Comparison of Visible–Near Infrared and Short Wave Infrared hyperspectral imaging for the evaluation of rainbow trout freshness

Khojastehnazhand, Mostafa; Khoshtaghaza, Mohammad Hadi; Mojaradi, Barat; Rezaei, Masoud; Goodarzi, Mohammad; Saeys, Wouter

doi:10.1016/j.foodres.2013.12.018

Cited by 37 publications

(15 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been reported by several authors that the capability of spectral imaging devices to determine quality parameters, noninvasively and in real time, where no reagents are required and no wastes are produced, has been accentuated in a wide sort of food products (ElMasry & Sun, ; Everard et al ., ; Kamruzzaman et al ., ). The usefulness of spectral imaging in fisheries products such as evaluating fish freshness (Sone et al ., ; Khojastehnazhand et al ., ), prediction of moisture, fat, protein and salt contents (ElMasry & Wold, ) and detection of abnormalities (Sivertsen et al ., ) has been recently emphasised. Therefore, it is highly suitable for industrial implementation and highly applicable for online monitoring of various physical and chemical properties during processing and can thus be used to aid process control.…”

Section: Introductionmentioning

confidence: 99%

Noninvasive sensing of thermal treatments of Japanese seafood products using imaging spectroscopy

ElMasry

Nakauchi

2015

Int J of Food Sci Tech

View full text Add to dashboard Cite

The potential of imaging spectroscopy for noncontact sensing of thermal treatments experienced on Japanese kamaboko was investigated. Samples were thermally treated at 100, 120, 140, 160, 180 and 200°C to core temperatures of 45, 50, 55, 60, 65, 70, 75 and 80°C and then promptly cooled and imaged in the short-wave near infrared spectral range of 900-2500 nm. Partial least square (PLS) regression models were developed using the whole spectral range as well as using the most important wavelengths to predict the core temperature (T C ) and thermal history (TH) yielding a reasonable level of accuracy of (R 2 P = 0.86 and RMSEP = 3.9°C) and (R 2 P = 0.83 and RMSEP = 0.29 min), respectively. Moreover, a stepwise linear discriminant analysis (LDA) model was developed for identifying samples whose core temperatures reached a threshold of 65°C. The LDA model yielded overall classification accuracy of 93.75% in both calibration and validation sets. The resulting discrimination function was then applied in a pixel-wise manner to produce understandable classification maps to exhibit the difference among samples with high accuracy.

show abstract

Section: Introductionmentioning

confidence: 99%

Noninvasive sensing of thermal treatments of Japanese seafood products using imaging spectroscopy

ElMasry

Nakauchi

2015

Int J of Food Sci Tech

View full text Add to dashboard Cite

show abstract

“…In addition, with constant trial and error, Kong and others () found that S‐G smoothing was the most suitable pretreatment method for detecting the peroxidase (POD) activity in tomato leaves. More recently, Khojastehnazhand and others () compared different combinations of SNV, MSC, S‐G Der1, and S‐G Der2 to improve the SNR in visible‐near infrared (Vis‐NIR) and short‐wave infrared (SWIR) HSI for evaluating rainbow trout freshness. They showed that the S‐G Der2 was the best pretreatment approach for predicting freshness, with an overall correct classification of 100% and 75% in Vis‐NIR and SWIR.…”

Section: Correction Methodsmentioning

confidence: 99%

Recent Advances in De‐Noising Methods and Their Applications in Hyperspectral Image Processing for the Food Industry

Dai

Sun

Cheng

et al. 2014

Comp Rev Food Sci Food Safe

View full text Add to dashboard Cite

There is great interest in developing hyperspectral imaging (HSI) techniques for rapid and nondestructive inspection of food quality, safety, and authenticity. In recent years, image quality has been constantly improved through advances in instrumentation, particularly in more powerful detectors. Nevertheless, pretreatment of data by de-noising is a necessary step to insure clean HSI datasets for further analysis. This review first introduces the typical and commonly used de-noising methods in HSI that correct for undesirable variations and remove noisy variables. Their advantages, disadvantages, and implementation are also discussed by giving examples of recent applications in the food industry. Finally, some advice is given for selecting the de-noising methods that are best suited for a particular application. This review offers an overview of the most frequently applied methods and the latest progress made in HSI de-noising in food applications. It provides systematic insight into future trends for generating high-accuracy predictions regarding food safety and quality.

show abstract

“…MSC method is effectively used in spectroscopic applications where light scattering variation and multiplicative noise were present [25,26]. SG smoothing were widely used in removing noise of baseline excursion and smoothing spectra [27,28]. For SG smoothing, a window width of 7 points was applied.…”

Section: Spectral Preprocessingmentioning

confidence: 99%

Integration of Artificial Neural Network Modeling and Hyperspectral Data Preprocessing for Discrimination of Colla Corii Asini Adulteration

Wang

et al. 2018

Journal of Food Quality

View full text Add to dashboard Cite

The study of hyperspectral imaging in tandem with spectral preprocessing and neural network techniques was conducted to realize Colla Corii Asini (CCA, E'jiao) adulteration discrimination. CCA was adulterated with pig skin gelatin (PSG) in the range of 5-95% (w/w) at 5% increments. Three methods were used to pretreat the original spectra, which are multiplicative scatter correction (MSC), Savitzky-Golay (SG) smoothing, and the combination of MSC and SG (MSC-SG). SPA was employed to select the characteristic wavelengths (CWs) to reduce the high dimension. Colour and texture features of CWs were extracted as input of prediction model. Two kinds of artificial neural network (ANN) with three spectral preprocessing methods were applied to establish the prediction models. The prediction model of generalized regression neural network (GRNN) in tandem with the MSC-SG preprocessed method presented satisfactory performance with the correct classification rate value of 92.5%. The results illustrated that the integration of preprocessing methods, hyperspectral imaging features, and ANN modeling had a great potential and feasibility for CCA adulteration discrimination.

show abstract

Comparison of Visible–Near Infrared and Short Wave Infrared hyperspectral imaging for the evaluation of rainbow trout freshness

Cited by 37 publications

References 47 publications

Noninvasive sensing of thermal treatments of Japanese seafood products using imaging spectroscopy

Noninvasive sensing of thermal treatments of Japanese seafood products using imaging spectroscopy

Recent Advances in De‐Noising Methods and Their Applications in Hyperspectral Image Processing for the Food Industry

Integration of Artificial Neural Network Modeling and Hyperspectral Data Preprocessing for Discrimination of Colla Corii Asini Adulteration

Contact Info

Product

Resources

About