Counting tilapia larvae using images captured by smartphones

In this work, we propose a new way for automatically counting fish larvae in Petri dishes using images captured by a standard smartphone. A new tilapia larvae image dataset for training and validating machine learning models has been created and used to validate a recent machine learning approach based on multi-stage model refinement of confidence maps. A mean absolute error (MAE) of 1.43 has been achieved using the proposed automatic larvae counter, indicating that the proposed approach is promising for larvae counting, as the mean number of larvae per image is more than 20. The proposed approach also achieved precision, recall, and F-measure values of 0.98, 0.92, and 0.95, respectively, for larvae detection using a dataset containing images from more than 6,000 manually annotated larvae. •Novel non-invasive image capture method for counting tilapia larvae.•New dataset of tilapia larvae acquired by smartphones for counting applications.•High-performance method for locating and counting larvae in Petri dishes.•Validation of recent heatmap machine learning method in a fish breeding problem.