{"id":{"repo_id":"uwo","oai_identifier":"oai:uwo.scholaris.ca:20.500.14721/36062"},"canonical_url":"https://search.dev.ndltd.org/etd/uwo/oai:uwo.scholaris.ca:20.500.14721/36062","repository":{"repo_id":"uwo","name":"Western University","base_url":"https://uwo.scholaris.ca/server/oai/request"},"display":{"title":"ASSESSMENT OF AI-GENERATED IMAGES USING COMPUTATIONAL METRICS AND HUMAN CENTRIC ANALYSIS","abstract":"The rapid advancements in AI-generated models for image generation have transformed image creation from entertainment to e-commerce, making robust evaluation essential. We designed and statistically validated a human study for assessing the photorealism and image quality of AI-generated images. The study indicated that camera images show more realism, while AI images, such as those generated by DALL-E2, excel in quality. Further analysis showed that existing metrics deviate from human judgments. To address this, we developed the Global-Local Image Perceptual Score (GLIPS), which evaluates photorealistic quality using Vision Transformer-based attention for local similarity and Maximum Mean Discrepancy (MMD) for global distributional similarity. Our evaluation showed that GLIPS aligns more closely with human perception compared to traditional metrics like FID and SSIM for photorealism, although MS-SSIM outperformed in image quality. Additionally, we introduced the Interpolative Binning Scale (IBS) for human-assisted metric scaling with human scores.","abstract_html":"The rapid advancements in AI-generated models for image generation have transformed image creation from entertainment to e-commerce, making robust evaluation essential. We designed and statistically validated a human study for assessing the photorealism and image quality of AI-generated images. The study indicated that camera images show more realism, while AI images, such as those generated by DALL-E2, excel in quality. Further analysis showed that existing metrics deviate from human judgments. To address this, we developed the Global-Local Image Perceptual Score (GLIPS), which evaluates photorealistic quality using Vision Transformer-based attention for local similarity and Maximum Mean Discrepancy (MMD) for global distributional similarity. Our evaluation showed that GLIPS aligns more closely with human perception compared to traditional metrics like FID and SSIM for photorealism, although MS-SSIM outperformed in image quality. Additionally, we introduced the Interpolative Binning Scale (IBS) for human-assisted metric scaling with human scores.","abstract_has_math":false,"creators":["Aziz, Memoona"],"institution":"The University of Western Ontario","degree_name":"M Sc","degree_level":null,"degree_discipline":"Computer Science","degree_department":null,"school":null,"contributors":[],"advisors":["Umair Rehman"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024-08-15","date_published":"2024-08-15","updated_at":"2026-07-27T21:56:20Z","subjects":["Photorealistic Image Quality","DALLE","Stable Difusion","Interpolative Binning Scale","GLIPS"],"languages":["en_ca"],"rights":[],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"https://hdl.handle.net/20.500.14721/36062","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Umair Rehman"]},{"key":"dc:creator","label":"Author","values":["Aziz, Memoona"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2025-07-10T20:45:31Z"]},{"key":"dc:date.issued","label":"Date","values":["2024-08-15"]},{"key":"dc:publisher","label":"Institution","values":["The University of Western Ontario"]},{"key":"dc:type","label":"Dc Type","values":["thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Computer Science"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M Sc"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Photorealistic Image Quality","DALLE","Stable Difusion","Interpolative Binning Scale","GLIPS"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en_ca"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/20.500.14721/36062"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."]},{"key":"dc:description.abstract","label":"Abstract","values":["The rapid advancements in AI-generated models for image generation have transformed image creation from entertainment to e-commerce, making robust evaluation essential. We designed and statistically validated a human study for assessing the photorealism and image quality of AI-generated images. The study indicated that camera images show more realism, while AI images, such as those generated by DALL-E2, excel in quality. Further analysis showed that existing metrics deviate from human judgments. To address this, we developed the Global-Local Image Perceptual Score (GLIPS), which evaluates photorealistic quality using Vision Transformer-based attention for local similarity and Maximum Mean Discrepancy (MMD) for global distributional similarity. Our evaluation showed that GLIPS aligns more closely with human perception compared to traditional metrics like FID and SSIM for photorealism, although MS-SSIM outperformed in image quality. Additionally, we introduced the Interpolative Binning Scale (IBS) for human-assisted metric scaling with human scores."]},{"key":"dc:title","label":"Title","values":["ASSESSMENT OF AI-GENERATED IMAGES USING COMPUTATIONAL METRICS AND HUMAN CENTRIC ANALYSIS"]}]}],"canonical_facts":{"dc:contributor.advisor":["Umair Rehman"],"dc:creator":["Aziz, Memoona"],"dc:date.accessioned":["2025-07-10T20:45:31Z"],"dc:date.issued":["2024-08-15"],"dc:description":["The thesis cover page in the PDF document includes references to Western University’s previous institutional repository platform, known as Scholarship@Western, and links to that platform (beginning with ir.lib.uwo.ca). In citing or referring to this thesis, use the DOI or handle from this page instead. Sample citation: Author name, \"Thesis title.\" (Year). Western University Open Repository. https://doi.org/10.71858/123456."],"dc:description.abstract":["The rapid advancements in AI-generated models for image generation have transformed image creation from entertainment to e-commerce, making robust evaluation essential. We designed and statistically validated a human study for assessing the photorealism and image quality of AI-generated images. The study indicated that camera images show more realism, while AI images, such as those generated by DALL-E2, excel in quality. Further analysis showed that existing metrics deviate from human judgments. To address this, we developed the Global-Local Image Perceptual Score (GLIPS), which evaluates photorealistic quality using Vision Transformer-based attention for local similarity and Maximum Mean Discrepancy (MMD) for global distributional similarity. Our evaluation showed that GLIPS aligns more closely with human perception compared to traditional metrics like FID and SSIM for photorealism, although MS-SSIM outperformed in image quality. Additionally, we introduced the Interpolative Binning Scale (IBS) for human-assisted metric scaling with human scores."],"dc:identifier.uri":["https://hdl.handle.net/20.500.14721/36062"],"dc:language.iso":["en_ca"],"dc:publisher":["The University of Western Ontario"],"dc:subject":["Photorealistic Image Quality","DALLE","Stable Difusion","Interpolative Binning Scale","GLIPS"],"dc:title":["ASSESSMENT OF AI-GENERATED IMAGES USING COMPUTATIONAL METRICS AND HUMAN CENTRIC ANALYSIS"],"dc:type":["thesis"],"thesis:degree_discipline":["Computer Science"],"thesis:degree_name":["M Sc"]},"updated_at":"2026-07-27T21:56:20Z"}