An improved seam carving method for enhancing the visual field of tunnel vision patients

TL;DR

This paper introduces a modified seam carving method to improve the visual field for tunnel vision patients by preserving important image details.

Contribution

The novel contribution is a multiscale image fusion-based seam carving method that improves visual retargeting for tunnel vision patients.

Findings

The method achieved a 30.8% improvement in composite quality metrics over existing retargeting methods.

Statistical analysis confirmed significant improvements in structural, perceptual, and feature-based metrics (p<0.001).

Abstract

Visual impairment has various forms all of which negatively affect the patient’s daily activities and prevent performing simple actions like walking safely in a street. Content-aware image retargeting can be used to enhance the scene for patients who have limited visual field i.e. tunnel vision. A modified Seam Carving method is presented in this research paper which can decrease the width of the input image to fit in the patient’s angle of vision while preserving the important objects in the original image as well as the image details. The method enhanced the original Seam Carving by calculating the energy map using multiscale image fusion that combines depth, saliency, foreground segmentation, and edge detection features, and used a forward-middle approach for the seam removal step. The results showed efficiency that outperformed various retargeting methods, achieving a 30.8% improvement in the composite score that integrates structural, perceptual, and feature-based quality metrics. Statistical analysis using paired t-tests (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$n = 73$$\end{document}) confirmed statistically significant improvements across all major metrics (\documentclass[12pt]{minimal}
\usepackage{amsmath}
\usepackage{wasysym}
\usepackage{amsfonts}
\usepackage{amssymb}
\usepackage{amsbsy}
\usepackage{mathrsfs}
\usepackage{upgreek}
\setlength{\oddsidemargin}{-69pt}
\begin{document}$$p<0.001$$\end{document}), including SSIM, SIFT feature matching, and modern deep learning-based perceptual quality metrics, compared to the baseline seam carving method.

Figures