Flex-Shape Convolution and an Interactive Image Segmentation System Public Deposited

http://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/5d86p434r

Descriptions

Attribute NameValues
Creator
Abstract or Summary
  • Semantic image segmentation is a relatively difficult task in computer vision. With the advent of deep learning, semantic image segmentation is increasingly of interest for researchers because of the excellent predictions from Convolutional Neural Network (CNN). However, CNNs have proven to struggle with obtaining global context of image due to convolutions being a local operation. Recent researches have proposed several global context-aware approaches: Atrous convolution, V-Net, multi-scale architecture, etc. Different from previous perspectives, this paper proposes two novel approaches to solve the problem of locating context in CNN. The first approach is called flex-shape convolution that improves the scaling and deformation capabilities of the CNN. The second approach samples auxiliary positive object pixels and negative non-object pixels for network to infer the object mask. Additionally, a web-based application of interactive image semantic annotator has been developed that allows both classical image segmentation algorithms and deep learning algorithms to assist researchers with annotating their images for semantic segmentation.
License
Resource Type
Date Available
Date Copyright
Date Issued
Degree Level
Degree Name
Degree Grantor
Commencement Year
Advisor
Committee Member
Non-Academic Affiliation
Keyword
Rights Statement
Peer Reviewed
Language
Replaces
Additional Information
  • description.provenance : Approved for entry into archive by Steven Van Tuyl(steve.vantuyl@oregonstate.edu) on 2017-06-12T20:47:57Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ZhouZheng2017.pdf: 6414311 bytes, checksum: 851c9cde3e03ca3c2412638263dcfde5 (MD5)
  • description.provenance : Submitted by Zheng Zhou (zhouzh@oregonstate.edu) on 2017-06-02T17:06:36Z No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ZhouZheng2017.pdf: 6414311 bytes, checksum: 851c9cde3e03ca3c2412638263dcfde5 (MD5)
  • description.provenance : Made available in DSpace on 2017-06-12T20:47:57Z (GMT). No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ZhouZheng2017.pdf: 6414311 bytes, checksum: 851c9cde3e03ca3c2412638263dcfde5 (MD5)
  • description.provenance : Approved for entry into archive by Julie Kurtz(julie.kurtz@oregonstate.edu) on 2017-06-04T16:19:05Z (GMT) No. of bitstreams: 2 license_rdf: 1370 bytes, checksum: cd1af5ab51bcc7a5280cf305303530e9 (MD5) ZhouZheng2017.pdf: 6414311 bytes, checksum: 851c9cde3e03ca3c2412638263dcfde5 (MD5)

Relationships

In Administrative Set:
Last modified: 10/21/2017

Downloadable Content

Download PDF
Citations:

EndNote | Zotero | Mendeley

Items