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

Abstract

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.

Spectroscopic approaches for non-destructive shell egg quality and freshness evaluation: Opportunities and challenges

“…Different factors can affect HSI results, such as the incident light angle and the number of wavelengths. Dai et al (2020) studied the influence of incident angles on the accuracy of egg HU prediction. Evaluating 350 eggs, and considering scattering, transmission, and mixed hyperspectral images, they found that the accuracy was higher (up to 100%) with scattering images and inversely proportional to the incident angle.…”

Current advances in detection of abnormal egg: a review

“…The optimal conditions of the egg freshness assessment model were investigated by using different types of hyperspectral images of eggs [ 15 ]. The reflection, scattering, transmission, and mixed hyperspectral images of eggs were acquired using a dual hyperspectral camera, and the incident angle of the light source to irradiate eggs was increased from 0° (for scattering hyperspectral image) to 60° (for mixed hyperspectral image) with an increment of 10°.…”

“…HSI techniques are useful to detect stale eggs by predicting the freshness of eggs [13][14][15]. Hyperspectral imaging was used to examine internal quality (freshness, air bubbles, and scattered yolks) of eggs [13].…”

“…Among the numerous statistical-based data analysis models and machine learning models, it is important to use the right model. Currently, studies on performance verification of various learning models are being conducted to develop an optimized egg detection algorithm [ 15 , 19 , 20 ].…”

“…Studies to develop abnormal egg detection technology using a modified pressure technology [9][10][11][12] and hyperspectral imaging technology [13][14][15][16] have also been conducted in addition to the currently commercialized technology. All techniques for detecting defective eggs are non-destructive and require a defective egg identification algorithm.…”