Inverse Quantum Fourier Transform Inspired Algorithm for Unsupervised Image Segmentation

TL;DR

This paper introduces a novel unsupervised image segmentation algorithm inspired by inverse quantum Fourier transform (IQFT), leveraging quantum-inspired mathematical structures to classify image pixels efficiently without training.

Contribution

It is the first to utilize IQFT for unsupervised image segmentation, offering a low-cost, training-free method suitable for real-time applications.

Findings

Outperforms K-means and Otsu-thresholding on benchmark datasets.

Achieves up to 50% improvement in mean Intersection-Over-Union (mIOU).

Demonstrates efficiency and effectiveness in real-world segmentation tasks.

Abstract

Image segmentation is a very popular and important task in computer vision. In this paper, inverse quantum Fourier transform (IQFT) for image segmentation has been explored and a novel IQFT-inspired algorithm is proposed and implemented by leveraging the underlying mathematical structure of the IQFT. Specifically, the proposed method takes advantage of the phase information of the pixels in the image by encoding the pixels' intensity into qubit relative phases and applying IQFT to classify the pixels into different segments automatically and efficiently. To the best of our knowledge, this is the first attempt of using IQFT for unsupervised image segmentation. The proposed method has low computational cost comparing to the deep learning-based methods and more importantly it does not require training, thus make it suitable for real-time applications. The performance of the proposed method is compared with K-means and Otsu-thresholding. The proposed method outperforms both of them on the PASCAL VOC 2012 segmentation benchmark and the xVIEW2 challenge dataset by as much as 50% in terms of mean Intersection-Over-Union (mIOU).