A data fusion detection method for fish freshness based on computer vision and near-infrared spectroscopy

Huang, Xingyi; Xu, Haixia; Lei, Wu; Dai, Houde; Yao, Liya; Han, Fangkai

doi:10.1039/c5ay03005f

Cited by 73 publications

(27 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(35) MSC is adopted as a widely used spectral preprocessing technique that can eliminate direct reflection and noise in the diffuse reflection and separate multiplicative interferences such as scatter and particle size at the same time. (36) Identically, SNV is used to correct baseline drift and eliminate undesirable scattering effects from the data matrix. (37) To optimize the accuracy of models, in this work, the spectral preprocessing methods performed were nontreatment, MSC, SNV, and SG smoothing with a second-order polynomial and window sizes of 23 points, as well as combinations of two preprocessing methods.…”

Section: Spectral Preprocessingmentioning

confidence: 99%

Prediction of Glycogen and Moisture Contents in Japanese Wagyu Beef by Fourier Transform Near-infrared Spectroscopy for Quality Evaluation

Yao¹,

Oe²,

Ye³

et al. 2019

Sensors and Materials

View full text Add to dashboard Cite

Keywords: glycogen, moisture content, Japanese wagyu beef, FT-NIR, PLSR (MSC) yielded optimum results with R p 2 of 0.795, RMSEP of 2.669%, and RPD of 2.008. The results of this study demonstrated that NIR spectroscopy offers great potential for the prediction of glycogen and moisture contents in Japanese wagyu beef samples. effect on Japanese consumers' preference owing to the improvement in beef quality such as tenderness. (2)(3)(4)(5)(6)(7) This is consistent with the conclusion that tenderness is the most important factor affecting beef palatability. (8)(9)(10)(11) However, additional studies have shown that when tenderness is at an acceptable level, flavor becomes the next most important factor affecting the beef preference of consumers. (10)(11)(12)(13)(14)(15) Flavor is a complex concept, which is composed of taste, odor, and the interaction of these factors. In our previous work, a sensory panel test was used to determine the relationship between sensory attributes (e.g., sweetness, fattiness, aroma, tenderness, flavor, and overall evaluation) and chemical composition characteristics (e.g., moisture, protein, free amino acid, glycogen, and fatty acid contents) of Japanese wagyu beef by the simmering method. (16) We demonstrated that the 'flavor' of sensory attributes was associated with glycogen and moisture contents. It has been widely reported that pre rigor muscle glycogen content has a negative curvilinear relationship with ultimate pH, (17) which is an indicator of the final palatability of meat. (18,19) In addition, the glycogen content in the muscle is related to the amounts of monosaccharides such as glucose and fructose after slaughter, which affect the development of meat flavor via the Maillard reaction; therefore, glycogen contributes to beef palatability. (20) Moisture content is often used to assess meat quality. (21) It also has a strong relationship with the contents of lipids that affect sensory attributes such as flavor, juiciness, texture, and appearance. (22) Therefore, to satisfy an increasing demand for evaluating meat quality by either the meat processing industry or consumers, fast, accurate, and nondestructive methods are urgently required.In recent years, near-infrared (NIR) spectroscopy, which is based on optical measurements of reflectance, transmittance, and interactance, has been considered as a nondestructive, fast, convenient, inexpensive, and precise technique. NIR spectroscopy combined with various multivariable data processing techniques has been effectively employed. Applications of the NIR technique to the evaluation of meat quality have been reviewed. (23) The NIR technique has the potential of detecting meat adulteration, (24,25) assessing meat microbial spoilage, (26,27) and estimating meat quality. (28,29) Nowadays, several research studies on Japanese wagyu beef have shown that NIR spectroscopy can be applied to predict the fat content and quantify the fatty acid composition. Kobayashi et al. have demonstrated the correlation between fat content and spectral infor...

show abstract

Section: Spectral Preprocessingmentioning

confidence: 99%

Prediction of Glycogen and Moisture Contents in Japanese Wagyu Beef by Fourier Transform Near-infrared Spectroscopy for Quality Evaluation

Yao¹,

Oe²,

Ye³

et al. 2019

Sensors and Materials

View full text Add to dashboard Cite

show abstract

“…Finally, a Back-Propagation Neural Network (BPNN) was used to classify the maturity level of Roma tomato and pear tomato. Huang (2016) used computer vision and NIR spectroscopy methods to obtain information about the organoleptic and structural changes of fish based on fish images. The PCA was employed to extract the most critical features from the data set, and a BackPropagation Artificial Neural Network (BP-ANN) was built to predict the fish freshness by training the algorithm to assess the extracted features.…”

Section: Machine Learning Approachesmentioning

confidence: 99%

Deep learning and machine vision for food processing: A survey

Zhu

Spachos

Pensini

et al. 2021

Current Research in Food Science

160

View full text Add to dashboard Cite

The quality and safety of food is an important issue to the whole society, since it is at the basis of human health, social development and stability. Ensuring food quality and safety is a complex process, and all stages of food processing must be considered, from cultivating, harvesting and storage to preparation and consumption. However, these processes are often labour-intensive. Nowadays, the development of machine vision can greatly assist researchers and industries in improving the efficiency of food processing. As a result, machine vision has been widely used in all aspects of food processing. At the same time, image processing is an important component of machine vision. Image processing can take advantage of machine learning and deep learning models to effectively identify the type and quality of food. Subsequently, follow-up design in the machine vision system can address tasks such as food grading, detecting locations of defective spots or foreign objects, and removing impurities. In this paper, we provide an overview on the traditional machine learning and deep learning methods, as well as the machine vision techniques that can be applied to the field of food processing. We present the current approaches and challenges, and the future trends.

show abstract

“…However, the conventional sensory, chemical, and microbiological methods are imprecise, time consuming, expensive, destructive, and labor-intensive; a fast, inexpensive, and simple method is needed. In recent years, some fast, non-destructive methods for assessing fish freshness have received attention, including near-infrared spectroscopy [5], front-face fluorescence spectroscopy [6], hyperspectral imaging [7], and image technologies [8]. Among these, the application of machine vision technology coupled with image-processing techniques to ascertain fish quality is a growing area [9] [10] [11] [12], in response to the demand for simple, low-cost, and rapid real-time techniques.…”

Section: Introductionmentioning

confidence: 99%

Developing a Machine Vision System Equipped with UV Light to Predict Fish Freshness Based on Fish-Surface Color

Liao¹,

Wei²,

Liu³

et al. 2021

FNS

View full text Add to dashboard Cite

This study assessed the feasibility of developing a machine vision system equipped with ultraviolet (UV) light, using changes in fish-surface color to predict aerobic plate count (APC, a standard freshness indicator) during storage. The APC values were tested and images of the fish surface were taken when fish were stored at room temperature. Then, images' color-space conversion among RGB, HSV, and L*a*b* color spaces was carried out and analyzed. The results revealed that a* and b* values from the UV-light image decreased linearly during storage. A further regression analysis of these two parameters with APC value demonstrated a good exponential relationship between the a* value and the APC value (R 2 = 0.97), followed by the b* (R 2 = 0.85). Therefore, our results suggest that the change in color of the fish surface under UV light can be used to assess fish freshness during storage.

show abstract

A data fusion detection method for fish freshness based on computer vision and near-infrared spectroscopy

Abstract: This article proposes and describes a data fusion detection method based on computer vision and spectroscopic techniques for fish freshness classification.

Cited by 73 publications

References 26 publications

Prediction of Glycogen and Moisture Contents in Japanese Wagyu Beef by Fourier Transform Near-infrared Spectroscopy for Quality Evaluation

Prediction of Glycogen and Moisture Contents in Japanese Wagyu Beef by Fourier Transform Near-infrared Spectroscopy for Quality Evaluation

Deep learning and machine vision for food processing: A survey

Developing a Machine Vision System Equipped with UV Light to Predict Fish Freshness Based on Fish-Surface Color

Contact Info

Product

Resources

About