Artificial Intelligence Empowered Multispectral Vision Based System for Non-Contact Monitoring of Large Yellow Croaker (Larimichthys crocea) Fillets

Abstract

A non-contact method was proposed to monitor the freshness (based on TVB-N and TBA values) of large yellow croaker fillets (Larimichthys crocea) by using a visible and near-infrared hyperspectral imaging system (400–1000 nm). In this work, the quantitative calibration models were built by using feed-forward neural networks (FNN) and partial least squares regression (PLSR). In addition, it was established that using a regression coefficient on the data can be further compressed by selecting optimal wavelengths (35 for TVB-N and 18 for TBA). The results validated that FNN has higher prediction accuracies than PLSR for both cases using full and selected reflectance spectra. Moreover, our FNN based model has showcased excellent performance even with selected reflectance spectra with rp = 0.978, R2p = 0.981, and RMSEP = 2.292 for TVB-N, and rp = 0.957, R2p = 0.916, and RMSEP = 0.341 for TBA, respectively. This optimal FNN model was then utilized for pixel-wise visualization maps of TVB-N and TBA contents in fillets.

Towards the development of foods 3D printer: Trends and technologies for foods printing

“…For fish, AI models like Support Vector Machine (SVM) and CNN predict quality using Total Viable Counts (TVC) from images, achieving over 86 % accuracy [ 156 ]. Additionally, Partial Least Squares Regression (PLSR) and Feed-forward Neural Networks (FNN) determine fish freshness by analyzing TVB-N and TBA with visible and NIR images [ 157 ]. In frozen foods, Back-propagation ANN (BP-ANN) assesses quality based on drip loss and texture parameters using NIR spectroscopy [ 158 ].…”

Freshness prediction method of large yellow croaker based on Internet of Things and neural network

“…In the study of aquatic product freshness, some scholars have utilized hyperspectral technology combined with TVB-N to predict the freshness of aquatic products [3] . Wang et al utilized a hyperspectral imaging system based on TVB-N and TBA values to monitor the freshness of large yellow croaker fillets, demonstrating higher reliability [4] .Cheng et al developed a multispectral imaging method and used a neural network model to simultaneously predict the TVB-N, TBARS, and K value indicators for detecting the freshness of grass carp fillets [5] .…”

A Combination of Near-Infrared Hyperspectral Imaging with Two-Dimensional Correlation Analysis for Monitoring the Content of Alanine in Beef

“…In previous investigations, the combination of several nondestructive rapid measurement methods and chemometric methods have been applied in the assessment of amino acid content, including visible near–infrared spectroscopy, near–infrared (NIR) spectroscopy, Fourier infrared spectroscopy, and nondestructive magnetic resonance imaging [ 11 , 12 , 13 , 14 ]. However, these studies mainly focused on the evaluation of research objectives concerning soybean, daqu, tea, potato, and ham [ 11 , 12 , 13 , 14 , 15 ], and detection indicators such as amino acid nitrogen [ 12 ], total amino acid [ 15 ], and total volatile basic nitrogen (TVB-N) have been emphatically discussed [ 16 ]. In addition, hyperspectral imaging (HSI) technology is more widely focused in predicting other meat-related quality attributes, especially nutritional attributes (fatty acid, protein, and intramuscular fat), technical attributes (pH and water holding capacity), sensory attributes (tenderness, color, hardness, gumminess, and chewiness), freshness attributes (thiobarbituric acid reactive substances (TBARS), total biogenic amines (TBA), and myoglobin), and microbial attributes (total viable count) of meat in different parts, types, and places of origin [ 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ].…”