polito.it
Politecnico di Torino (logo)

Enhanced Normalized Cuts with Spectral Weight Adjustment for Image Segmentation

Giacomo Bastiani

Enhanced Normalized Cuts with Spectral Weight Adjustment for Image Segmentation.

Rel. Edoardo Fadda. Politecnico di Torino, Corso di laurea magistrale in Ingegneria Matematica, 2024

[img]
Preview
PDF (Tesi_di_laurea) - Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives.

Download (9MB) | Preview
Abstract:

This work investigates an enhancement to the normalized cuts algorithm, introducing a preliminary spectral segmentation analysis to make the process of binary image segmentation more effective. In particular, we propose two improvements: (i) use the results of the proposed preliminary spectral clustering algorithm as a prior for the final segmentation (ii) use Bayesian optimization coupled with Gaussian processes to tunes the hyperparameters. Then, using the results from this procedure, and by maximizing a confidence measure it is possible to obtain a set of pixels belonging to the foreground and the background. These pixels are passed to a min-cut/max-flow algorithm as the source and sink nodes for further refinement, therefore automating the process of foreground/background pixel selection for this algorithm. Finally, the normalized cuts algorithm has been customized to perform video segmentation in real time. Experiments on a subset of the MSRA10K dataset and in different video conditions showed relevant improvements in segmentation quality and real-time usage. The proposed methodologies have the potential to be the starting point for more advanced techniques in fields requiring precise and efficient video segmentation, such as hand tracking.

Relators: Edoardo Fadda
Academic year: 2023/24
Publication type: Electronic
Number of Pages: 67
Subjects:
Corso di laurea: Corso di laurea magistrale in Ingegneria Matematica
Classe di laurea: New organization > Master science > LM-44 - MATHEMATICAL MODELLING FOR ENGINEERING
Aziende collaboratrici: UNSPECIFIED
URI: http://webthesis.biblio.polito.it/id/eprint/31612
Modify record (reserved for operators) Modify record (reserved for operators)