Vol. 2 Issue 1
Year: 2015
Issue:Mar-May
Title:Comparison of Spatial Domain Features for Writer Recognition Under Different Ink Width Conditions
Author Name:Sharada Laxman Kore and Shaila Apte
Synopsis:
In this paper, the authors tested the usefulness of most commonly used existing methods of writer recognition under different ink width conditions. A comparative study of Spatial Domain Features is presented in this paper. The existing methods give low error rate when they compare two handwritten images with different pen type. To improve the accuracy to a higher level histogram, variance in histogram bins and normalized histogram are used as features to recognize the handwriting. The system is tested for 981 writers with 2 samples, each with different writing instruments. The system is tested using Chain Code and Differential Chain Codes. Experimental result shows that the histogram of chain code outperform the other methods with 90.46 % as the recognition accuracy on this newly created dataset.
Year: 2015
Issue:Mar-May
Title:Comparison of Spatial Domain Features for Writer Recognition Under Different Ink Width Conditions
Author Name:Sharada Laxman Kore and Shaila Apte
Synopsis:
In this paper, the authors tested the usefulness of most commonly used existing methods of writer recognition under different ink width conditions. A comparative study of Spatial Domain Features is presented in this paper. The existing methods give low error rate when they compare two handwritten images with different pen type. To improve the accuracy to a higher level histogram, variance in histogram bins and normalized histogram are used as features to recognize the handwriting. The system is tested for 981 writers with 2 samples, each with different writing instruments. The system is tested using Chain Code and Differential Chain Codes. Experimental result shows that the histogram of chain code outperform the other methods with 90.46 % as the recognition accuracy on this newly created dataset.
No comments:
Post a Comment