| Author | Manandhar, Arun |
| Call Number | AIT Thesis no.CS-93-24 |
| Subject(s) | Image processing
|
| Note | A thesis submitted in partial fulfilment of the requirement for the degree of Master of Science |
| Publisher | Asian Institute of Technology |
| Abstract | Automatically finding the corresponding features in different images is one of the
central problem in photogrammetry and computer and machine vision. Correspondence is
necessary for 2D and 3-D measurement of an object for objection detection, classification and
identification. One of the steps towards solving this correspondence problem is the main aim
of the study.
Basically, area-based matching method has been adopted to match a new data set i.e.
three line stereo scanner imagery of Sinjuku, Tokyo city, Japan because of some of its
advantage over feature based matching. An adaptive least square correlation technique which
is area based has been fully utilized and algorithm for this technique has been developed and
implemented. Prior to matching, the algorithm for preprocessing of images by using Wallis
filter, selection of matched points in the template image by using interest operator and finding
approximate value in other search images have been developed and implemented. The result
are analyzed and discussed. |
| Year | 1993 |
| Type | Thesis |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Computer Science (CS) |
| Chairperson(s) | Murai, Shunji; |
| Examination Committee(s) | Huynh, Ngoc Phien;Yulu, Qi; |
| Scholarship Donor(s) | DAAD, Germany; |
| Degree | Thesis (M.Sc.) - Asian Institute of Technology, 1993 |