Deep Discriminant Analysis in binary segmentation of images

Image segmentation is a fundamental task in image processing, with applications ranging from medical imaging to autonomous systems. This thesis introduces a novel Deep Discriminant Analysis (DDA) loss, which integrates classical discriminant analysis principles into deep neural networks to increase...

Full description

Bibliographic Details
Author: Sztamborski, Adam
Format: master thesis
Publication Date:2025
Country:España
Institution:Universitat Politècnica de Catalunya (UPC)
Repository:UPCommons. Portal del coneixement obert de la UPC
Language:English
OAI Identifier:oai:upcommons.upc.edu:2117/445045
Online Access:https://hdl.handle.net/2117/445045
Access Level:Open access
Keyword:Computer vision
Deep learning
Machine learning
Imaging systems in medicine
Deep Discriminant Analysis
Discriminant loss
Fisher criterion
Image segmentation
U-Net
Convolutional neural networks
Dichotomous image segmentation
Anàlisi discriminant profunda
Pèrdua discriminant
Criteri de Fisher
Segmentació d'imatges
Aprenentatge profund
Segmentació dicotòmica d'imatges
Visió per ordinador
Aprenentatge automàtic
Imatgeria mèdica
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
Description
Summary:Image segmentation is a fundamental task in image processing, with applications ranging from medical imaging to autonomous systems. This thesis introduces a novel Deep Discriminant Analysis (DDA) loss, which integrates classical discriminant analysis principles into deep neural networks to increase class separability in segmentation tasks. The proposed loss encourages the network to produce wellseparated representations of foreground and background pixels in the learned feature space, leading to more discriminative and interpretable representations. The effectiveness of the DDA loss is first validated on synthetic and simple classi-cation problems, then evaluated on the challenging DIS5K dataset using a tailored U-Net architecture. Experimental results demonstrate consistent improvements over the standard Binary Cross-Entropy (BCE) loss, yielding faster convergence, higher separability, and superior segmentation metrics across multiple test subsets. All experiments are carried out using publicly available datasets and open-source frameworks, with careful consideration of reproducibility, computational efficiency, and ethical standards. These findings confirm that discriminant analysis principles can be effectively embedded within deep architectures, offering a practical enhancement to contemporary segmentation methods.