An improved nondestructive measurement method for salmon freshness based on spectral and image information fusion

Wu, Ting; Yang, Ling; Zhou, Juan; Lai, Dong Cheng; Zhong, Nan

doi:10.1016/j.compag.2019.01.039

Cited by 22 publications

(10 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the study of river crabs by X. Li et al (2020)), wavelet transform (WT) and PCA were identified as the optimal preprocessing and feature extraction methods by experimental comparison, and the final model based on WT‐PCA‐PLSR had a prediction coefficient of determination R 2 of .89 and an RMSEP of 3.00. T. Wu, Yang, Zhou, Cheng, Zhong (2019) fused the visible spectral data (400–700 nm) of salmon with RGB image information and built a neural network model to predict salmon's TVC and TVB‐N values. The results showed that the accuracy of the test set was 92.3%, and the prediction accuracy of the fused data was much higher than that of the individual data.…”

Section: Spectroscopy Technologymentioning

confidence: 99%

“…After external validation set validation and T-test, there was no significant difference between the predicted and true values obtained by the model (p > .05). In the study of river crabs by X. Li et al (2020)), wavelet transform (WT) and PCA were identified as the optimal preprocessing and feature extraction methods by experimental comparison, and the final model based on WT-PCA-PLSR had a prediction coefficient of determination R 2 of .89 and an RMSEP of 3.00.T Wu, Yang, Zhou, Cheng, Zhong (2019). fused the visible spectral data (400-700 nm) of salmon with RGB image information and built a neural network model to predict salmon's TVC and TVB-N values.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Research progress on nondestructive testing technology for aquatic products freshness

Wang

Xie

et al. 2022

J Food Process Engineering

View full text Add to dashboard Cite

As one of the vital food, aquatic products help to improve diet structure and alleviate food pressure. Aquatics food has a tender taste, with protein, polyunsaturated fatty acid (PUFA), and other nutrients. At the same time, aquatic products are highly susceptible to spoilage due to their properties in processing, transportation, and storage, which damages the economic efficiency of producers and may pose a threat to the dietary safety of consumers. Therefore, researchers have been working to developing an efficient, nondestructive, and practical technology to detect the freshness of aquatic products in real-time and easily. This article describes the representative techniques applied in recent years for the nondestructive inspection of aquatic products' freshness in terms of working principles, application examples, and characteristics. It summarizes each technique's development prospects and challenges.

show abstract

Section: Spectroscopy Technologymentioning

confidence: 99%

mentioning

confidence: 99%

Research progress on nondestructive testing technology for aquatic products freshness

Wang

Xie

et al. 2022

J Food Process Engineering

View full text Add to dashboard Cite

show abstract

“…The process of sorting fish needs to be done quickly and precisely [7] because of the perishable state of fish due to bacterial reproduction in fish, chemical reaction and biochemical processes that take place in the fish's body [8,9]. Fish sorting is closely related to the ability of market managers to identify the freshness of fish to be marketed to consumers [10].…”

Section: Introductionmentioning

confidence: 99%

Implementation of Naïve Bayes for Fish Freshness Identification Based on Image Processing

Saputra

Yudhana

Umar

2022

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

Consumption of fish as a food requirement for the fulfillment of community nutrition is increasing. This was followed by an increase in the amount of fish caught that were sold at fish markets. Market managers must be concerned about the dispersion of huge amounts of fish in the market in order to determine the freshness of the fish before it reaches the hands of consumers. So far, market managers have relied on traditional ways to determine the freshness of fish in circulation. The issue is that traditional solutions, such as the use expert assessment, demand a human physique that quickly experiences fatigue. Technological developments can be a solution to these problems, such as utilizing image processing techniques classification method. Image processing with the use of color features is an effective method to determine the freshness of fish. The classification method used in this research is the Naive Bayes method. This study aims to identify the freshness of fish based on digital images and determine the performance level of the method. The identification process uses the RGB color value feature of fisheye images. The stages of fish freshness identification include cropping, segmentation, RGB value extraction, training, and testing. The classification data are 210 RGB value of extraction images which are divided into 147 data for training and 63 data for testing. The research data were divided into fresh class, started to rot class, and rotted class. The research shows that the Naive Bayes algorithm can be used in the process of identifying the freshness level of fish based on fisheye images with a test accuracy rate of 79.37%.

show abstract

“…Wang, Peng, Sun, Zheng, and Wei (2018) developed a portable optical device based on dual‐band visible/near infrared (Vis/NIR) spectroscopy, which realized real‐time and simultaneous detection of pork quality attributes. Wu, Yang, Zhou, Lai, and Zhong (2019) developed an improved non‐destructive measurement method for salmon freshness based on spectral and image information fusion, which effectively improved the accuracy of salmon freshness prediction model. Zhang et al (2018) studied golden pompano freshness based on the fusion of Vis/NIR spectroscopy and electronic nose, which presented a forecasting accuracy of 93.3%.…”

Section: Introductionmentioning

confidence: 99%

Comparison of mutton freshness grade discrimination based on hyperspectral imaging, near infrared spectroscopy and their fusion information

Zhu

Bai

Qiu

et al. 2021

J Food Process Engineering

View full text Add to dashboard Cite

The discrimination models of mutton freshness grades based on hyperspectral imaging (HSI, 400-1,000 nm), near infrared spectroscopy (NIRS, 900-2,500 nm) and their fusion information were established and compared in this study. Mutton freshness was divided into three grades by the comprehensive evaluation criterion. Then the characteristic variables were screened from preprocessed full-band variables, and discriminant models were established and compared based on the full-band variables, the characteristic variables and fusion information. The results showed that both full-band models of HSI and NIRS showed good performance, and the accuracies of all datasets were higher than 92.6%. The model accuracy decreased gradually with the decrease of the variables number when modeling with characteristic variables. When modeling with fusion information, the extreme learning machine models had better performance, and the accuracies of all datasets were over 92.7%. Comprehensively considering the accuracy, the cost, the efficiency of data acquisition and analysis, the fusion of HSI and NIRS had no significant effect compared to the single sensor with full-band variables, and NIRS was possibly more economical and practical than HSI. This study provides reference and theoretical basis for selection of sensors in future studies and development of simplified, low-cost detection devices for mutton freshness grade. Practical Applications Based on the full-band variables, the characteristic variables, and fusion information of HSI (400-1,000 nm) and NIRS (900-2,500 nm), the discrimination models of mutton freshness grades were established and compared. The characteristic variables were screened by the methods of CARS, GA, SPA and their synergic methods. We could come to a conclusion that both full-band models of HSI and NIRS showed good results. Comprehensively considering the accuracy, the cost, the efficiency of data acquisition and analysis, the fusion of HSI and NIRS had no significant effect compared to the single sensor based on the full-band variables, and NIRS was possibly more economical and practical than HSI. This study provides reference and theoretical basis for selection of sensors in future studies and development of simplified, low-cost detection devices for mutton freshness grade.

show abstract

An improved nondestructive measurement method for salmon freshness based on spectral and image information fusion

Cited by 22 publications

References 18 publications

Research progress on nondestructive testing technology for aquatic products freshness

Research progress on nondestructive testing technology for aquatic products freshness

Implementation of Naïve Bayes for Fish Freshness Identification Based on Image Processing

Comparison of mutton freshness grade discrimination based on hyperspectral imaging, near infrared spectroscopy and their fusion information

Contact Info

Product

Resources

About