Parameter recovery using Radon transform

Komal Komal, Nandita Bhattacharjee, David Albrecht, Bala Srinivasan

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearch


In computer vision, alignment of images plays an important role in different day to day life applications by bringing similar points of images into correspondence. Conventionally, images are aligned by using the extracted features of images. However, the extraction of features is difficult, time consuming and not suitable for low quality images. Whereas pixel based alignment methods are applicable to low quality images and do not require extensive image processing applications. However, these methods are computationally exhaustive that makes it difficult to use for real time applications. Therefore, we need a pixel based method for image alignment that can overcome the limitations of computational complexity. In this paper, we have proposed an efficient Radon transform based method to compute the transformation parameters between two images for aligning them. Moreover, the proposed approach is verified on test images of varying classes and results demonstrate that the proposed method can compute the parameters accurately and efficiently as compared to the existing approaches.

Original languageEnglish
Title of host publicationMoMM 2018 - The 16th International Conference on Advances in Mobile Computing and Multimedia
Subtitle of host publicationNovember 19 - 21, 2018 Yogyakarta, Indonesia
EditorsPari Delir Haghighi, Ivan Luiz Salvadori, Matthias Steinbauer, Ismail Khalil, Gabriele Anderst-Kotsis
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages10
ISBN (Electronic)9781450364522
Publication statusPublished - 2018
EventInternational Conference on Advances in Mobile Computing and Multimedia 2018 - Yogyakarta, Indonesia
Duration: 19 Nov 201821 Nov 2018
Conference number: 16th (Proceedings)


ConferenceInternational Conference on Advances in Mobile Computing and Multimedia 2018
Abbreviated titleMoMM 2018
Internet address

Cite this