Portland State University. Department of Computer Science
Date of Award
Master of Science (M.S.) in Computer Science
1 online resource (vi, 48 pages)
For the last several years, convolutional neural network (CNN) based object detection systems have used a regression technique to predict improved object bounding boxes based on an initial proposal using low-level image features extracted from the CNN. In spite of its prevalence, there is little critical analysis of bounding-box regression or in-depth performance evaluation. This thesis surveys an array of techniques and parameter settings in order to further optimize bounding-box regression and provide guidance for its implementation. I refute a claim regarding training procedure, and demonstrate the effectiveness of using principal component analysis to handle unwieldy numbers of features produced by very deep CNNs.
Dickerson, Naomi Lynn, "Refining Bounding-Box Regression for Object Localization" (2017). Dissertations and Theses. Paper 3940.