Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish

Taheri‐Garavand, Amin; Nasiri, Alireza; Banan, Ashkan; Zhang, Yudong

doi:10.1016/j.jfoodeng.2020.109930

Cited by 66 publications

(18 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Common carp fish (Cyprinus carpio) is one of the most important fish species of freshwater [21], distributed in the Asia and Europe [22]. It has been estimated that the production of common carp fish is about 4.32 million tons [21]. When fish is exposed to any kind of toxin, it could lead to changes in biochemical, hematological parameters, histological alteration, and gut microbial dysbiosis [23].…”

Section: Introductionmentioning

confidence: 99%

Long-term exposure to high-concentration silver nanoparticles induced toxicity, fatality, bioaccumulation, and histological alteration in fish (Cyprinus carpio)

Kakakhel

Sajjad

et al. 2021

Environ Sci Eur

View full text Add to dashboard Cite

Background Currently, nanotechnology and nanoparticles have quickly emerged and have gained the attention of scientists due to their massive applications in environmental sectors. However, these environmental applications of silver nanoparticles potentially cause serious effects on terrestrial and aquatic organisms. In the current study, freshwater fish C. carpio were exposed to blood-mediated silver nanoparticles for toxicity, mortality, bioaccumulation, and histological alterations. Silver nanoparticles were fabricated using animal blood serum and their toxic effect was studied against common carp fish at different concentrations levels (0.03, 0.06, and 0.09 mg/L). Results The findings have revealed a little influence of blood-induced silver nanoparticles on fish behavior at the highest concentration (0.09 mg/L). However, bioaccumulation of blood-mediated silver nanoparticles was reported in different organs of fish. Maximum bioaccumulation of silver nanoparticles was reported in the liver, followed by the intestine, gills, and muscles. Furthermore, the findings have shown that the bioaccumulation of silver nanoparticles led to histopathological alterations; including damaged structure of gill tissue and have caused necrosis. It is summarized that histopathological alteration in gill and intestine mostly occurred by the highest concentration of blood-induced silver nanoparticles (0.09 mg/L). Conclusion This study provides evidence of the silver nanoparticles influence on aquatic life; however, further systematic studies are crucial to access the effects of AgNPs on aquatic life.

show abstract

Section: Introductionmentioning

confidence: 99%

Long-term exposure to high-concentration silver nanoparticles induced toxicity, fatality, bioaccumulation, and histological alteration in fish (Cyprinus carpio)

Kakakhel

Sajjad

et al. 2021

Environ Sci Eur

View full text Add to dashboard Cite

show abstract

“…Deep learning has been used for a myriad of applications ranging from games to medicine, but its applicability has only partly been explored for fish classification [10][11][12][13][14]. A specific Convolutional Neural Network (CNN) called Fast R-CNN has been applied for object detection to extract the fish from images taken in natural environment and actively ignoring background noise [6].…”

Section: Introductionmentioning

confidence: 99%

Temperate fish detection and classification: a deep learning based approach

Knausgård

Wiklund²,

Sørdalen

et al. 2021

Appl Intell

View full text Add to dashboard Cite

A wide range of applications in marine ecology extensively uses underwater cameras. Still, to efficiently process the vast amount of data generated, we need to develop tools that can automatically detect and recognize species captured on film. Classifying fish species from videos and images in natural environments can be challenging because of noise and variation in illumination and the surrounding habitat. In this paper, we propose a two-step deep learning approach for the detection and classification of temperate fishes without pre-filtering. The first step is to detect each single fish in an image, independent of species and sex. For this purpose, we employ the You Only Look Once (YOLO) object detection technique. In the second step, we adopt a Convolutional Neural Network (CNN) with the Squeeze-and-Excitation (SE) architecture for classifying each fish in the image without pre-filtering. We apply transfer learning to overcome the limited training samples of temperate fishes and to improve the accuracy of the classification. This is done by training the object detection model with ImageNet and the fish classifier via a public dataset (Fish4Knowledge), whereupon both the object detection and classifier are updated with temperate fishes of interest. The weights obtained from pre-training are applied to post-training as a priori. Our solution achieves the state-of-the-art accuracy of 99.27% using the pre-training model. The accuracies using the post-training model are also high; 83.68% and 87.74% with and without image augmentation, respectively. This strongly indicates that the solution is viable with a more extensive dataset.

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

Smart deep learning-based approach for non-destructive freshness diagnosis of common carp fish

Cited by 66 publications

References 43 publications

Long-term exposure to high-concentration silver nanoparticles induced toxicity, fatality, bioaccumulation, and histological alteration in fish (Cyprinus carpio)

Long-term exposure to high-concentration silver nanoparticles induced toxicity, fatality, bioaccumulation, and histological alteration in fish (Cyprinus carpio)

Temperate fish detection and classification: a deep learning based approach

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

Contact Info

Product

Resources

About