Skip to Main content Skip to Navigation
Conference papers

SEMANTIC SEGMENTATION VIA SPARSE CODING OVER HIERARCHICAL REGIONS

Wenbin Zou 1, * Kidiyo Kpalma 2 Joseph Ronsin 2
* Corresponding author
1 Département Image et Automatique
IETR - Institut d'Electronique et de Télécommunications de Rennes
Abstract : The purpose of this paper is segmenting objects in an image and assigning a predefined semantic label to each object. There are two areas of novelty in this paper. On one hand, hierarchical regions are used to guide semantic segmenta-tion instead of using single-level regions or multi-scale regions generated by multiple segmentations. On the other hand, sparse coding is introduced as high level description of the regions, which contributes to less quantization error than traditional bag-of-visual-words method. Experiments on the challenging Microsoft Research Cambridge dataset (MSRC 21) show that our algorithm achieves state-of-the-art performance.
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00728136
Contributor : Kidiyo Kpalma <>
Submitted on : Tuesday, September 4, 2012 - 9:46:49 PM
Last modification on : Thursday, March 5, 2020 - 5:03:30 PM
Document(s) archivé(s) le : Wednesday, December 5, 2012 - 10:18:51 AM

File

ICIP2012Submission.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00728136, version 1

Citation

Wenbin Zou, Kidiyo Kpalma, Joseph Ronsin. SEMANTIC SEGMENTATION VIA SPARSE CODING OVER HIERARCHICAL REGIONS. IEEE International Conference on Image Processing (ICIP), Sep 2012, Orlando, United States. 4 p. ⟨hal-00728136⟩

Share

Metrics

Record views

493

Files downloads

492