Title :
Local-spectrum-based distinction between handwritten and machine-printed characters
Author :
Koyama, J. ; Hirose, A. ; Kato, M.
Author_Institution :
Univ. of Tokyo, Tokyo
Abstract :
In this paper, we propose a method to distinguish between handwritten and machine-printed characters with no need to locate character or text-line positions. We transform a local region in a document image into frequency domain to extract feature values including fluctuations caused by handwriting. We feed the feature values to an optimized multilayer perceptron (MLP) to get likelihood of handwriting. We call this method the spectrum-domain local fluctuation detection (SDLFD) method. Experimental results show that our method distinguishes handwritten characters from machine-printed ones with no need of text-line position information. We also found that the scheme is robust against the change in scanning resolution.
Keywords :
document image processing; feature extraction; frequency-domain analysis; handwritten character recognition; image resolution; multilayer perceptrons; optimisation; document image; feature value extraction; frequency domain; handwritten character; local-spectrum-based distinction; machine-printed character; optimized multilayer perceptron; scanning resolution; spectrum-domain local fluctuation detection method; Character recognition; Discrete wavelet transforms; Engines; Feature extraction; Feeds; Fluctuations; Frequency domain analysis; Image segmentation; Multilayer perceptrons; Optical character recognition software; Fourier transform; Handwriting recognition; Human vision; Image texture analysis; Optical character recognition;
Conference_Titel :
Image Processing, 2008. ICIP 2008. 15th IEEE International Conference on
Conference_Location :
San Diego, CA
Print_ISBN :
978-1-4244-1765-0
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2008.4711931