Date

5-1-2015

Document Type

Thesis

Degree

Master of Science

Department

Electrical and Computer Engineering

First Adviser

Zhou, Chao

Abstract

In this thesis, we introduced a new method of marking the heart region of Drosophila in its different living stages which are known as larva, pupa and adult with convolutional neural networks. The images of Drosophila are acquired by a custom optical coherence microscopy (OCM) system in lab, this method of extracting the heart position of the fly obtained by the convolutional neural network in this article is of considerable significance for future research on the fly heart. We will elaborate in the article on how we completed the training and testing of this model and how we acquire the training and testing data of this experiment.

Share

COinS