ML Anthology

On Integration of Vision Modules

Sharath Pankanti, Anil K. Jain, Mihran Tüceryan
CVPR 1994 pp. 316-322
doi:10.1109/CVPR.1994.323846 /cvpr/1994/pankanti1994cvpr-integration/

Abstract

Individual cues from visual modules are fallible and often ambiguous. As a result, only integrated vision systems can be expected to give a reliable performance in practice. The design of such systems is challenging since each vision module works under different and possibly conflicting sets of assumptions. We have proposed and implemented a multiresolution system which integrates perceptual grouping, segmentation, stereo, shape from shading, and line labelling modules. The output of the integrated system is shown to be relatively insensitive to the constraints imposed by the individual modules. 1

PDF CVPR Semantic Scholar

Cite

Text

Pankanti et al. "On Integration of Vision Modules." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994. doi:10.1109/CVPR.1994.323846

Markdown

[Pankanti et al. "On Integration of Vision Modules." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1994.](https://mlanthology.org/cvpr/1994/pankanti1994cvpr-integration/) doi:10.1109/CVPR.1994.323846

BibTeX

@inproceedings{pankanti1994cvpr-integration,
  title     = {{On Integration of Vision Modules}},
  author    = {Pankanti, Sharath and Jain, Anil K. and Tüceryan, Mihran},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1994},
  pages     = {316-322},
  doi       = {10.1109/CVPR.1994.323846},
  url       = {https://mlanthology.org/cvpr/1994/pankanti1994cvpr-integration/}
}