Your browser does not fully support modern features. Please upgrade for a smoother experience.
Orthographic Similarity: History
Please note this is an old version of this entry, which may differ significantly from the current revision.

Orthographic similarity is a measure of the degree of visual correspondence between two written text representations based on the arrangement, composition, and spatial configuration of their graphic symbols. Within handwritten text recognition and computer vision, the concept describes the extent to which character or word images share comparable visual patterns derived from stroke structures, symbol shapes, character layouts, and spatial relationships, independent of their semantic or linguistic meanings [1]. Orthographic similarity is typically characterized by the comparison of image-level or representation-level features, including contour information, pixel distributions, structural patterns, and geometric configurations extracted from handwritten or printed text samples [2]. It differs from semantic similarity, which concerns equivalence or relatedness of meaning, and from phonetic similarity, which concerns correspondence in sound patterns. In handwriting recognition systems, orthographic similarity represents a visual similarity relationship between textual forms that can be quantified through feature-based or learned similarity measures for comparing and analyzing written symbols and text images [3].

  • Handwritten text recognition
  • Visual similarity
  • Character representation
  • Feature matching

Handwritten Text Recognition Techniques • Computer Vision and Pattern Recognition • Computer Science • Physical Sciences

References

  1. R. Plamondon; S.N. Srihari; Online and off-line handwriting recognition: a comprehensive survey. IEEE Trans. Pattern Anal. Mach. Intell. 2000, 22, 63-84. [CrossRef]
  2. Y. Lecun; L. Bottou; Y. Bengio; P. Haffner; Gradient-based learning applied to document recognition. Proc. IEEE 1998, 86, 2278-2324. [CrossRef]
  3. Alex Graves; Marcus Liwicki; Santiago Fernández; Roman Bertolami; Horst Bunke; Jürgen Schmidhuber; A Novel Connectionist System for Unconstrained Handwriting Recognition. IEEE Trans. Pattern Anal. Mach. Intell. 2008, 31, 855-868. [CrossRef]
More
This entry is offline, you can click here to edit this entry!
Write an Entry