Friday 29th of March 2024
 

Fast Image Registration Based on Features Extraction and Accurate Matching Points for Image Stitching


Maha Abdul-Rahman Hasso and Ruaa Moayad Elyas

The image registration is one step of the image stitching technique. This step plays an important role in the resulted stitch image. The image registration depends on the accuracy of its basics that is the feature detection and feature matching. This work is present an automatic algorithm to get a good final stitched image. The work main aim is to achieve a good quality stitched image obtained in less time. In this work, to reduce the time for feature detecting, SURF technique is mostly used algorithm as it is the fastest descriptor. RANSAC is applied for outlier elimination and to robustly estimate the best fitting homography, and at end homography transformation is used as transformation model to warp image with inverse warping. Good results are obtained after applying the presented method. The results are examined visually.

Keywords: Registration, stitching, homography, SURF, RANSAC.

Download Full-Text


ABOUT THE AUTHORS

Maha Abdul-Rahman Hasso
(Ph. D.) is currently a lecturer at Mosul University/ College of Computer Science and Mathematics/ Computer Science Department. She received B.Sc. degree in Computer Science from University of Mosul in 1991, M.Sc. degree from University of Mosul in 1998 and Ph. D. degree from University of Mosul in 2006. Her research interests and activity are in image processing, computer vision, pattern recognition, remote sensing applications and biometrics. Now, she teaches digital image processing, pattern recognition and visual programming for postgraduate and undergraduate students.

Ruaa Moayad Elyas
M.Sc. degree student in Mosul University/ College of Computer Science and Mathematics/ Computer Science Department


IJCSI Published Papers Indexed By:

 

 

 

 
+++
About IJCSI

IJCSI is a refereed open access international journal for scientific papers dealing in all areas of computer science research...

Learn more »
Join Us
FAQs

Read the most frequently asked questions about IJCSI.

Frequently Asked Questions (FAQs) »
Get in touch

Phone: +230 911 5482
Email: info@ijcsi.org

More contact details »