NCSI: Accurate Hair Segmentation and Classification Using Deep Learning

Status	Completed
Mentor Name	Hao Ji
Mentor's XSEDE Affiliation	Education Allocation
Mentor Has Been in XSEDE Community	4-5 years
Project Title	Accurate Hair Segmentation and Classification Using Deep Learning
Summary	Many real-life applications such as human identification and beautification, demand accurate hair segmentation and classification in images. In this project, we plan to leverage state-of-the-art deep learning techniques to build accurate models for hair segmentation and classification. We will build deep learning models using TensorFlow, train them on XSEDE Bridges GPU clusters, and benchmark their performance with application cases running in real time using webcams and mobile devices.
Job Description	Students participating in this project will work on the following tasks: 1) learn modern deep learning libraries and computer vision libraries to create a complete pipeline for hair segemtation and classification; 2) prepare an image dataset of various hairstyles from 3D models and apply data augmentation techniques to enlarge the image dataset; and 3) apply transfer learning to fine-tune several pre-trained deep learning models to create learning models for hair segmentation and classification.
Computational Resources	XSEDE Bridges' GPU clusters
Contribution to Community
Position Type	Intern
Training Plan	I will offer a "Machine Learning and Its Applications" course in the fall semester of 2018. This course will prepare students with the necessary knowledge and skills in Machine Learning. During this project, I will work closely with the students and plan to have weekly meetings with them to guide their research progress.
Student Prerequisites/Conditions/Qualifications	Must have an undergraduate at California State Polytechnic University, Pomona Must have a good understanding of linear algebra and good programming skills in Python.
Duration	Semester
Start Date	08/23/2018
End Date	12/09/2018