ML Anthology

Active Character Recognition Using 'a*-Like' Algorit

Jaehwa Park, Venu Govindaraju
CVPR 2000 pp. 2082-2087
doi:10.1109/CVPR.2000.854744 /cvpr/2000/park2000cvpr-active/

Abstract

This paper describes an Active Character Recognition methodology, henceforth referred to as ACR. We present in this paper a method that uses an active heuristic function similar to the one used by A* search algorithm that adaptively determines the length of the feature vector as well as the features themselves used to classify an input pattern. ACR adapts to factors such as the quality of the input pattern, its intrinsic similarities and differences from patterns of other classes it is being compared against and the processing time available. Furthermore, the finer resolution is accorded to only certain "zones" of the input pattern which are deemed important given the classes that are being discriminated. Experimental results support the methodology presented. Recognition rate of ACR is about 96% on the NIST data sets and the speed is better than traditional classification methods.

CVPR Semantic Scholar

Cite

Text

Park and Govindaraju. "Active Character Recognition Using 'a*-Like' Algorit." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000. doi:10.1109/CVPR.2000.854744

Markdown

[Park and Govindaraju. "Active Character Recognition Using 'a*-Like' Algorit." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2000.](https://mlanthology.org/cvpr/2000/park2000cvpr-active/) doi:10.1109/CVPR.2000.854744

BibTeX

@inproceedings{park2000cvpr-active,
  title     = {{Active Character Recognition Using 'a*-Like' Algorit}},
  author    = {Park, Jaehwa and Govindaraju, Venu},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2000},
  pages     = {2082-2087},
  doi       = {10.1109/CVPR.2000.854744},
  url       = {https://mlanthology.org/cvpr/2000/park2000cvpr-active/}
}