Document Type



This item is available under a Creative Commons License for non-commercial use only


Computer Sciences

Publication Details

A dissertation submitted in partial fulfilment of the requirements of Technological University Dublin for the degree of M.Sc. in Computer Science (Data Analytics)


The CIRSY system (or Chick Instance Recognition System) is am image processing system developed as part of this research to detect images of chicks in highly-populated images that uses the leading algorithm in instance segmentation tasks, called the Mask R-CNN. It extends on the Faster R-CNN framework used in object detection tasks, and this extension adds a branch to predict the mask of an object along with the bounding box prediction. Mask R-CNN has proven to be effective ininstance segmentation and object de-tection tasks after outperforming all existing models on evaluation of the Microsoft Common Objects in Context (MS COCO) dataset (He, Gkioxari, Dollfar, & Girshick, 2017). However, this research explores to what extent the Mask R-CNN framework can perform in instance level recognition of small objects in poorly lit images. By leveraging on the benefits of transfer learning in training deep neural networks, this research further explores if re tuning the Mask R-CNN algorithm can significantly improve the models performance after it has been trained after applying the weights from the implementation of the model trained on the MS COCO dataset. The CIRSY system was trained on various synthetic datasets with varying degrees of transformation and noise applied. These datasets were built from a collection of CCTV footage of chicks in a poultry farm. The experiments conducted showed that although there were slight improvements in the model performance, these improvements were not statistically significant.