Inverse Quantum Fourier Transform Inspired Algorithm for Unsupervised Image Segmentation
This work addresses image segmentation for computer vision applications by introducing a novel quantum-inspired method that is incremental, as it adapts IQFT to a new domain but builds on existing segmentation benchmarks.
The authors tackled unsupervised image segmentation by proposing an inverse quantum Fourier transform (IQFT)-inspired algorithm that encodes pixel intensity into qubit phases and applies IQFT for automatic classification, achieving up to 50% higher mean Intersection-Over-Union (mIOU) than K-means and Otsu-thresholding on PASCAL VOC 2012 and xVIEW2 datasets.
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).