Scale-invariant image segmentation using machine learning

Show simple item record

dc.contributor.advisor Rhinelander, Jason
dc.creator Andrews, Rasheed
dc.date.accessioned 2019-03-25T14:16:45Z
dc.date.available 2019-03-25T14:16:45Z
dc.date.issued 2018
dc.identifier.other TA1638.4 A53 2018
dc.identifier.uri http://library2.smu.ca/handle/01/28276
dc.description xii, 124 leaves : illustrations (chiefly colour) ; 29 cm
dc.description Includes abstract and appendix.
dc.description Includes bibliographical references (leaves 100-105).
dc.description.abstract The increased application of segmentation requires more robust machine learning algorithms that can handle variations of the input. The areas of robotics, self-driving cars, automated drone delivery systems, and Speed Enforcement Cameras (SEC) all rely on accurate predictions from machine learning algorithms. CNNs are the current state of the art in image recognition which has led to their increased application in areas of classification, object detection, and segmentation. However, scale invariance poses a significant issue for CNNs; fixed kernel size hinders the prediction accuracy of the network for objects of varying sizes. This research introduces a training methodology and image pre-processing techniques which makes these networks more robust or invariant to the changes in the size of the object. en_CA
dc.language.iso en en_CA
dc.publisher Halifax, N.S. : Saint Mary's University
dc.subject.lcc TA1638.4
dc.subject.lcsh Image segmentation
dc.subject.lcsh Machine learning
dc.subject.lcsh Neural networks (Computer science)
dc.title Scale-invariant image segmentation using machine learning en_CA
dc.type Text en_CA
thesis.degree.name Master of Science in Computing and Data Analytics
thesis.degree.level Masters
thesis.degree.discipline Mathematics and Computing Science
thesis.degree.grantor Saint Mary's University (Halifax, N.S.)


Files in this item

 
 

This item appears in the following Collection(s)

Show simple item record