Optimized imaging prefiltering for enhanced image segmentation

2025-08-05

AI Summary

Traditional machine learning models suffer from limited performance in unsupervised or few-shot image segmentation due to insufficient labeled data and suboptimal feature representation. Method: We propose integrating the Box-Cox transformation as a learnable preprocessing module, with a focus on adaptive parameter estimation—replacing fixed or empirically chosen parameters with a statistics-driven algorithm that enhances inter-class separability and feature robustness. Contribution/Results: Experiments demonstrate substantial improvements in discriminant analysis-based segmentation: +8.2% average Dice score and 1.7× inference speedup. In contrast, deep learning models show negligible gains, underscoring the method’s unique efficacy under low-data regimes. To our knowledge, this is the first systematic study revealing how Box-Cox parameter selection differentially impacts segmentation paradigms—highlighting its value for lightweight, interpretable, and data-efficient preprocessing in medical and remote sensing imaging.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Dimensionality Reduction/Feature Selection
• Reasoning under Uncertainty: Graphical Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The Box-Cox transformation, introduced in 1964, is a widely used statistical tool for stabilizing variance and improving normality in data analysis. Its application in image processing, particularly for image enhancement, has gained increasing attention in recent years. This paper investigates the use of the Box-Cox transformation as a preprocessing step for image segmentation, with a focus on the estimation of the transformation parameter. We evaluate the effectiveness of the transformation by comparing various segmentation methods, highlighting its advantages for traditional machine learning techniques-especially in situations where no training data is available. The results demonstrate that the transformation enhances feature separability and computational efficiency, making it particularly beneficial for models like discriminant analysis. In contrast, deep learning models did not show consistent improvements, underscoring the differing impacts of the transformation across model types and image characteristics.

Problem

• Enhancing image segmentation via Box-Cox transformation preprocessing
• Optimizing parameter estimation for Box-Cox in image processing
• Comparing transformation effects on ML vs. deep learning models

Innovation

• Box-Cox transformation for image preprocessing
• Parameter estimation enhances feature separability
• Improves traditional ML without training data