{"id":{"repo_id":"missouri","oai_identifier":"oai:mospace.umsystem.edu:10355/62086"},"canonical_url":"https://search.dev.ndltd.org/etd/missouri/oai:mospace.umsystem.edu:10355/62086","repository":{"repo_id":"missouri","name":"University of Missouri","base_url":"https://mospace.umsystem.edu/oai/request"},"display":{"title":"Multi-scale target detection based on morphological shared-weight neural network","abstract":"Convolutional Neural Networks (CNN) are a popular neural network structure for image based applications. This thesis discusses an alternative network, the morphological shared-weight neural network (MSNN) for object detection. In this thesis, three combined network structures are developed for multi-scale object detection. The dataset used for the experiments presented here were created by the author for this thesis study. The convolutional neural network is used as the baseline for judging the performance of the MSNN. Experiments suggest that when training data is limited, the MSNN has a more robust and precise performance as compared with the CNN.","abstract_html":"Convolutional Neural Networks (CNN) are a popular neural network structure for image based applications. This thesis discusses an alternative network, the morphological shared-weight neural network (MSNN) for object detection. In this thesis, three combined network structures are developed for multi-scale object detection. The dataset used for the experiments presented here were created by the author for this thesis study. The convolutional neural network is used as the baseline for judging the performance of the MSNN. Experiments suggest that when training data is limited, the MSNN has a more robust and precise performance as compared with the CNN.","abstract_has_math":false,"creators":["Shen, Shuxian"],"institution":"University of Missouri--Columbia","degree_name":"M.S.","degree_level":"Masters","degree_discipline":"Computer science (MU)","degree_department":null,"school":null,"contributors":[],"advisors":["Keller, James M."],"committee_chairs":[],"committee_members":[],"year":2017,"date_issued":"2017","date_published":"2017","updated_at":"2026-07-24T03:08:20Z","subjects":[],"languages":["eng","English"],"rights":["OpenAccess."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.32469/10355/62086"],"render_values":[{"text":"https://doi.org/10.32469/10355/62086","href":"https://doi.org/10.32469/10355/62086","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10355/62086","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Keller, James M."]},{"key":"dc:creator","label":"Author","values":["Shen, Shuxian"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2017-11-09T15:17:35Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2017-11-09T15:17:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2017"]},{"key":"dc:publisher","label":"Institution","values":["University of Missouri--Columbia"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer science (MU)"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Missouri--Columbia"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["OpenAccess."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.32469/10355/62086"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10355/62086"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Convolutional Neural Networks (CNN) are a popular neural network structure for image based applications. This thesis discusses an alternative network, the morphological shared-weight neural network (MSNN) for object detection. In this thesis, three combined network structures are developed for multi-scale object detection. The dataset used for the experiments presented here were created by the author for this thesis study. The convolutional neural network is used as the baseline for judging the performance of the MSNN. Experiments suggest that when training data is limited, the MSNN has a more robust and precise performance as compared with the CNN."]},{"key":"dc:source","label":"Dc Source","values":["Submited to University of Missouri--Columbia Graduate School."]},{"key":"dc:title","label":"Title","values":["Multi-scale target detection based on morphological shared-weight neural network"]}]}],"canonical_facts":{"dc:contributor.advisor":["Keller, James M."],"dc:creator":["Shen, Shuxian"],"dc:date.accessioned":["2017-11-09T15:17:35Z"],"dc:date.available":["2017-11-09T15:17:35Z"],"dc:date.issued":["2017"],"dc:description.abstract":["Convolutional Neural Networks (CNN) are a popular neural network structure for image based applications. This thesis discusses an alternative network, the morphological shared-weight neural network (MSNN) for object detection. In this thesis, three combined network structures are developed for multi-scale object detection. The dataset used for the experiments presented here were created by the author for this thesis study. The convolutional neural network is used as the baseline for judging the performance of the MSNN. Experiments suggest that when training data is limited, the MSNN has a more robust and precise performance as compared with the CNN."],"dc:identifier.doi":["https://doi.org/10.32469/10355/62086"],"dc:identifier.uri":["https://hdl.handle.net/10355/62086"],"dc:language":["English"],"dc:language.iso":["eng"],"dc:publisher":["University of Missouri--Columbia"],"dc:rights":["OpenAccess."],"dc:source":["Submited to University of Missouri--Columbia Graduate School."],"dc:title":["Multi-scale target detection based on morphological shared-weight neural network"],"dc:type":["Thesis"],"thesis:degree_discipline":["Computer science (MU)"],"thesis:degree_level":["Masters"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Missouri--Columbia"]},"updated_at":"2026-07-24T03:08:20Z"}