Applications of Electronic Nose, Electronic Eye and Electronic Tongue in Quality, Safety and Shelf Life of Meat and Meat Products: A Review

The quality and shelf life of meat and meat products are key factors that are usually evaluated by complex and laborious protocols and intricate sensory methods. Devices with attractive characteristics (fast reading, portability, and relatively low operational costs) that facilitate the measurement of meat and meat products characteristics are of great value. This review aims to provide an overview of the fundamentals of electronic nose (E-nose), eye (E-eye), and tongue (E-tongue), data preprocessing, chemometrics, the application in the evaluation of quality and shelf life of meat and meat products, and advantages and disadvantages related to these electronic systems. E-nose is the most versatile technology among all three electronic systems and comprises applications to distinguish the application of different preservation methods (chilling vs. frozen, for instance), processing conditions (especially temperature and time), detect adulteration (meat from different species), and the monitoring of shelf life. Emerging applications include the detection of pathogenic microorganisms using E-nose. E-tongue is another relevant technology to determine adulteration, processing conditions, and to monitor shelf life. Finally, E-eye has been providing accurate measuring of color evaluation and grade marbling levels in fresh meat. However, advances are necessary to obtain information that are more related to industrial conditions. Advances to include industrial scenarios (cut sorting in continuous processing, for instance) are of great value.

Computer Vision and Machine Learning for Tuna and Salmon Meat Classification

Aquatic products are popular among consumers, and their visual quality used to be detected manually for freshness assessment. This paper presents a solution to inspect tuna and salmon meat from digital images. The solution proposes hardware and a protocol for preprocessing images and extracting parameters from the RGB, HSV, HSI, and L*a*b* spaces of the collected images to generate the datasets. Experiments are performed using machine learning classification methods. We evaluated the AutoML models to classify the freshness levels of tuna and salmon samples through the metrics of: accuracy, receiver operating characteristic curve, precision, recall, f1-score, and confusion matrix (CM). The ensembles generated by AutoML, for both tuna and salmon, reached 100% in all metrics, noting that the method of inspection of fish freshness from image collection, through preprocessing and extraction/fitting of features showed exceptional results when datasets were subjected to the machine learning models. We emphasize how easy it is to use the proposed solution in different contexts. Computer vision and machine learning, as a nondestructive method, were viable for external quality detection of tuna and salmon meat products through its efficiency, objectiveness, consistency, and reliability due to the experiments’ high accuracy.

Prediction of Whole Pork Loin and Individual Chops’ Intramuscular Fat Using Computer Vision System Technology

The objective of this study was to compare different methods of evaluating intramuscular fat (IMF) in pork and test the accuracy of using a computer vision system (CVS) on different locations of the loin. Whole pork loins (n = 1,400) were obtained from 6 pork processing plants. Subjective marbling scores and CVS IMF percentage (CVS IMF%) were assessed on the ventral lean surface of the whole loin and the 3rd (A) and 10th (B) rib chops. Additionally, the A and B chops were evaluated for crude fat percentage (CF%) using ether extract. The CF% of the whole loin was represented by using the average CF% of A and B chops. A combination of the bootstrap method and stepwise regression models was used to increase prediction and robustness for CF% prediction. To better understand whether plants played an effect, models for individual plants and using all plants together were built, tested, and compared. Results were that subjective marbling score had stronger correlations with CF% compared to CVS IMF% for the whole loin (0.70 vs. 0.58), A chop (0.79 vs.0.62), and B chop (0.74 vs. 0.61). When using the stepwise regression models to predict CF%, B chop (71.8%) had the highest prediction accuracy (estimates within 0.5% residual compared to CF% were considered accurate) followed by A chop (58.1%) and whole loin (48.2%). When comparing individual plant models and overall models, the overall accuracy improved; however, this improvement in accuracy was not consistent through every single plant. In conclusion, CVS has shown potential to estimate pork IMF on all locations, especially the posterior pork chop.