Detection of starch in minced chicken meat based on hyperspectral imaging technique and transfer learning

Abstract

In order to the quickly and nondestructively detect whether starch is adulterated in minced chicken meat, a novel method combining hyperspectral imaging (HSI) technique with transfer learning was proposed in this study. First of all, hyperspectral images of minced chicken meat with different mass fractions of starch were collected and spectral information of the samples in the range of 400.89-1000.19 nm was extracted. Then, the hyperspectral data was preprocessed via continuous wavelet transform (CWT), which transformed the pixel-level hyperspectral data into twodimensional spectrograms. Furthermore, classification model for identifying starch in minced chicken meat was constructed based on the GoogLeNet network pretrained on ImageNet data set. Finally, the support vector machine (SVM) model and the convolutional neural network (CNN) model without transfer learning were established for comparison. The results indicated that the model based on GoogLeNet network had a higher classification accuracy, up to 98.6%. Therefore, this study demonstrates the feasibility of the detection of starch in minced chicken meat based on HSI technique and transfer learning.Practical applications: The identification of starch in the minced chicken meat is of particular significance for maintaining the market order and safeguarding the human health. An innovative method based on hyperspectral imaging technique and transfer learning to identify whether the minced chicken meat mixed with starch was proposed in this study. The method achieved quickly, nondestructively and accurately detection of starch in minced chicken meat.

A Literature Review on the Quality Evaluation of Soybeans Using Electronic Nose

“…The results of this investigation revealed a substantial decrease (P< 0.05) in the moisture content of all treated soybean samples, with roasting at 230 °C for 30 minutes yielding the lowest value of 2.18% [13]. Moreover, the e-nose has an ability to identify 11 volatile chemicals in Korean soybean, while the e-tongue assesses the intensity of 5 basic tastes [42]. Through the used of the principal component analysis, the contribution rates of the first and second principal components detected by electronic nose and tongue for minced chicken meat adulterated with soy protein were 99.2% and 0.6%, respectively, and the total contribution rate was 99.8% leading to the result that the combination of electronic nose and electronic tongue sensors has the potential to distinguish and predict soy protein-based or starch-based adulteration in minced chicken meat, and it has also been demonstrated to be a useful identification method for meat contamination detection with high efficiency and accuracy [43].…”

A Literature Review On The Quality Evaluation Of Soybeans Using Electronic Nose

“…Moreover, the e-nose has an ability to identify 11 volatile chemicals in Korean soybean, while the e-tongue assesses the intensity of 5 basic tastes [42]. Through the used of the principal component analysis, the contribution rates of the first and second principal components detected by electronic nose and tongue for minced chicken meat adulterated with soy protein were 99.2% and 0.6%, respectively, and the total contribution rate was 99.8% leading to the result that the combination of electronic nose and electronic tongue sensors has the potential to distinguish and predict soy protein-based or starch-based adulteration in minced chicken meat, and it has also been demonstrated to be a useful identification method for meat contamination detection with high efficiency and accuracy [43]. Hence, this device can be utilized in breeding as a fast screening tool programs, in the selection of soybean mutants/varieties with varying volatile profiles, as well as in the mapping of the QTLs and loci responsible for these features.…”

“…The findings confirm that integrating LRCNN with the e-nose effectively identifies gas information associated with soybeans from various growing areas, presenting a promising new method for soybean quality traceability. Another study where the electronic nose is coupled with an effective deep learning method is a study where they introduce the adaptive convolutional kernel channel attention network (AKCA-Net) coupled with an electronic nose (enose) to establish traceability in soybean quality [43]. The e-nose system is initially employed to gather gas information from soybeans of various origins.…”

Freshness prediction of modified atmosphere packaging lamb meat based on digital images from mobile portable devices

“…Currently, the detection of meat product freshness typically involves the use of traditional physical and chemical methods (Elisseeva et al, 2020; Li et al, 2017; Li & Wang, 2021), odor sensor technology (Li et al, 2022; Liu & Fang, 2019), electronic nose technology (Huang & Gu, 2022; Li et al, 2023; Liu et al, 2022; Wakhid et al, 2022), near‐infrared (NIR) technology (He et al, 2019; Lam et al, 2020; Zhang et al, 2022), hyperspectral imaging (HSI) technology (Shi et al, 2022; Yang et al, 2023; Zhuang et al, 2022), and other techniques. In terms of meat quality detection, Dong et al (2023) employed hyperspectral technology to establish a regression model based on full‐spectrum and characteristic wavelengths, and found that the partial least squares regression model exhibited the best predictive performance.…”