{"id":{"repo_id":"carleton","oai_identifier":"oai:carleton.scholaris.ca:20.500.14718/43558"},"canonical_url":"https://search.dev.ndltd.org/etd/carleton/oai:carleton.scholaris.ca:20.500.14718/43558","repository":{"repo_id":"carleton","name":"Carleton University","base_url":"https://carleton.scholaris.ca/server/oai/request"},"display":{"title":"Text-Guided Image-to-Image Translation for Converting RGB Maps to Tactile Images","abstract":"Tactile graphics provide blind and visually impaired individuals access to visual information through touch, aiding navigation, education, and social interaction. However, manual tactile design is costly, time-intensive, and difficult to scale. This thesis proposes a novel approach to generate tactile maps from RGB maps using text-guided image-to-image translation. By leveraging natural language prompts, the method enables control over map details, such as lakes, rivers, and cities, allowing outputs to be tailored to specific needs. A custom dataset of 1,845 RGB maps was developed, paired with multiple tactile counterparts, each reflecting unique combinations of detail levels for map components. Text prompts were crafted to describe these tactile variations, resulting in 9,800 triplets (RGB map, tactile map, prompt) for training and evaluation. Human evaluations confirmed the model outperforms a baseline model, with 47% of outputs requiring minimal adjustments. This scalable solution streamlines tactile map production while maintaining high quality.","abstract_html":"Tactile graphics provide blind and visually impaired individuals access to visual information through touch, aiding navigation, education, and social interaction. However, manual tactile design is costly, time-intensive, and difficult to scale. This thesis proposes a novel approach to generate tactile maps from RGB maps using text-guided image-to-image translation. By leveraging natural language prompts, the method enables control over map details, such as lakes, rivers, and cities, allowing outputs to be tailored to specific needs. A custom dataset of 1,845 RGB maps was developed, paired with multiple tactile counterparts, each reflecting unique combinations of detail levels for map components. Text prompts were crafted to describe these tactile variations, resulting in 9,800 triplets (RGB map, tactile map, prompt) for training and evaluation. Human evaluations confirmed the model outperforms a baseline model, with 47% of outputs requiring minimal adjustments. This scalable solution streamlines tactile map production while maintaining high quality.","abstract_has_math":false,"creators":["Choubineh, Alireza"],"institution":"Carleton University","degree_name":"Master of Computer Science (M.C.S.)","degree_level":"Master's","degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025","date_published":"2025","updated_at":"2026-07-24T01:34:22Z","subjects":[],"languages":["en"],"rights":["Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2025-16415"],"render_values":[{"text":"10.22215/etd/2025-16415","href":"https://doi.org/10.22215/etd/2025-16415","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14718/43558","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:creator","label":"Author","values":["Choubineh, Alireza"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-05-23T20:03:35Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2025-05-23T20:03:35Z"]},{"key":"dc:date.issued","label":"Date","values":["2025"]},{"key":"dc:publisher","label":"Institution","values":["Carleton University"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Computer Science (M.C.S.)"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["10.22215/etd/2025-16415"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14718/43558"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Tactile graphics provide blind and visually impaired individuals access to visual information through touch, aiding navigation, education, and social interaction. However, manual tactile design is costly, time-intensive, and difficult to scale. This thesis proposes a novel approach to generate tactile maps from RGB maps using text-guided image-to-image translation. By leveraging natural language prompts, the method enables control over map details, such as lakes, rivers, and cities, allowing outputs to be tailored to specific needs. A custom dataset of 1,845 RGB maps was developed, paired with multiple tactile counterparts, each reflecting unique combinations of detail levels for map components. Text prompts were crafted to describe these tactile variations, resulting in 9,800 triplets (RGB map, tactile map, prompt) for training and evaluation. Human evaluations confirmed the model outperforms a baseline model, with 47% of outputs requiring minimal adjustments. This scalable solution streamlines tactile map production while maintaining high quality."]},{"key":"dc:title","label":"Title","values":["Text-Guided Image-to-Image Translation for Converting RGB Maps to Tactile Images"]}]}],"canonical_facts":{"dc:creator":["Choubineh, Alireza"],"dc:date.accessioned":["2025-05-23T20:03:35Z"],"dc:date.available":["2025-05-23T20:03:35Z"],"dc:date.issued":["2025"],"dc:description.abstract":["Tactile graphics provide blind and visually impaired individuals access to visual information through touch, aiding navigation, education, and social interaction. However, manual tactile design is costly, time-intensive, and difficult to scale. This thesis proposes a novel approach to generate tactile maps from RGB maps using text-guided image-to-image translation. By leveraging natural language prompts, the method enables control over map details, such as lakes, rivers, and cities, allowing outputs to be tailored to specific needs. A custom dataset of 1,845 RGB maps was developed, paired with multiple tactile counterparts, each reflecting unique combinations of detail levels for map components. Text prompts were crafted to describe these tactile variations, resulting in 9,800 triplets (RGB map, tactile map, prompt) for training and evaluation. Human evaluations confirmed the model outperforms a baseline model, with 47% of outputs requiring minimal adjustments. This scalable solution streamlines tactile map production while maintaining high quality."],"dc:identifier.doi":["10.22215/etd/2025-16415"],"dc:identifier.uri":["https://hdl.handle.net/20.500.14718/43558"],"dc:language.iso":["en"],"dc:publisher":["Carleton University"],"dc:rights":["Copyright © 2024 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner."],"dc:title":["Text-Guided Image-to-Image Translation for Converting RGB Maps to Tactile Images"],"dc:type":["thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Computer Science (M.C.S.)"]},"updated_at":"2026-07-24T01:34:22Z"}