Distinction between handwritten and machine-printed characters with no need to locate character or text line position

In this paper, we propose a method for distinction between handwritten and machine-printed characters with no need to locate positions of characters or text lines. We call the proposed method psilaspectrum-based local fluctuation detection method. The method transforms local regions in document images into power spectrum to extract feature values which represent fluctuations caused by handwriting. We employ a multilayer perceptron for the distinction. We feed the obtained feature values to a preliminarily optimized multilayer perceptron (MLP), and the MLP yields likelihood of handwriting. We prepare a document image which has randomly aligned characters for an experiment. The experimental result shows that our method can distinguish handwritten and machine-printed characters with no need to locate positions of characters or text lines.

[1]  J. Daugman.  Uncertainty relation for resolution in space, spatial frequency, and orientation optimized by two-dimensional visual cortical filters. , 1985, Journal of the Optical Society of America. A, Optics and image science.

[2]  Rolf Ingold,et al.  Optical Font Recognition Using Typographical Features , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  H. Nothdurft.  Sensitivity for structure gradient in texture discrimination tasks , 1985, Vision Research.

[4]  Ramanujan S. Kashi,et al.  A human vision based computational model for chromatic texture segregation , 1997, IEEE Trans. Syst. Man Cybern. Part B.

[5]  Kuo-Chin Fan,et al.  Classification Of Machine-Printed And Handwritten Texts Using Character Block Layout Variance , 1998, Pattern Recognit..

[6]  Robert A. Morris,et al.  Classification of digital typefaces using spectral signatures , 1992, Pattern Recognit..

[7]  Jonathan J. Hull,et al.  Font and Function Word Identification in Document Recognition , 1996, Comput. Vis. Image Underst..

[8]  B. Julesz.  TEXTURE AND VISUAL PERCEPTION. , 1965, Scientific American.

[9]  Tieniu Tan,et al.  Rotation Invariant Texture Features and Their Use in Automatic Script Identification , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  F. Kingdom,et al.  Sensitivity to orientation modulation in micropattern-based textures , 1995, Vision Research.

[11]  Paul Scheunders,et al.  Statistical texture characterization from discrete wavelet representations , 1999, IEEE Trans. Image Process..

[12]  David S. Doermann,et al.  Machine printed text and handwriting identification in noisy document images , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[13]  Bidyut Baran Chaudhuri,et al.  Machine-printed and hand-written text lines identification , 2001, Pattern Recognit. Lett..

[14]  Tieniu Tan,et al.  Font Recognition Based on Global Texture Analysis , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Zsolt Miklós Kovács-Vajna,et al.  A system for machine-written and hand-written character distinction , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[16]  Isamu Motoyoshi,et al.  Spatiotemporal interactions in detection of texture orientation modulations , 2002, Vision Research.

[17]  Sridha Sridharan,et al.  Texture for script identification , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  J. P. Jones,et al.  An evaluation of the two-dimensional Gabor filter model of simple receptive fields in cat striate cortex. , 1987, Journal of neurophysiology.

[19]  Kai-Kuang Ma,et al.  Rotation-invariant and scale-invariant Gabor features for texture image retrieval , 2007, Image Vis. Comput..