[-] Show simple item record

dc.contributor.advisorHan, Xu (Tony Xu)eng
dc.contributor.authorSun, Miao (Engineer)eng
dc.date.issued2016eng
dc.date.submitted2016 Falleng
dc.descriptionDissertation supervisor: Dr. Tony X. Han.eng
dc.descriptionIncludes vita.eng
dc.description.abstractSignificant advancement of research on image classification and object detection has been achieved in the past decade. Deep convolutional neural networks have exhibited superior performance in many visual recognition tasks including image classification, object detection, and scene labeling, due to their large learning capacity and resistance to overfit. However, learning a robust deep CNN model for object recognition is still quite challenging because image classification and object detection is a severely unbalanced large-scale problem. In this dissertation, we aim at improving the performance of image classification and object detection algorithms by taking advantage of deep convolutional neural networks by utilizing the following strategies: We introduce Deep Neural Pattern, a local feature densely extracted from an image with arbitrary resolution using a well trained deep convolutional neural network. We propose a latent CNN framework, which will automatically select the most discriminate region in the image to reduce the effect of irrelevant regions. We also develop a new combination scheme for multiple CNNs via Latent Model Ensemble to overcome the local minima problem of CNNs. In addition, a weakly supervised CNN framework, referred to as Multiple Instance Learning Convolutional Neural Networks is developed to alleviate strict label requirements. Finally, a novel residual-network architecture, Residual networks of Residual networks, is constructed to improve the optimization ability of very deep convolutional neural networks. All the proposed algorithms are validated by thorough experiments and have shown solid accuracy on large scale object detection and recognition benchmarks.eng
dc.description.bibrefIncludes bibliographical references (pages 105-119).eng
dc.format.extent1 online resource (xvi, 120 pages) : illustrationseng
dc.identifier.merlinb118921411eng
dc.identifier.oclc993435095eng
dc.identifier.urihttps://hdl.handle.net/10355/59786
dc.identifier.urihttps://doi.org/10.32469/10355/59786eng
dc.languageEnglisheng
dc.publisherUniversity of Missouri--Columbiaeng
dc.relation.ispartofcollectionUniversity of Missouri--Columbia. Graduate School. Theses and Dissertationseng
dc.rightsOpenAccesseng
dc.rights.licenseThis work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivs 3.0 License.eng
dc.subject.FASTNeural networks (Computer science) -- Researcheng
dc.subject.FASTComputer visioneng
dc.subject.FASTImage processing.eng
dc.titleLarge scale image classification and object detectioneng
dc.typeThesiseng
thesis.degree.disciplineElectrical engineering (MU)eng
thesis.degree.grantorUniversity of Missouri--Columbiaeng
thesis.degree.levelDoctoraleng
thesis.degree.namePh. D.eng


Files in this item

[PDF]
[PDF]
[PDF]

This item appears in the following Collection(s)

[-] Show simple item record