Feature Based Registration for Panoramic Image Generation
The construction of large, high-resolution view is an active area of research in many fields like computer vision and computer graphics. This research is concerned with combining multiple images with overlapping region to produce a panoramic view by the detection of feature points for images with different camera motion in an efficient and fast way. Feature extraction is an important and critical step in panoramic view construction. This study presents techniques of corner detection, geometric moments and random sampling to accurately locate the important feature points in the images under noise, transformation, lighting, little viewpoint changes, blurring and compression circumstances. For each extracted feature in the image, a descriptor is calculated and the matching is done based on the homograph transformation. The results of experiments conducted on images taken by handheld camera and images taken from the internet. The results show that the proposed algorithm is fast and efficient compared with the panorama generation using the most famous SIFT method.
Keywords: Feature extraction, motion estimation, registration, panoramic image.
Download Full-Text
ABOUT THE AUTHORS
Kawther Abbas Sallal
Kawther Abbas Sallal received the B.S. and M.Sc. in computer science from University of Technology, Baghdad, Iraq in 2003 and 2006 respectively. She is now preparing for PHD degree in computer science in Babylon University, Babylon, Iraq. Her interests include image processing, computer vision, video processing, computer graphics, biometrics and data security.
Abdul-Monem Saleh Rahma
Abdul-Monem Saleh Rahma is currently a professor and head of the computer sciences Department, University of Technology, Baghdad, Iraq. He received his M.Sc. degree from Brunel University, UK in 1982 and his PHD degree from Loughborough University of Technology, UK in 1985. He published more than 100 papers in computer science and supervised on more than 24 PHD and 57 M.Sc. students. His research interests focus on image processing, video processing, computer graphics, biometrics and computer security.
Kawther Abbas Sallal
Kawther Abbas Sallal received the B.S. and M.Sc. in computer science from University of Technology, Baghdad, Iraq in 2003 and 2006 respectively. She is now preparing for PHD degree in computer science in Babylon University, Babylon, Iraq. Her interests include image processing, computer vision, video processing, computer graphics, biometrics and data security.
Abdul-Monem Saleh Rahma
Abdul-Monem Saleh Rahma is currently a professor and head of the computer sciences Department, University of Technology, Baghdad, Iraq. He received his M.Sc. degree from Brunel University, UK in 1982 and his PHD degree from Loughborough University of Technology, UK in 1985. He published more than 100 papers in computer science and supervised on more than 24 PHD and 57 M.Sc. students. His research interests focus on image processing, video processing, computer graphics, biometrics and computer security.
