Image Segmentation and Labeling Using Free-Form Semantic Annotation
(2014) 22nd International Conference on Pattern Recognition (ICPR 2014) p.2281-2286- Abstract
- In this paper we investigate the problem of segmenting images using the information in text annotations. In contrast to the general image understanding problem, this type of annotation guided segmentation is less ill-posed in the sense that for the output there is higher consensus among human annotations. In the paper we present a system based on a combined visual and semantic pipeline. In the visual pipeline, a list of tentative figure-ground segmentations is first proposed. Each such segmentation is classified into a set of visual categories. In the natural language processing pipeline, the text is parsed and chunked into objects. Each chunk is then compared with the visual categories and the relative distance is computed using the... (More)
- In this paper we investigate the problem of segmenting images using the information in text annotations. In contrast to the general image understanding problem, this type of annotation guided segmentation is less ill-posed in the sense that for the output there is higher consensus among human annotations. In the paper we present a system based on a combined visual and semantic pipeline. In the visual pipeline, a list of tentative figure-ground segmentations is first proposed. Each such segmentation is classified into a set of visual categories. In the natural language processing pipeline, the text is parsed and chunked into objects. Each chunk is then compared with the visual categories and the relative distance is computed using the word-net structure. The final choice of segments and their correspondence to the chunked objects are then obtained using combinatorial optimization. The output is compared to manually annotated ground-truth images. The results are promising and there are several interesting avenues for continued research. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/5052492
- author
- Tegen, Agnes ; Weegar, Rebecka ; Hammarlund, Linus ; Oskarsson, Magnus LU ; Jiang, Fangyuan LU ; Medved, Dennis LU ; Nugues, Pierre LU and Åström, Karl LU
- organization
- publishing date
- 2014
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- [Host publication title missing]
- pages
- 2281 - 2286
- publisher
- IEEE - Institute of Electrical and Electronics Engineers Inc.
- conference name
- 22nd International Conference on Pattern Recognition (ICPR 2014)
- conference location
- Stockholm, Sweden
- conference dates
- 2014-08-24 - 2014-08-28
- external identifiers
-
- wos:000359818002067
- scopus:84919946714
- ISSN
- 1051-4651
- DOI
- 10.1109/ICPR.2014.396
- language
- English
- LU publication?
- yes
- id
- 84497869-1395-4fe4-a472-79cbd9dd2bfe (old id 5052492)
- date added to LUP
- 2016-04-01 14:29:30
- date last changed
- 2022-01-28 00:51:54
@inproceedings{84497869-1395-4fe4-a472-79cbd9dd2bfe, abstract = {{In this paper we investigate the problem of segmenting images using the information in text annotations. In contrast to the general image understanding problem, this type of annotation guided segmentation is less ill-posed in the sense that for the output there is higher consensus among human annotations. In the paper we present a system based on a combined visual and semantic pipeline. In the visual pipeline, a list of tentative figure-ground segmentations is first proposed. Each such segmentation is classified into a set of visual categories. In the natural language processing pipeline, the text is parsed and chunked into objects. Each chunk is then compared with the visual categories and the relative distance is computed using the word-net structure. The final choice of segments and their correspondence to the chunked objects are then obtained using combinatorial optimization. The output is compared to manually annotated ground-truth images. The results are promising and there are several interesting avenues for continued research.}}, author = {{Tegen, Agnes and Weegar, Rebecka and Hammarlund, Linus and Oskarsson, Magnus and Jiang, Fangyuan and Medved, Dennis and Nugues, Pierre and Åström, Karl}}, booktitle = {{[Host publication title missing]}}, issn = {{1051-4651}}, language = {{eng}}, pages = {{2281--2286}}, publisher = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}}, title = {{Image Segmentation and Labeling Using Free-Form Semantic Annotation}}, url = {{http://dx.doi.org/10.1109/ICPR.2014.396}}, doi = {{10.1109/ICPR.2014.396}}, year = {{2014}}, }