Image Analysis of Foods

Starch granule size and shape characterization of yam (Dioscorea alata L.) flour using automated image analysis

BACKGROUND

Roots, tubers and bananas (RTB) play an essential role as staple foods, particularly in Africa. Consumer acceptance for RTB products relies strongly on the functional properties of, which may be affected by the size and shape of its granules. Classically, these are characterized either using manual measurements on microscopic photographs of starch colored with iodine, or using a laser light-scattering granulometer (LLSG). While the former is tedious and only allows the analysis of a small number of granules, the latter only provides limited information on the shape of the starch granule.

RESULTS

In this study, an open-source solution was developed allowing the automated measurement of the characteristic parameters of the size and shape of yam starch granules by applying thresholding and object identification on microscopic photographs. A random forest (RF) model was used to predict the starch granule shape class. This analysis pipeline was successfully applied to a yam diversity panel of 47 genotypes, leading to the characterization of more than 205 000 starch granules. Comparison between the classical and automated method shows a very strong correlation (R2 = 0.99) and an absence of bias for granule size. The RF model predicted shape class with an accuracy of 83%. With heritability equal to 0.85, the median projected area of the granules varied from 381 to 1115 μm2 and their observed shapes were ellipsoidal, polyhedral, round and triangular.

CONCLUSION

The results obtained in this study show that the proposed open-source pipeline offers an accurate, robust and discriminating solution for medium-throughput phenotyping of yam starch granule size distribution and shape classification. © 2023 The Authors. Journal of The Science of Food and Agriculture published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.

Use of ImageJ Software for Assessment of Mechanical Damage to Starch Granules

This study attempted to assess the influence of mechanical forces on potato, tapioca, wheat, rice, and maize starch granules. For this purpose, we used digital analysis of microscopic images of starch granules before and after starch grinding using ImageJ software. Additionally, we studied the influence of temperature on the size and shape of starch granules by drying the starches for 30 min at 60 °C. Our results indicate that mechanical forces very rarely cause damage to starch granules, such as breaking or cracking. In most cases, the action of mechanical forces results only in smoother shape of starch granules and their shrinking, linked with rising temperature. Results of this study show that ImageJ software can be successfully used to assess starch granule size and shape.

Assessment of dairy products stability by physicochemical and spectroscopic analyses and digital images

Abstract The oxidative action of chemical substances present in dairy products may contribute to the darkening of the product. Product color is one of the first factors to be considered by the consumer for acceptance or rejection. In the food industry, the color parameter is measured using colorimeters and spectrophotometers; nevertheless, the use of digital images for colorimetric tests has been surveyed in the food area. Therefore, the present work aimed at investigating for 45 days the chemical, physicochemical and colorimetric alterations of creamy dairy dessert with white chocolate flavor and strawberry-flavored yogurt. These alterations were monitored by the analysis of the parameters pH, acidity, soluble solids content, in addition to spectroscopy in the middle-infrared region and digital images. The data collected were processed in a computational environment applying chemometric tools. As result, it was verified that there were alterations in the parameters evaluated; nonetheless, the acidity of the dairy dessert remained constant during the storage period. From the Principal Component Analysis (PCA) using the color variables, it was observed that the samples were grouped and separated by type and storage time in agreement with the visually observed colorimetric modifications.

Use of image analysis to identify woody breast characteristics in 8-week-old broiler carcasses

Woody breast (WB) condition causes significant economic losses to the global poultry industry, and the lack of an objective and fast tool to identify this myopathy is a contributing factor. The aim of this study was to determine if there are broiler carcass conformation changes that can be used to identify WB characteristics using image analysis. Images of 8-wk-old male broiler carcasses (n = 544) of high breast-yielding strains were captured before evisceration, which were processed and analyzed using ImageJ software. Measurements were as follows: M0, breast length; M1, breast width in the cranial region; M2, one-fifth of the breast length starting at the tip of keel; M3, breast width at the end of M2; M4, angle formed at the tip of keel and extending to outer points of M3; M5, area of the triangle formed by M3 and lines generated by M4; M6, area of the breast above M3; and M7, M6 minus M5. Ratios of these measurements were also considered. Whole breast fillets were scored for WB severity based on tactile assessment and compression analysis to correlate them. Spearman's correlation coefficient (r_s) between WB scores and compression force was highly significant (r_s = 0.83, P < 0.01). Measurements M4 and M3 as well as ratios M9 (M3/M2) and M11 (M1/M0) had the highest correlation to the WB score (r_s ≥ 0.70; P < 0.01) and compression force (r_s ≥ 0.64; P < 0.01). The best validated model (generalized [Gen.] R² = 0.60) to predict WB included M1, M2, and M3. Using this model, 84% of broiler carcasses were correctly classified as WB or normal with a sensitivity of 82% to detect affected samples. Alternatively, M4 and M6 as well as ratios M9 and M11 could be considered as predictors in different models (Gen. R² ≥ 0.56). The same predictors were significant to estimate compression force (Gen. R² ≥ 0.49). These data support the use of image analysis to predict WB condition in broiler carcasses. The potential integration of these image measurements into commercial in-line vision grading systems would allow processors to sort broiler carcasses by WB severity.

Latest advances in imaging techniques for characterizing soft, multiphasic food materials

Over the last two decades, the development and production of innovative, customer-tailored food products with enhanced health benefits have seen major advances. However, the manufacture of edible materials with tuned physical and organoleptic properties requires a good knowledge of food microstructure and its relationship to the macroscopic properties of the final food product. Food products are complex materials, often consisting of multiple phases. Furthermore, each phase usually contains a variety of biological macromolecules, such as carbohydrates, proteins and lipids, as well as water droplets and gas bubbles. Micronutrients, such as vitamins and minerals, might also play an important role in determining and engineering food microstructure. Considering this complexity, highly advanced physio-chemical techniques are required for characterizing the microstructure of food systems prior to, during and after processing. Fast, in situ techniques are also essential for industrial applications. Due to the wide variety of instruments and methods, the scope of this paper is focused only on the latest advances of selected food characterization techniques, with emphasis on soft, multi-phasic food materials.

Online Feature Selection for Robust Classification of the Microbiological Quality of Traditional Vanilla Cream by Means of Multispectral Imaging

The performance of an Unsupervised Online feature Selection (UOS) algorithm was investigated for the selection of training features of multispectral images acquired from a dairy product (vanilla cream) stored under isothermal conditions. The selected features were further used as input in a support vector machine (SVM) model with linear kernel for the determination of the microbiological quality of vanilla cream. Model training (n = 65) was based on two batches of cream samples provided directly by the manufacturer and stored at different isothermal conditions (4, 8, 12, and 15 °C), whereas model testing (n = 132) and validation (n = 48) were based on real life conditions by analyzing samples from different retail outlets as well as expired samples from the market. Qualitative analysis was performed for the discrimination of cream samples in two microbiological quality classes based on the values of total viable counts [TVC ≤ 2.0 log CFU/g (fresh samples) and TVC ≥ 6.0 log CFU/g (spoiled samples)]. Results exhibited good performance with an overall accuracy of classification for the two classes of 91.7% for model validation. Further on, the model was extended to include the samples in the TVC range 2-6 log CFU/g, using 1 log step to define the microbiological quality of classes in order to assess the potential of the model to estimate increasing microbial populations. Results demonstrated that high rates of correct classification could be obtained in the range of 2-5 log CFU/g, whereas the percentage of erroneous classification increased in the TVC class (5,6) that was close to the spoilage level of the product. Overall, the results of this study demonstrated that the UOS algorithm in tandem with spectral data acquired from multispectral imaging could be a promising method for real-time assessment of the microbiological quality of vanilla cream samples.