Image augmentation with conformal mappings for a convolutional neural network

DOI10.1007/S40314-023-02501-9arXiv2212.05258MaRDI QIDQ6184797FDOQ6184797

Authors: Oona Rainio, M. M. S. Nasser, M. Vuorinen, Riku Klén 

Publication date: 5 January 2024

Published in: Computational and Applied Mathematics (Search for Journal in Brave)

Abstract: For augmentation of the square-shaped image data of a convolutional neural network (CNN), we introduce a new method, in which the original images are mapped onto a disk with a conformal mapping, rotated around the center of this disk and mapped under such a M"obius transformation that preserves the disk, and then mapped back onto their original square shape. This process does not result the loss of information caused by removing areas from near the edges of the original images unlike the typical transformations used in the data augmentation for a CNN. We offer here the formulas of all the mappings needed together with detailed instructions how to write a code for transforming the images. The new method is also tested with simulated data and, according the results, using this method to augment the training data of 10 images into 40 images decreases the amount of the error in the predictions by a CNN for a test set of 160 images in a statistically significant way (p-value=0.0360).

Full work available at URL: https://arxiv.org/abs/2212.05258

Recommendations

• A full stage data augmentation method in deep convolutional neural network for natural image classification
• Image analysis by conformal embedding
• A Note on the Regularity of Images Generated by Convolutional Neural Networks
• Perceptual Adversarial Networks for Image-to-Image Transformation
• Image morphing in deep feature spaces: theory and applications

zbMATH Keywords

deep learningconformal mappingconvolutional neural networkimage augmentation

Mathematics Subject Classification ID

Computing methodologies for image processing (68U10) Schwarz-Christoffel-type mappings (30C30)

Cites Work

• NIST handbook of mathematical functions
• Title not available (Why is that?)
• Title not available (Why is that?)
• Schwarz-Christoffel Mapping
• Title not available (Why is that?)
• Title not available (Why is that?)
• Handbook of conformal mappings and applications

Cited In (1)

• A full stage data augmentation method in deep convolutional neural network for natural image classification

This page was built for publication: Image augmentation with conformal mappings for a convolutional neural network

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6184797)