Using a Combination of Spectral and Textural Data to Measure Water-Holding Capacity in Fresh Chicken Breast Fillets

Abstract

The aim here was to explore the potential of visible and near-infrared (Vis/NIR) hyperspectral imaging (400-1000 nm) to classify fresh chicken breast fillets into different water-holding capacity (WHC) groups. Initially, the extracted spectra and image textural features, as well as the mixed data of the two, were used to develop partial least square-discriminant analysis (PLS-DA) classification models. Smoothing, a first derivative process, and principle component analysis (PCA) were carried out sequentially on the mean spectra of all samples to deal with baseline offsets and identify outlier data. Six samples located outside the confidence ellipses of 95% confidence level in the score plot were defined as outliers. A PLS-DA model based on the outlier-free spectra provided a correct classification rate (CCR) value of 78% in the prediction set. Then, seven optimal wavelengths selected using a successive projections algorithm (SPA) were used to develop a simplified PLS-DA model that obtained a slightly reduced CCR with a value of 73%. Moreover, the gray-level co-occurrence matrix (GLCM) was implemented on the first principle component image (with 98.13% of variance) of the hyperspectral image to extract textural features (contrast, correlation, energy, and homogeneity). The CCR of the model developed using textural variables was less optimistic with a value of 59%. Compared to results of models based on spectral or textural data individually, the performance of the model based on the mixed data of optimal spectral and textural features was the best with an improved CCR of 86%. The results showed that the spectral and textural data of hyperspectral images together can be integrated in order to measure and classify the WHC of fresh chicken breast fillets.

An Intelligent Detector for Sensing Pork Freshness In Situ Based on a Multispectral Technique

“…From Section 3.4 , it can be seen that most of the variables have poor discriminant results and belong to non-informative variables. An increase in non-informative variables reduces the predictive ability of the PLS-DA model [ 28 , 37 ]. Therefore, in order to obtain a concise and stable discriminative model, which is convenient for loading and using the handheld detection device, it is necessary to screen the spectral shape features.…”

“…To eliminate invalid variables, the most influential variables were selected from the PLS-DA model developed based on three spectral shape features (SR, SD, NSID). The weighted regression coefficient is considered to be the most sensitive indication of wavelength and accounts for most of the variation in the corresponding analysis [ 36 , 37 , 38 ].…”

Learning-Based Colorization of Grayscale Aerial Images Using Random Forest Regression

“…Consequently, statistical features are utilized here, as this approach is simple, easy to implement, and has strong adaptability and robustness, among which the gray-level co-occurrence matrix (GLCM) is used [47,48]. The GLCM is used extensively in texture description, and the co-occurrence matrices provide better results than do other forms of texture discrimination [49,50]. For remote sensing images, four types of statistics-angular second moment, contrast, correlation, and entropy-are better suited to texture feature extraction, so they have been selected for statistics in this study [51].…”

Structuring pea towards meat analogues

“…Pork (m) (Ayuso et al, 2013) Dry cured meat products (m) (Corona et al, 2013) Hyperspectral imaging Spatially compositional analysis, fiber orientation Beef (m) (Cluff et al, 2008;ElMasry et al, 2011;Rady & Adedeji, 2018van Beers et al, 2017) Pork (m) (Barbin et al, 2012(Barbin et al, , 2013Cheng et al, 2018;Huang et al, 2017;Kucha et al, 2018;Rady & Adedeji, 2018Yang et al, 2017) Lamb (m) (Kamruzzaman et al, 2012) Chicken (m) (Jia et al, 2018;Rady & Adedeji, 2018, 2020) X-ray Tomography Structure with a resolution from mm to μm Beef (m) (Einarsdóttir et al, 2014;Frisullo et al, 2010;Kröger et al, 2006;Mathanker et al, 2013;Miklos et al, 2015;Schoeman et al, 2016) Pork (m) (Brienne et al, 2001;Einarsdóttir et al, 2014;Frisullo et al, 2010;Kröger et al, 2006;Mathanker et al, 2013;Miklos et al, 2015;Schoeman et al, 2016) Chicken (m) (Adedeji & Ngadi, 2011) High moisture extruded product (ma) (Philipp et al, 2017) Shear cell structures (ma) (Dekkers, Hamoen, et al, 2018;Tian et al, 2018;Zhaojun Wang et al, 2019 and Chapter 2)…”

“…Fulladosa et al, 2010;Gou et al, 2013;Mabood et al, 2020;Rady & Adedeji, 2018) Chicken (m)(Jia et al, 2018;Krepper et al, 2018;Nolasco Perez et al, 2018; Jens Petter Wold et al, 2019) Beef (m)(Bonin et al, 2020;Cafferky et al, 2020;Cozzolino & Murray, 2004;Rady & Adedeji, 2018;Ripoll et al, 2008; Weng et al.al., 2005;Hoban et al, 2016) …”