Mobile media annotation, search and retrieval
Image annotation has been extensively researched upon, and is an important influence in image search and retrieval. This final year project aims to investigate different approaches to image annotation, by contextual information annotation and content-based image retrieval. For the first aspect, the...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Final Year Project (FYP) |
| Language: | English |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/45802 |
| _version_ | 1826120974372700160 |
|---|---|
| author | Chew, Siew Mooi. |
| author2 | Yap Kim Hui |
| author_facet | Yap Kim Hui Chew, Siew Mooi. |
| author_sort | Chew, Siew Mooi. |
| collection | NTU |
| description | Image annotation has been extensively researched upon, and is an important influence in image search and retrieval. This final year project aims to investigate different approaches to image annotation, by contextual information annotation and content-based image retrieval. For the first aspect, the Gaussian Mixture Models have been used effectively to represent keywords and time information of the images in the database, and could be used in exploring further on integration of contextual information to create an accurate automated image annotation process. For the aspect on content-based search, the effects of scene recognition using color SIFT descriptors were investigated. Color SIFT descriptors have been used for local feature representation after the Harris Laplace salient point or dense sampling detectors have been executed for feature extraction. The Bag of Words framework is adapted, and each image is represented by a set of local features plotted over a histogram. The hierarchical k-means approach is used in clustering, and the Support Vector Machine is used in machine learning. These methods were selected from previous works, which proved their robustness as compared to other techniques. From the testing results, it is proven from our database of scene categories that the descriptors OpponentSIFT and CSIFT performed better, and the dense sampling approach also yielded better results. |
| first_indexed | 2024-10-01T05:25:11Z |
| format | Final Year Project (FYP) |
| id | ntu-10356/45802 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T05:25:11Z |
| publishDate | 2011 |
| record_format | dspace |
| spelling | ntu-10356/458022023-07-07T16:14:45Z Mobile media annotation, search and retrieval Chew, Siew Mooi. Yap Kim Hui School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval Image annotation has been extensively researched upon, and is an important influence in image search and retrieval. This final year project aims to investigate different approaches to image annotation, by contextual information annotation and content-based image retrieval. For the first aspect, the Gaussian Mixture Models have been used effectively to represent keywords and time information of the images in the database, and could be used in exploring further on integration of contextual information to create an accurate automated image annotation process. For the aspect on content-based search, the effects of scene recognition using color SIFT descriptors were investigated. Color SIFT descriptors have been used for local feature representation after the Harris Laplace salient point or dense sampling detectors have been executed for feature extraction. The Bag of Words framework is adapted, and each image is represented by a set of local features plotted over a histogram. The hierarchical k-means approach is used in clustering, and the Support Vector Machine is used in machine learning. These methods were selected from previous works, which proved their robustness as compared to other techniques. From the testing results, it is proven from our database of scene categories that the descriptors OpponentSIFT and CSIFT performed better, and the dense sampling approach also yielded better results. Bachelor of Engineering 2011-06-22T01:16:53Z 2011-06-22T01:16:53Z 2011 2011 Final Year Project (FYP) http://hdl.handle.net/10356/45802 en Nanyang Technological University 79 p. application/pdf |
| spellingShingle | DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval Chew, Siew Mooi. Mobile media annotation, search and retrieval |
| title | Mobile media annotation, search and retrieval |
| title_full | Mobile media annotation, search and retrieval |
| title_fullStr | Mobile media annotation, search and retrieval |
| title_full_unstemmed | Mobile media annotation, search and retrieval |
| title_short | Mobile media annotation, search and retrieval |
| title_sort | mobile media annotation search and retrieval |
| topic | DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval |
| url | http://hdl.handle.net/10356/45802 |
| work_keys_str_mv | AT chewsiewmooi mobilemediaannotationsearchandretrieval |