Automatic stitching program of x-ray images using the Harris corner detection

Authors

  • Thanakrit Chanchayanon Radiological Technology Program, Faculty of Medicine, Prince of Songkla University
  • Affan Bueraheng Radiological Technology Program, Faculty of Medicine, Prince of Songkla University
  • Jonwgat Cheewakul Radiological Technology Program, Faculty of Medicine, Prince of Songkla University
  • Natee Ina Radiological Technology Program, Faculty of Medicine, Prince of Songkla University

Keywords:

Harris corner detection, images stitching, x-ray images

Abstract

The purposes of this research were to develop a new method of x-ray images stitching by Harris corner detection, and to compare the proposed methods with the correlation coefficient method and the commercial software of the SAMSUNG x-ray machine. We studied using two parts of the lower limb anthropomorphic phantoms. The image stitching accuracy test was then performed and compared with the correlation coefficient method. We used the images that were stitched by the software of the SAMSUNG x-ray machine as the gold standard. The experimental results were compared with previous methods by analyzing based on the same database. It was demonstrated that the error length of 1.14% and the accuracy of 99.43% with 58.39 seconds of image stitching time was found for the images stitched by Harris corner detection. The error length of 3.90% and the accuracy of 61.27% with 12.67 seconds of image stitching time was found for the correlation coefficient method.

Downloads

Download data is not yet available.

References

Chen C, Kojcev R, Haschtmann D, et al. Ruler Based Automatic C-Arm Image Stitching Without Overlapping Constraint. J Digit Imaging 2015;28:474–80.

Wang L, Traub J, Heining SM, et al. Long bone X-ray image stitching using Camera Augmented Mobile C-arm. MICCAI 2008;11:578–86.

Kim BS, Choi WJ, Kim YS, et al. Total ankle replacement in moderate to severe varus deformity of the ankle. The Journal of Bone and Joint Surgery British volume 2009;91-B:1183–90.

Yang F, He Y, Deng ZS, et al. Improvement of automated image stitching system for DR X-ray images. Comput Biol Med 2016;71:108–114.

Samsudin S, Adwan S, Arof H, et al. Development of automated image stitching system for radiographic images. J Digit Imaging 2013;26:361–70.

Le M-H, Woo B-S, Jo K-H. A Comparison of SIFT and Harris conner features for correspondence points matching. 2011 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2011;1–4.

ถิรวุฒิ โรจนอัมพวัน, พรชัย พฤกษ์ภัทรานนต์, สาวิตร์ ตัณฑนุช, นัที อินา, จงวัฒน์ ชีวกุล. การประเมินเทคนิคสัมประสิทธิ์สหสัมพันธ์สาหรับเชื่อมต่อภาพถ่ายทางรังสีเพื่อการวินิจฉัย กระดูกรยางค์. วารสารวิศวกรรมศาสตร์ มหาวิทยาลัยเทคโนโลยีราชมงคลล้านนา 2018;2.

Adwan S, Alsaleh I, Majed R. A new approach for image stitching technique using Dynamic Time Warping (DTW) algorithm towards scoliosis X-ray diagnosis. Measurement 2016;84:32–46.

Chandratre R, Chakkarwar VA. Image Stitching using Harris Feature Detection and Random Sampling. International Journal of Computer Applications 2014;89:0975–8887.

Le M-H, Woo B-S, Jo K-H. A Comparison of SIFT and Harris conner features for correspondence points matching. 2011 17th Korea-Japan Joint Workshop on Frontiers of Computer Vision (FCV) 2011;1–4.

การเปรียบเทียบภาพที่ผ่านการเชื่อมต่อโดยวิธี ของซอฟต์แวร์เครื่องเอกซเรย์ซัมซุง (A) และวิธีการตรวจจับ มุมแบบฮาร์ริส (B)

Downloads

Published

2021-02-01

How to Cite

1.
Chanchayanon T, Bueraheng A, Cheewakul J, Ina N. Automatic stitching program of x-ray images using the Harris corner detection. Thai J Rad Tech [Internet]. 2021 Feb. 1 [cited 2024 Dec. 5];45(1):13-21. Available from: https://he02.tci-thaijo.org/index.php/tjrt/article/view/248109

Issue

Section

Original articles