SAMF: Small-Area-Aware Multi-focus Image Fusion for Object Detection

TL;DR

This paper introduces SAMF, a novel small-area-aware multi-focus image fusion method that improves the detection of small focused regions and enhances object detection accuracy by segmenting and selectively fusing focus areas.

Contribution

The proposed algorithm uniquely segments images into focused, defocused, and uncertain regions, and employs a pixel selection rule to better preserve small focus areas for improved detection.

Findings

Outperforms existing methods in detecting small focus regions.

Enhances object detection accuracy in multi-focus images.

Accurately preserves uncertain transition regions.

Abstract

Existing multi-focus image fusion (MFIF) methods often fail to preserve the uncertain transition region and detect small focus areas within large defocused regions accurately. To address this issue, this study proposes a new small-area-aware MFIF algorithm for enhancing object detection capability. First, we enhance the pixel attributes within the small focus and boundary regions, which are subsequently combined with visual saliency detection to obtain the pre-fusion results used to discriminate the distribution of focused pixels. To accurately ensure pixel focus, we consider the source image as a combination of focused, defocused, and uncertain regions and propose a three-region segmentation strategy. Finally, we design an effective pixel selection rule to generate segmentation decision maps and obtain the final fusion results. Experiments demonstrated that the proposed method can accurately detect small and smooth focus areas while improving object detection performance, outperforming existing methods in both subjective and objective evaluations. The source code is available at https://github.com/ixilai/SAMF.