I am broadly interested in learning visual phenomenon from images by designing features and employing classification techniques. My overarching goal is to involve students to employ image analysis and learning for tasks originating in different STEM fields. Towards that goal, I am currently working on projects involving Computed Tomography (CT) scans of human lungs, microscopic images of geological rocks (in collaboration with Dr. Matty Mookerjee, Department of Geology) and digital images of animals in the wild (in collaboration with Dr. Chris Halle at the Center for Environmental Inquiry). More information regarding these projects can be found here. SSU students who are interested in these projects are welcome to contact me!
I've been a faculty member in the Department of Computer Science at Sonoma State University since August 2015. I obtained my Ph.D. in 2009 from the Center of Intelligent Machines (CIM) at McGill University where I worked on object detection in digital images (Thesis link). My primary research area is computer vision and medical imaging. I am broadly interested in learning visual phenomenon from images and applying learned models for classification/detection/segmentation tasks. SSU students who are interested in this area are welcome to contact me!
Previously, from July 2012 - July 2015, I was a post-doctoral researcher at the Iowa Institue of Biomedical Imaging (IIBI) in the University of Iowa where I worked on Lung Segmentation in CT scans. Prior to that, I worked as a gameplay programmer at Behavior Interactive in Montreal, Canada where I worked on the following game titles: Sims 3 (Wii), Transformers Dark of the Moon (Wii/3DS), Wipeout 2 (3DS) and Goldrun (iOS).
A. Encarnacion, B. Katin, M. Mookerjee and G.Gill, Building a Geological Cyber-infrastructure: Automatically Detecting Clasts in Photomicrographs, Poster presentation at EarthCube Annual Meeting (San Diego), held virtually due to Covid-19, Jun. 2020. (Web link)
J. B. Martinez and G. Gill, "Comparison of Pre-Trained vs Domain-Specific Convolutional Neural Networks for Classification of Interstitial Lung Disease," 2019 International Conference on Computational Science and Computational Intelligence (CSCI), Las Vegas, NV, USA, 2019, pp. 991-994. (PDF link)
J. Bautista-Martinez, M. Mookerjee and G.Gill, Building a Geological Cyber-infrastructure: Classifying Clasts in Photomicrographs, Poster presentation at EarthCube Annual Meeting, Denver, June 2019. (PDF link)
J. Bautista-Martinez, S. Penna and G.Gill, Applications of Convolutional Neural Network Model for classifying Interstitial Lung Disease images from Computed Tomography scans. Selected to represent Sonoma State University (acceptance rate ~43%) at the 33rd Annual CSU Student Research Competition, CSU Fullerton, April 2019. (PDF link)
S. Penna, C. Havranek and G.Gill, A computational framework based on convolutional neural network for classifying interstitial lung disease in computed tomography scans, Student poster presentation at CSUPERB annual symposium (acceptance rate ~74% across all CSUs), Jan 2019. (PDF link)
B. Cogan, M. Puryear and G.Gill, Towards building a geological cyber-infrastructure: classifying sigma-clast images in photomicrographs, Student poster presentation at CCSC Southwest Region conference, March 2018. Recipient of Best poster award. (PDF link)
J. Meixensperger, S. Perry and G.Gill, Performance of traditional image processing and convolutional neural network in classifying interstitial lung disease, Student poster presentation at CCSC Southwest Region conference, March 2018 (Recipient of 2nd Best poster award) and SSU Science Symposium of Research and Creativity, May 2018 (Recipient of the “Bright Idea” award). (PDF link)
J. Granados and G.Gill, Using pre-trained convolutional neural networks to classify interstitial lung diseases in computed tomography scans, Student poster presentation at CSUPERB annual symposium (acceptance rate ~71% across all CSUs), January 2018. (PDF link)
G. Gill and R. R. Beichel, Segmentation of Lungs with Interstitial Lung Disease in CT Scans: A TV-L1 Based Texture Analysis Approach, Advances in Visual Computing, LNCS 8887, pp. 511-520, 2014. (PDF link)