Automatic object segmentation using perceptual grouping of regions with contextual constraints
Image segmentation is still considered a very challenging subject despite years of research effort poured into the field. The problem is exacerbated when there is need for specific object detection. Since objects can be visually non-homogeneous, techniques that attempt to segment images into visuall...
| Main Authors: | , , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
IEEE
2015
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/56313/1/Automatic%20object%20segmentation%20using%20perceptual%20grouping%20of%20regions%20with%20contextual%20constraints.pdf |
| _version_ | 1825931391412469760 |
|---|---|
| author | Zand, Mohsen C. Doraisamy, Shyamala Abdul Halin, Alfian Mustaffa, Mas Rina |
| author_facet | Zand, Mohsen C. Doraisamy, Shyamala Abdul Halin, Alfian Mustaffa, Mas Rina |
| author_sort | Zand, Mohsen |
| collection | UPM |
| description | Image segmentation is still considered a very challenging subject despite years of research effort poured into the field. The problem is exacerbated when there is need for specific object detection. Since objects can be visually non-homogeneous, techniques that attempt to segment images into visually uniform regions using only the bottom-up cues, tend to fail. We propose a novel two-step model that incorporates both bottom-up information and top-down object constraints. Firstly, a set of uniform regions are generated using an extension of contour detection, seeded region growing, and graph-based methods. The second step applies co-occurrence constraints on the image regions in order to perceptually group regions into objects. This unsupervised segmentation process models each object using higher-level knowledge in the form of visual co-occurrences of its constituent parts. Experiments on the horse and ImageCLEF databases show that the proposed technique performs comparably well with existing state-of-the-art techniques. |
| first_indexed | 2024-03-06T09:26:02Z |
| format | Conference or Workshop Item |
| id | upm.eprints-56313 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T09:26:02Z |
| publishDate | 2015 |
| publisher | IEEE |
| record_format | dspace |
| spelling | upm.eprints-563132017-07-31T05:22:13Z http://psasir.upm.edu.my/id/eprint/56313/ Automatic object segmentation using perceptual grouping of regions with contextual constraints Zand, Mohsen C. Doraisamy, Shyamala Abdul Halin, Alfian Mustaffa, Mas Rina Image segmentation is still considered a very challenging subject despite years of research effort poured into the field. The problem is exacerbated when there is need for specific object detection. Since objects can be visually non-homogeneous, techniques that attempt to segment images into visually uniform regions using only the bottom-up cues, tend to fail. We propose a novel two-step model that incorporates both bottom-up information and top-down object constraints. Firstly, a set of uniform regions are generated using an extension of contour detection, seeded region growing, and graph-based methods. The second step applies co-occurrence constraints on the image regions in order to perceptually group regions into objects. This unsupervised segmentation process models each object using higher-level knowledge in the form of visual co-occurrences of its constituent parts. Experiments on the horse and ImageCLEF databases show that the proposed technique performs comparably well with existing state-of-the-art techniques. IEEE 2015 Conference or Workshop Item PeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/56313/1/Automatic%20object%20segmentation%20using%20perceptual%20grouping%20of%20regions%20with%20contextual%20constraints.pdf Zand, Mohsen and C. Doraisamy, Shyamala and Abdul Halin, Alfian and Mustaffa, Mas Rina (2015) Automatic object segmentation using perceptual grouping of regions with contextual constraints. In: 5th International Conference on Image Processing, Theory, Tools and Applications 2015 (IPTA 2015), 10-13 Nov. 2015, Orleans, France. (pp. 530-534). 10.1109/IPTA.2015.7367203 |
| spellingShingle | Zand, Mohsen C. Doraisamy, Shyamala Abdul Halin, Alfian Mustaffa, Mas Rina Automatic object segmentation using perceptual grouping of regions with contextual constraints |
| title | Automatic object segmentation using perceptual grouping of regions with contextual constraints |
| title_full | Automatic object segmentation using perceptual grouping of regions with contextual constraints |
| title_fullStr | Automatic object segmentation using perceptual grouping of regions with contextual constraints |
| title_full_unstemmed | Automatic object segmentation using perceptual grouping of regions with contextual constraints |
| title_short | Automatic object segmentation using perceptual grouping of regions with contextual constraints |
| title_sort | automatic object segmentation using perceptual grouping of regions with contextual constraints |
| url | http://psasir.upm.edu.my/id/eprint/56313/1/Automatic%20object%20segmentation%20using%20perceptual%20grouping%20of%20regions%20with%20contextual%20constraints.pdf |
| work_keys_str_mv | AT zandmohsen automaticobjectsegmentationusingperceptualgroupingofregionswithcontextualconstraints AT cdoraisamyshyamala automaticobjectsegmentationusingperceptualgroupingofregionswithcontextualconstraints AT abdulhalinalfian automaticobjectsegmentationusingperceptualgroupingofregionswithcontextualconstraints AT mustaffamasrina automaticobjectsegmentationusingperceptualgroupingofregionswithcontextualconstraints |