Combination of spectral and textural information of hyperspectral imaging for the prediction of the moisture content and storage time of cooked beef

Yang, Dong; He, Di; Lu, Anxiang; Ren, Dong; Wang, Jihua

doi:10.1016/j.infrared.2017.05.005

Cited by 52 publications

(18 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, PC images which depicted the most information of the original image were selected based on their variance contribution for further processing. Each transformed image from color to the gray‐level intensity is the linear sum of each hypercube image at specific wavelengths multiplied by equivalent weighting coefficients (Fan et al, ; Huang et al, ; Yang, He, Lu, Ren, & Wang, ; Zhao et al, ). Then, textural features were extracted from the selected PC images employing gray‐level co‐occurrence matrix (GLCM) method proposed by Haralick, Shanmugam, and Dinstein ().…”

Section: Methodsmentioning

confidence: 99%

Section: Extraction Of Textural Variablesmentioning

confidence: 99%

See 1 more Smart Citation

Combination of spectra and image information of hyperspectral imaging data for fast prediction of lipid oxidation attributes in pork meat

Aheto

Huang

Tian

et al. 2019

J Food Process Engineering

View full text Add to dashboard Cite

This study highlighted the potential of integrating texture and spectra information of hyperspectral imaging to predict the evolution of 2‐thiobarbituric acid reactive substances (TBARS) and peroxide value (PV) as lipid oxidation attributes in pork muscles under diverse processing conditions. Partial least square regression (PLSR) models were established on data fusion information (image and optimal spectra) and compared with other three PLSR models built on spectra (full range and optimal), and image information. Regarding TBARS measurement, model based on optimal spectra was superior with determination coefficient of prediction (Rp2) of .896, root mean square error of prediction (RMSEP) of 1.034, and residual predictive deviation (RPD) of 2.311 as compared to the data fusion model (Rp2 = .865, RMSEP = 0.994, RPD = 2.280). For PV, model on data fusion yielded the best (Rp2 = .899, RMSEP = 0.966, RPD = 2.314) followed by that on optimal spectra (Rp2 = .883, RMSEP = 1.073, RPD = 2.281). Then prediction maps were drawn to visualize the distribution of TBARS and PV in the samples using models built on optimal spectra. The maps revealed intrinsic differences in samples which are not readily perceptible by visual observation. Practical Applications Models based on spectra and spatial information of hyperspectral imaging have been widely used to predict and visualize food quality attributes. However, these are not enough to elucidate the impact of processing on the meat samples as it may not be able to directly measure attributes related to external properties such as texture properties. The present study investigated the feasibility of integrating texture features obtained from gray‐level co‐occurrence matrix and spectra data to predict quality changes associated with pork meat subjected to diverse processing conditions. The results obtained proved that the methods presented can be useful for designing future experiments in a bid to establishing robust models for food quality assessment.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Extraction Of Textural Variablesmentioning

confidence: 99%

Combination of spectra and image information of hyperspectral imaging data for fast prediction of lipid oxidation attributes in pork meat

Aheto

Huang

Tian

et al. 2019

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…As compared to common spectroscopic techniques and machine vision imaging, one of the advantages of HSI is that it can provide both spectral and spatial information at the same time. To fully seek the advantages of HSI, some researchers [21][22][23][24] have investigated the fusion of spectral and textural data to improve the accuracy of model prediction and classification. For example, in order to improve the detection accuracy of soluble solids content of apples, spectral and textural features extracted from hyperspectral reflectance images were integrated to build combined partial least square (CPLS) regression models [21].…”

Section: Introductionmentioning

confidence: 99%

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

et al. 2018

View full text Add to dashboard Cite

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.

show abstract

“…By hyperspectral data analysis, the external and internal characteristics of the samples can be predicted. Previous studies have convincingly demonstrated that HSI technology possesses the potential for assessing capsaicin concentrations and water content in chili peppers (Jiang et al, 2018), anthocyanin content in sweet potato , protein content in wheat kernels (Caporaso, Whitworth, & Fisk, 2018), sugar content in dangshang pear , decayed honey peaches , firmness and sweetness of tomatoes (Rahman, Park, Bae, & Cho, 2018), moisture content of cooked beef (Yang et al, 2017), total pigments of red meats (Xiong et al, 2015), and so on. However, the research on determining total phenolic content in Flos Lonicerae by using HSI technology is scarce.…”

mentioning

confidence: 99%

“…With the development of hyperspectral imaging (HSI) technology, it has been extensively applied in agriculture and food industry in recent years (Li & Chen, 2017;Xiong et al, 2015). HSI technology, as a fast and nondestructive detection method, can simultaneously capture spectral and spatial information of samples by combining spectral and imaging techniques (Feng, Liu, Shi, & Wang, 2018;Jiang et al, 2019;Yang, He, Lu, Ren, & Wang, 2017). The collected hyperspectral images contain the large amount of data that is represented by a three-dimensional "hypercube" (Kiani, van Ruth, van Raamsdonk, & Minaei, 2019).…”

mentioning

confidence: 99%

Total phenolic content prediction inFlos Loniceraeusing hyperspectral imaging combined with wavelengths selection methods

Liu

Wang

Gao

et al. 2019

J Food Process Engineering

View full text Add to dashboard Cite

Hyperspectral imaging (HSI) method was applied to rapidly and nondestructively predict total phenolic content in Flos Lonicerae. The least squares support vector machine (LS‐SVM) and partial least squares regression (PLSR) models were developed on the basis of full wavelengths data and characteristic wavelengths data chosen by six wavelengths selection ways. The results clarified that standard normal variable (SNV) was the optimal pretreatment method, and the nonlinear LS‐SVM model based on the characteristic wavelengths chosen by the combination (CARS‐SPA) of competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA) yielded the best prediction performance for the total phenolic content. The overall results demonstrated that the proposed CARS‐SPA was a good method for selecting characteristic wavelengths to enhance prediction performance of HSI, and nonlinear LS‐SVM was more appropriate than linear PLSR for the prediction of total phenolic content in Flos Lonicerae. Practical applications Flos Lonicerae is a well‐known traditional Chinese medicinal herb, and also the raw material of various medicines and herbal tea. The demand for Flos Lonicerae is increasing. Therefore, monitoring the quality of Flos Lonicerae is very important to consumers and industry of Flos Lonicerae. The phenolic compounds content in Flos Lonicerae is one of the key internal quality factors. The traditional methods (such as spectrophotometric techniques or high‐performance liquid chromatography) for detecting total phenolic content are time‐consuming, labor‐consuming, and destructive. Hyperspectral imaging (HSI) is a nondestructive and reliable method for quality inspection. The results showed that SNV was determined as the best method for pretreatment, and the nonlinear CARS‐SPA‐LS‐SVM model was developed for total phenolic content detection with high precision. It could be verified that HSI technology is effective and promising for rapid determination of total phenolic content and quality control of Flos Lonicerae as well as other agricultural products.

show abstract

Combination of spectral and textural information of hyperspectral imaging for the prediction of the moisture content and storage time of cooked beef

Cited by 52 publications

References 47 publications

Combination of spectra and image information of hyperspectral imaging data for fast prediction of lipid oxidation attributes in pork meat

Combination of spectra and image information of hyperspectral imaging data for fast prediction of lipid oxidation attributes in pork meat

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

Total phenolic content prediction inFlos Loniceraeusing hyperspectral imaging combined with wavelengths selection methods

Contact Info

Product

Resources

About