Robust Image Segmentation in Low Depth Of Field Images

TL;DR

This paper introduces a parameterless, fully automatic segmentation algorithm for low depth of field images, enhancing object detection robustness without manual parameter tuning, validated on real-world datasets.

Contribution

The paper presents a novel, parameterless segmentation method specifically designed for low DOF images, outperforming existing techniques in robustness.

Findings

Superior robustness compared to similar methods

No manual parameter tuning required

Effective on real-world high and low DOF images

Abstract

In photography, low depth of field (DOF) is an important technique to emphasize the object of interest (OOI) within an image. Thus, low DOF images are widely used in the application area of macro, portrait or sports photography. When viewing a low DOF image, the viewer implicitly concentrates on the regions that are sharper regions of the image and thus segments the image into regions of interest and non regions of interest which has a major impact on the perception of the image. Thus, a robust algorithm for the fully automatic detection of the OOI in low DOF images provides valuable information for subsequent image processing and image retrieval. In this paper we propose a robust and parameterless algorithm for the fully automatic segmentation of low DOF images. We compare our method with three similar methods and show the superior robustness even though our algorithm does not require any parameters to be set by hand. The experiments are conducted on a real world data set with high and low DOF images.