Framework for image search in visual databases using keypoints, their descriptors and geometric constraints
Image matching and retrieval is one of the most important areas of computer vision. The key objective of image matching is detection of near-duplicate images. This chapter discusses an extension of this concept, namely, the retrieval of near-duplicate image fragments. We assume no a’priori informati...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/44206 |
| _version_ | 1826112668481617920 |
|---|---|
| author | Ang, Zixuan |
| author2 | Andrzej Stefan Sluzek |
| author_facet | Andrzej Stefan Sluzek Ang, Zixuan |
| author_sort | Ang, Zixuan |
| collection | NTU |
| description | Image matching and retrieval is one of the most important areas of computer vision. The key objective of image matching is detection of near-duplicate images. This chapter discusses an extension of this concept, namely, the retrieval of near-duplicate image fragments. We assume no a’priori information about visual contents of those fragments. The number of such fragments in an image is also unknown.
Therefore, we address the problem and propose the solution based purely on
visual characteristics of image fragments. The method combines two
techniques: a local image analysis and a global geometry synthesis. In the
former stage, we analyze low-level image characteristics, such as local
intensity gradients or local shape approximations. In the latter stage, we
formulate global geometrical hypotheses about the image contents and verify
them using a probabilistic framework. |
| first_indexed | 2024-10-01T03:10:51Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/44206 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:10:51Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/442062023-03-03T20:48:11Z Framework for image search in visual databases using keypoints, their descriptors and geometric constraints Ang, Zixuan Andrzej Stefan Sluzek School of Computer Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval Image matching and retrieval is one of the most important areas of computer vision. The key objective of image matching is detection of near-duplicate images. This chapter discusses an extension of this concept, namely, the retrieval of near-duplicate image fragments. We assume no a’priori information about visual contents of those fragments. The number of such fragments in an image is also unknown. Therefore, we address the problem and propose the solution based purely on visual characteristics of image fragments. The method combines two techniques: a local image analysis and a global geometry synthesis. In the former stage, we analyze low-level image characteristics, such as local intensity gradients or local shape approximations. In the latter stage, we formulate global geometrical hypotheses about the image contents and verify them using a probabilistic framework. Bachelor of Engineering (Computer Engineering) 2011-05-31T02:40:54Z 2011-05-31T02:40:54Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/44206 en Nanyang Technological University 42 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval Ang, Zixuan Framework for image search in visual databases using keypoints, their descriptors and geometric constraints |
| title | Framework for image search in visual databases using keypoints, their descriptors and geometric constraints |
| title_full | Framework for image search in visual databases using keypoints, their descriptors and geometric constraints |
| title_fullStr | Framework for image search in visual databases using keypoints, their descriptors and geometric constraints |
| title_full_unstemmed | Framework for image search in visual databases using keypoints, their descriptors and geometric constraints |
| title_short | Framework for image search in visual databases using keypoints, their descriptors and geometric constraints |
| title_sort | framework for image search in visual databases using keypoints their descriptors and geometric constraints |
| topic | DRNTU::Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval |
| url | http://hdl.handle.net/10356/44206 |
| work_keys_str_mv | AT angzixuan frameworkforimagesearchinvisualdatabasesusingkeypointstheirdescriptorsandgeometricconstraints |