Multiple Images Recovery Using a Single Affine Transformation

TL;DR

This paper introduces a novel corruption recovery transformation (CRT) model that uses a single affine transformation to recover multiple corrupted images, improving noise data recovery and image recognition accuracy.

Contribution

The paper presents a new CRT model that efficiently learns from data to recover multiple corrupted images with a single affine transformation, enhancing noise removal and recognition.

Findings

Effective recovery of noisy images demonstrated on six datasets.

Improved image recognition accuracy using the CRT model.

CRT can be efficiently learned and applied to new corrupted images.

Abstract

In many real-world applications, image data often come with noises, corruptions or large errors. One approach to deal with noise image data is to use data recovery techniques which aim to recover the true uncorrupted signals from the observed noise images. In this paper, we first introduce a novel corruption recovery transformation (CRT) model which aims to recover multiple (or a collection of) corrupted images using a single affine transformation. Then, we show that the introduced CRT can be efficiently constructed through learning from training data. Once CRT is learned, we can recover the true signals from the new incoming/test corrupted images explicitly. As an application, we apply our CRT to image recognition task. Experimental results on six image datasets demonstrate that the proposed CRT model is effective in recovering noise image data and thus leads to better recognition results.