A software for automatic identification of oyster species

The files includes all data and final analysis of the work done in CS8 - oysters, task 8.2, CSTP8.2.2_A new software for automatic identification of oyster species. This includes the data management descriptor document (DataSheet_oyster_image_classification.docx), images used (oyster_classification_images.zip), the code developed (oyster_classification_code_package.zip) and different models evaluated (oyster_classification_models.zip), the genetics data produced (oyster_classification_biometrics and PCR.xlsx) and the project report (C639_ostronklassificering.pdf). The content of the files is described briefely below. The data is used in deliverables D1.2, D1.4, D1.5 and D1.6 in the AquaVitae project.

oyster_classification_images.zip

The data set contains the images used for training the classification models that are capable of classifying images of oysters as either Ostrea edulis or Magallana gigas. The images are sorted in folders named “train” (training data) and “validation” (validation data) with both folders containing sub-folders called “mg” (images of Magallana gigas) and “oe” (images of Ostrea edulis).

oyster_classification_code_package.zip

The data set contains the code for training a neural network for classifying oyster species based on images. The code also includes localization of oyster within an image and inference of the classification along with the trained models.

oyster_classification_models.zip

The data set contains the trained classification models that are capable of classifying images of oysters as either Ostrea edulis or Magallana gigas.

oyster_classification_biometrics and PCR.xlsx

The data set contains biometric information for a subset of 240 Ostrea edulis, 240 Magallana gigas and 204 oysters of unsure species denotation sampled as a start pool for the image analysis project and for genetic evaluation of species belonging.