A novel hybrid system for automatic detection of fish quality from eye and gill color characteristics using transfer learning technique

Akgül, İsmail; Kaya, Volkan; Tanır, Özge Zencir

doi:10.1371/journal.pone.0284804

Cited by 5 publications

(2 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For enhanced accuracy in future study, it would be beneficial to gather more image data and to explore the potential of combined models while conducting further fine-tuning. For example, Akgül et al [13] applied the Xception model in a study of fish freshness detection, achieving successful results when combined with Yolo-v5 for anchovy (Engraulis encrasicolus) and horse mackerel (Trachurus trachurus). Additionally, comparing specific external fish body parts, such as color, fins, tail, body length, and width, might enhance classification performance.…”

Section: Fine-tuningmentioning

confidence: 99%

“…Carnagie et al [12] used the Xception model to classify essential oil plants, reporting highest accuracy levels of 75% during validation and 81% during testing by the fourth epoch. Furthermore, Akgül et al [13] utilized Xception for fish freshness detection and obtained successful outcomes when combined with Yolo-v5, achieving 88.00% and 94.67% accuracy levels for anchovy (Engraulis encrasicolus) and Horse mackerel (Trachurus trachurus) datasets, respectively. Chen et al [14] employed a deep neural system for fish classification, utilizing two branches: one for detecting, aligning, and classifying fish based on pose and scale variations; and the other for leveraging contextual information to infer fish types.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Transfer Learning Model Application for Rastrelliger brachysoma and R. kanagurta Image Classification Using Smartphone-Captured Images

Jongjaraunsuk,

Taparhudee,

Sirisuay

et al. 2024

Fishes

View full text Add to dashboard Cite

Prior aquatic animal image classification research focused on distinguishing external features in controlled settings, utilizing either digital cameras or webcams. Identifying visually similar species, like short mackerel (Rastrelliger brachysoma) and Indian mackerel (Rastrelliger kanagurta), is challenging without specialized knowledge. However, advancements in computer technology have paved the way for leveraging machine learning and deep learning systems to address such challenges. In this study, transfer learning techniques were employed, utilizing established pre-trained models such as ResNet50, Xception, InceptionV3, VGG19, VGG16, and MobileNetV3Small. These models were applied to differentiate between the two species using raw images captured by a smartphone under uncontrolled conditions. The core architecture of the pre-trained models remained unchanged, except for the removal of the final fully connected layer. Instead, a global average pooling layer and two dense layers were appended at the end, comprising 1024 units and by a single unit, respectively. To mitigate overfitting concerns, early stopping was implemented. The results revealed that, among the models assessed, the Xception model exhibited the most promising predictive performance. It achieved the highest average accuracy levels of 0.849 and 0.754 during training and validation, surpassing the other models. Furthermore, fine-tuning the Xception model by extending the number of epochs yielded more impressive outcomes. After 30 epochs of fine-tuning, the Xception model demonstrated optimal performance, reaching an accuracy of 0.843 and displaying a 10% improvement in predictions compared to the model without fine-tuning. These findings highlight the efficacy of transfer learning, particularly with the Xception model, in accurately distinguishing visually similar aquatic species using smartphone-captured images, even in uncontrolled conditions.

show abstract

Section: Fine-tuningmentioning

confidence: 99%