miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor
Axiomatically, symmetry is a fundamental property of mathematical functions defining similarity measures, where similarity measures are important tools in many areas of computer science, including machine learning and image processing. In this paper, we investigate a new technique to measure the sim...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-12-01
|
Series: | Symmetry |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-8994/12/12/2078 |
_version_ | 1797544663632052224 |
---|---|
author | Thuvanan Borvornvitchotikarn Werasak Kurutach |
author_facet | Thuvanan Borvornvitchotikarn Werasak Kurutach |
author_sort | Thuvanan Borvornvitchotikarn |
collection | DOAJ |
description | Axiomatically, symmetry is a fundamental property of mathematical functions defining similarity measures, where similarity measures are important tools in many areas of computer science, including machine learning and image processing. In this paper, we investigate a new technique to measure the similarity between two images, a fixed image and a moving image, in multi-modal image registration (MIR). MIR in medical image processing is essential and useful in diagnosis and therapy guidance, but still a very challenging task due to the lack of robustness against the rotational variance in the image transformation process. Our investigation leads to a novel, local self-similarity descriptor, called the modality-independent and rotation-invariant descriptor (miRID). By relying on the mean of the intensity values, an miRID is simply computable and can effectively handle the complicated intensity relationship between multi-modal images. Moreover, it can also overcome the problem of rotational variance by sorting the numerical values, each of which is the absolute difference between each pixel’s intensity and the mean of all pixel intensities within a patch of the image. The experimental result shows that our method outperforms others in both multi-modal rigid and non-rigid image registrations. |
first_indexed | 2024-03-10T14:03:46Z |
format | Article |
id | doaj.art-3a0df5ae7f7d41a1907563cbc3d8b568 |
institution | Directory Open Access Journal |
issn | 2073-8994 |
language | English |
last_indexed | 2024-03-10T14:03:46Z |
publishDate | 2020-12-01 |
publisher | MDPI AG |
record_format | Article |
series | Symmetry |
spelling | doaj.art-3a0df5ae7f7d41a1907563cbc3d8b5682023-11-21T00:49:03ZengMDPI AGSymmetry2073-89942020-12-011212207810.3390/sym12122078miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant DescriptorThuvanan Borvornvitchotikarn0Werasak Kurutach1Faculty of Information Science and Technology, Mahanakorn University of Technology, Bangkok 10530, ThailandFaculty of Information Science and Technology, Mahanakorn University of Technology, Bangkok 10530, ThailandAxiomatically, symmetry is a fundamental property of mathematical functions defining similarity measures, where similarity measures are important tools in many areas of computer science, including machine learning and image processing. In this paper, we investigate a new technique to measure the similarity between two images, a fixed image and a moving image, in multi-modal image registration (MIR). MIR in medical image processing is essential and useful in diagnosis and therapy guidance, but still a very challenging task due to the lack of robustness against the rotational variance in the image transformation process. Our investigation leads to a novel, local self-similarity descriptor, called the modality-independent and rotation-invariant descriptor (miRID). By relying on the mean of the intensity values, an miRID is simply computable and can effectively handle the complicated intensity relationship between multi-modal images. Moreover, it can also overcome the problem of rotational variance by sorting the numerical values, each of which is the absolute difference between each pixel’s intensity and the mean of all pixel intensities within a patch of the image. The experimental result shows that our method outperforms others in both multi-modal rigid and non-rigid image registrations.https://www.mdpi.com/2073-8994/12/12/2078multi-modal image registrationsimilarity measurerotation invariantlocal binary patterns |
spellingShingle | Thuvanan Borvornvitchotikarn Werasak Kurutach miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor Symmetry multi-modal image registration similarity measure rotation invariant local binary patterns |
title | miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor |
title_full | miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor |
title_fullStr | miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor |
title_full_unstemmed | miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor |
title_short | miRID: Multi-Modal Image Registration Using Modality-Independent and Rotation-Invariant Descriptor |
title_sort | mirid multi modal image registration using modality independent and rotation invariant descriptor |
topic | multi-modal image registration similarity measure rotation invariant local binary patterns |
url | https://www.mdpi.com/2073-8994/12/12/2078 |
work_keys_str_mv | AT thuvananborvornvitchotikarn miridmultimodalimageregistrationusingmodalityindependentandrotationinvariantdescriptor AT werasakkurutach miridmultimodalimageregistrationusingmodalityindependentandrotationinvariantdescriptor |