The Influence of Image Complexity on Handwriting Recognition

Abstract : Automated recognition of unconstrained handwriting continues to be a challenging research task. In addition to the errors caused by image quality, image features, segmentation, and recognition, in this paper we have also explored the influence of image complexity on handwriting recognition and compared humans' versus machines' recognition. We describe a new methodology that will exploit the gap between the abilities of humans and computers in reading handwritten text images and investigate the influence of handwritten image complexity and Gestalt Laws of perception on this gap. Experimental results are presented and compared for image density and perimetric complexity of handwritten challenges. We make use of current challenges in handwriting recognition for applications in Cyber security.
Complete list of metadatas

Cited literature [13 references]  Display  Hide  Download

https://hal.inria.fr/inria-00112666
Contributor : Anne Jaigu <>
Submitted on : Thursday, November 9, 2006 - 2:50:49 PM
Last modification on : Tuesday, August 13, 2019 - 11:40:13 AM
Long-term archiving on : Tuesday, April 6, 2010 - 10:01:58 PM

Identifiers

  • HAL Id : inria-00112666, version 1

Collections

Citation

Amalia Rusu, Venu Govindaraju. The Influence of Image Complexity on Handwriting Recognition. Tenth International Workshop on Frontiers in Handwriting Recognition, Université de Rennes 1, Oct 2006, La Baule (France). ⟨inria-00112666⟩

Share

Metrics

Record views

257

Files downloads

474