A Modular Approach for Object Segmentation and Image Inpainting

Silva, Alexandre Santos

A Modular Approach for Object Segmentation and Image Inpainting

2025-10-22Master thesis

datacite.subject.fos	Engenharia e Tecnologia::Engenharia Eletrotécnica, Eletrónica e Informática
dc.contributor.advisor	Ribeiro, José Carlos Bregieiro
dc.contributor.advisor	Miragaia, Rolando Lúcio Germano
dc.contributor.advisor	Silva, Fernando José Mateus da
dc.contributor.advisor	Costa, Rogério Luís de Carvalho
dc.contributor.author	Silva, Alexandre Santos
dc.date.accessioned	2025-11-14T18:29:15Z
dc.date.available	2025-11-14T18:29:15Z
dc.date.issued	2025-10-22
dc.description.abstract	In this project, we propose ModInPainTor, a modular solution for object segmentation and removal in images. ModInPainTor takes advantage of advanced models from literature to deliver high-quality image inpainting results. This solution is inspired by InPainTor, a previous project that utilized a highly-integrated Convolutional Neural Network-based model for object detection and removal but lacked a comprehensive evaluation of its performance. We conduct a thorough evaluation of the InPainTor and ModInPainTor solutions, assessing their effectiveness in anonymizing visual data while maintaining data quality. The evaluation involves quantitative metrics to measure the quality of the results and a qualitative analysis to evaluate the visual quality of the anonymized images. Furthermore, we investigate the impact of object segmentation accuracy on the quality of the anonymized images. Our findings indicate that Mod- InPainTor significantly improves the visual quality of anonymized images compared to InPainTor, albeit with increased computational requirements. We find that the proposed solution could be effectively employed in industrial settings where anonymization quality is prioritized over computational efficiency.	eng
dc.description.sponsorship	PRR - Plano para a Recuperação e Resiliência for their financial support within the Sustainable Stone by Portugal project, Call: 2021-C05i0101- 02—agendas/alianças mobilizadoras para a reindustrialização - PRR, Proposal: C632482988- 00467016.
dc.identifier.tid	204050065
dc.identifier.uri	http://hdl.handle.net/10400.8/14628
dc.language.iso	eng
dc.rights.uri	http://creativecommons.org/licenses/by/4.0/
dc.subject	Anonymization
dc.subject	Image inpainting
dc.subject	Object segmentation
dc.subject	Object removal
dc.title	A Modular Approach for Object Segmentation and Image Inpainting
dc.title.alternative	Advanced Techniques of Artificial Intelligence and Computer Vision in Industrial Environments	por
dc.type	master thesis