{"id":{"repo_id":"houston","oai_identifier":"oai:uh-ir.tdl.org:10657/5755"},"canonical_url":"https://search.dev.ndltd.org/etd/houston/oai:uh-ir.tdl.org:10657/5755","repository":{"repo_id":"houston","name":"University of Houston","base_url":"https://uh-ir.tdl.org/server/oai/request"},"display":{"title":"Segment and Cut: A Simpler Method for Extracting Bounding-Boxes for Object Detection","abstract":"Object detectors that are based on bounding-box regression are complex and require a lot of refinement to get good results. Is there a simpler way of doing object detection? To that end, I present a new method for object detection where you first segment an image, and then cut each object from the segmentation to produce its bounding box. The key to this method is that it uses only ground truth bounding box data to generate the ground truth segmentation mask, rather than using a semantic-segmentation mask which are pixel-perfect. Additionally, I present a modified Flood Fill algorithm for the cutting task. Using this method, I eliminate the need for bounding-box regression, anchor-boxes, region proposal methods and all of their associated complexities. Experiments show that my method gets competitive performance on the WIDER Face dataset with full-size images and runs between 30 and 50 FPS when using 640x480 pixel images.","abstract_html":"Object detectors that are based on bounding-box regression are complex and require a lot of refinement to get good results. Is there a simpler way of doing object detection? To that end, I present a new method for object detection where you first segment an image, and then cut each object from the segmentation to produce its bounding box. The key to this method is that it uses only ground truth bounding box data to generate the ground truth segmentation mask, rather than using a semantic-segmentation mask which are pixel-perfect. Additionally, I present a modified Flood Fill algorithm for the cutting task. Using this method, I eliminate the need for bounding-box regression, anchor-boxes, region proposal methods and all of their associated complexities. Experiments show that my method gets competitive performance on the WIDER Face dataset with full-size images and runs between 30 and 50 FPS when using 640x480 pixel images.","abstract_has_math":false,"creators":["Brown, Justin Michael 1994-"],"institution":"University of Houston","degree_name":"Master of Science","degree_level":"Masters","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Shah, Shishir Kirit"],"committee_chairs":[],"committee_members":["Wiley, Robert","Kakadiaris, Ioannis A."],"year":2019,"date_issued":"2019-05","date_published":"2019-05","updated_at":"2026-07-24T02:33:01Z","subjects":["Object detection","Image Segmentation","Face recognition"],"languages":["eng"],"rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/10657/5755","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Shah, Shishir Kirit"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Wiley, Robert","Kakadiaris, Ioannis A."]},{"key":"dc:creator","label":"Author","values":["Brown, Justin Michael 1994-"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2020-01-04T03:03:28Z"]},{"key":"dc:date.issued","label":"Date","values":["2019-05"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Masters"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Science"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Houston"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Object detection","Image Segmentation","Face recognition"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10657/5755"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Object detectors that are based on bounding-box regression are complex and require a lot of refinement to get good results. Is there a simpler way of doing object detection? To that end, I present a new method for object detection where you first segment an image, and then cut each object from the segmentation to produce its bounding box. The key to this method is that it uses only ground truth bounding box data to generate the ground truth segmentation mask, rather than using a semantic-segmentation mask which are pixel-perfect. Additionally, I present a modified Flood Fill algorithm for the cutting task. Using this method, I eliminate the need for bounding-box regression, anchor-boxes, region proposal methods and all of their associated complexities. Experiments show that my method gets competitive performance on the WIDER Face dataset with full-size images and runs between 30 and 50 FPS when using 640x480 pixel images."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Segment and Cut: A Simpler Method for Extracting Bounding-Boxes for Object Detection"]}]}],"canonical_facts":{"dc:contributor.advisor":["Shah, Shishir Kirit"],"dc:contributor.committeemember":["Wiley, Robert","Kakadiaris, Ioannis A."],"dc:creator":["Brown, Justin Michael 1994-"],"dc:date.accessioned":["2020-01-04T03:03:28Z"],"dc:date.issued":["2019-05"],"dc:description.abstract":["Object detectors that are based on bounding-box regression are complex and require a lot of refinement to get good results. Is there a simpler way of doing object detection? To that end, I present a new method for object detection where you first segment an image, and then cut each object from the segmentation to produce its bounding box. The key to this method is that it uses only ground truth bounding box data to generate the ground truth segmentation mask, rather than using a semantic-segmentation mask which are pixel-perfect. Additionally, I present a modified Flood Fill algorithm for the cutting task. Using this method, I eliminate the need for bounding-box regression, anchor-boxes, region proposal methods and all of their associated complexities. Experiments show that my method gets competitive performance on the WIDER Face dataset with full-size images and runs between 30 and 50 FPS when using 640x480 pixel images."],"dc:format.mimetype":["application/pdf"],"dc:identifier.uri":["https://hdl.handle.net/10657/5755"],"dc:language.iso":["eng"],"dc:rights":["The author of this work is the copyright owner. UH Libraries and the Texas Digital Library have their permission to store and provide access to this work. Further transmission, reproduction, or presentation of this work is prohibited except with permission of the author(s)."],"dc:subject":["Object detection","Image Segmentation","Face recognition"],"dc:title":["Segment and Cut: A Simpler Method for Extracting Bounding-Boxes for Object Detection"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Masters"],"thesis:degree_name":["Master of Science"],"thesis:institution_name":["University of Houston"]},"updated_at":"2026-07-24T02:33:01Z"}