Radon-Gabor Barcodes for Medical Image Retrieval

TL;DR

This paper introduces Radon-Gabor barcodes, a new binary feature extraction method combining Radon and Gabor transforms, to improve medical image retrieval robustness against variations and noise.

Contribution

It presents two novel barcode techniques, GRIBCs and GRGBCs, that leverage combined Radon-Gabor features for enhanced image annotation and retrieval.

Findings

Achieved approximately 81% retrieval accuracy on IRMA dataset.

Low total error scores of 322 and 330 for the two methods.

Demonstrated robustness against scale, rotation, noise, and illumination changes.

Abstract

In recent years, with the explosion of digital images on the Web, content-based retrieval has emerged as a significant research area. Shapes, textures, edges and segments may play a key role in describing the content of an image. Radon and Gabor transforms are both powerful techniques that have been widely studied to extract shape-texture-based information. The combined Radon-Gabor features may be more robust against scale/rotation variations, presence of noise, and illumination changes. The objective of this paper is to harness the potentials of both Gabor and Radon transforms in order to introduce expressive binary features, called barcodes, for image annotation/tagging tasks. We propose two different techniques: Gabor-of-Radon-Image Barcodes (GRIBCs), and Guided-Radon-of-Gabor Barcodes (GRGBCs). For validation, we employ the IRMA x-ray dataset with 193 classes, containing 12,677 training images and 1,733 test images. A total error score as low as 322 and 330 were achieved for GRGBCs and GRIBCs, respectively. This corresponds to $\approx 81\%$ retrieval accuracy for the first hit.