Classification of fish freshness using a convolutional neural network
Abstract In the work, the freshness of the trout (Oncorhynchus mykiss) was analyzed, this aspect being very important to determine its quality. The objective is to propose a computational model based on a CNN to classify the freshness of the trout based on the changes in color of their eyes and gill...
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Lenguaje: | inglés |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | Enlace permanente (DOI o Handle) |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Sumario: | Abstract In the work, the freshness of the trout (Oncorhynchus mykiss) was analyzed, this aspect being very important to determine its quality. The objective is to propose a computational model based on a CNN to classify the freshness of the trout based on the changes in color of their eyes and gills. For this, an image data set was created with the acquired trout. To obtain the results, 3 experiments were carried out, the first; with 2 classes (days 1 and 9), the second with 3 classes (days 1, 5 and 9) and the third with 5 classes (days 1, 3, 5, 7 and 9), all the experiments were run in Google colab.The results were validated with a confusion matrix and ROC curve. The best results were given by the ResNeXt5032x4d model, with 2 classes it obtained an accuracy of 0.9833, 3 classes an accuracy of 0.9222 and with 5 classes an accuracy of 0.8800. |
|---|