Deep Learning Ventricle Segmentation
Zach | 05 January 2022
This project was a part of my Master’s research where the goal was to create an automatic deep learning segmentation approach which performed quickly and provided accurate segmentation results. We used the U-Net model as our baseline which is useful for small datasets like our own and well-suited for 3D ultrasound data. Some of our earlier preliminary work can be seen in our conference paper here which looked into 2D multiplane models for solving our problem.
read moreRutgers RGB-D Amazon Picking Challenge
Zach | 01 April 2020
This was a class assignment where we had to perform pose estimation on an object that was store din a shelving unit using only RGB-D data. The assignment was based on the Amazon Picking Challenge and featured data collected by Rutgers. The pose estimation for 6 objects was determined using the SIFT algorithm which determined similar features from both the object face and the object located in the bin then the homography matrix was found using RANSAC. This project was done entirely with the Python implementation of OpenCV.
read moreCell Tracking and Segmentation
Zach | 01 December 2019
This was a class project in which our group chose to do cell tracking and segmentation from an open source dataset. We compared traditional segmentation techniques such as graph cut and level set methods to the U-Net deep learning segmentation model. In addition, we were able to identify separate individual cells and track their motion over consecutive frames using conventional computer vision techniques.
read morePredicting Movie Success Using Machine Learning
Zach | 01 April 2019
In this project, we created models which can predict how successful a movie will be. We defined success as how much money a movie makes and how many Academy Award wins/ nominations they have. The more money and awards, the greater amount of success. The models were developped using a regression model to determine the amount of money made and a classification model for number of Oscar wins.
read more