis model (LDA) for pattern recognition based on the diffuse transmission measurement was employed to analyze egg freshness during storage. NIR diffuse transmission spectroscopy showed great potential for egg storage time discrimination in normal atmospheric conditions. The LDA model discrimination rated up to 91.4% in the prediction set, while only 25.6% of samples were correctly discriminated among eggs in refrigerated storage conditions. Furthermore, NIR spectra, combined with the synergy interval partial least squares (Si-PLS) model, showed excellent ability in egg physical index prediction under normal atmospheric conditions. The root means square error of prediction (RMSEP) values of Haugh unit, yolk index, and weight loss from predictive Si-PLS models were 4.25, 0.031, and 0.005432, respectively.

The grades and freshness assessment of eggs based on density detection using machine vision and weighing sensor

The water displacement and flotation are two of the most accurate and rapid methods for grading and assessing freshness of agricultural products based on density determination. However, these techniques are still not suitable for use in agricultural inspections of products such as eggs that absorb water which can be considered intrusive or destructive and can affect the result of measurements. Here we present a novel proposal for a method of non-destructive, non-invasive, low cost, simple and real—time monitoring of the grading and freshness assessment of eggs based on density detection using machine vision and a weighing sensor. This is the first proposal that divides egg freshness into intervals through density measurements. The machine vision system was developed for the measurement of external physical characteristics (length and breadth) of eggs for evaluating their volume. The weighing system was developed for the measurement of the weight of the egg. Egg weight and volume were used to calculate density for grading and egg freshness assessment. The proposed system could measure the weight, volume and density with an accuracy of 99.88%, 98.26% and 99.02%, respectively. The results showed that the weight and freshness of eggs stored at room temperature decreased with storage time. The relationship between density and percentage of freshness was linear for the all sizes of eggs, the coefficient of determination (R2) of 0.9982, 0.9999, 0.9996, 0.9996 and 0.9994 for classified egg size classified 0, 1, 2, 3 and 4, respectively. This study shows that egg freshness can be determined through density without using water to test for water displacement or egg flotation which has future potential as a measuring system important for the poultry industry.

Development of predictive models for eggs freshness and shelf-life under different storage temperatures

The objective of the present study was to develop models for egg freshness and shelf-life predictions for the selected evaluation indicators including egg weight, Haugh unit (HU), and albumen height. Experiments were carried out at different storage temperatures for a total period of 29 – 32 days. All data were collected and fitted in to Arrhenius equation for egg freshness, while the HU data were applied to probability model for the shelf-life prediction. The results showed that egg weight, albumen height and HU decreased significantly, and albumen pH increased with the extension of storage time. The higher the storage temperature was, the faster the egg quality decreased. In addition, the bias factor ( Bf ), accuracy factor ( Af ) and the standard error of prediction ( %SEP ) were selected to verify the developed quality models. Maximum rescaled R-square statistic, the Hosmer-Lemeshow goodness-of-fit statistic, and the receiver operating characteristic (ROC) curve were used to evaluate the goodness-of-fit of the developed probability model for the shelf-life of eggs, which indicated that the presented predictive models can be used to assess egg freshness and predict shelf-life during different storage temperatures.

Rapid and Nondestructive Determination of Egg Freshness Category and Marked Date of Lay using Spectral Fingerprint

The potential of nondestructive prediction of egg freshness based on near-infrared (NIR) spectra fingerprints would be beneficial to quality control officers and consumers alike. In this study, handheld NIR spectrometer in the range of 740 nm to 1070 nm and chemometrics were used to simultaneously determine egg freshness based on marked date of lay for eggs stored under cold and ambient conditions. The spectra acquired from the eggs were preprocessed using multiplicative scatter correction and principal component analysis (MSC-PCA). Linear discriminant analysis (LDA) was used to build identification model to predict the category of freshness, while partial least square regression (PLS-R) was used to determine the marked date of lay. The performance of LDA model was above 95% identification rate in both calibration and prediction set for the eggs stored under ambient and cold storage. For eggs stored in ambient storage, LDA had 95.54% identification rate at 5 principal components, while at cold storage LDA has 100% identification rate at 5 principal components for determining the marked date of lay, and partial least square regression (PLS-R) gave R = 0.87 and RMSEI = 2.57 for ambient storage and R = 0.88 and RMSEI = 2.66 for cold storage in independent set, respectively. The results show that handheld spectrometer and multivariate analysis could be used for rapid and nondestructive measurement of egg freshness. This provides a novel solution for egg integrity prediction along the value chain.

Nondestructive Detection for Egg Freshness Based on Hyperspectral Scattering Image Combined with Ensemble Learning

Scattering hyperspectral technology is a nondestructive testing method with many advantages. Here, we propose a method to improve the accuracy of egg freshness, research the influence of incident angles of light source on the accuracy, and explain its mechanism. A variety of weak classifiers classify eggs based on the spectra after preprocessing and feature wavelength extraction to obtain three classifiers with the highest accuracy. The three classifiers are used as metamodels of stacking ensemble learning to improve the highest accuracy from 96.25% to 100%. Moreover, the highest accuracy of scattering, reflection, transmission, and mixed hyperspectral of eggs are 100.00%, 88.75%, 95.00%, and 96.25%, respectively, indicating that the scattering hyperspectral for egg freshness detection is better than that of the others. In addition, the accuracy is inversely proportional to the angle of incidence, i.e., the smaller the incident angle, the camera collects a larger proportion of scattering light, which contains more biochemical parameters of an egg than that of reflection and transmission. These results are very important for improving the accuracy of non-destructive testing and for selecting the incident angle of a light source, and they have potential applications for online non-destructive testing.