Cursive character recognition – a character segmentation method using projection profile-based
ROBERTO J. RODRIGUES 1
ANTONIO CARLOS GAY THOMÉ 1
1NCE- Núcleo de Computação Eletrônica/UFRJ, Caixa Postal 2324, Ilha do Fundão, Rio de Janeiro, RJ, Brasil
Abstract. This paper reports the results of a study on a first sight decision tree algorithm for cursive script recognition based
on the use of histogram as a projection profile technique. A postal code image data scanned is converted in a 2-dimension
matrix representation to be used with a set of algorithms to provide full range segmentation. The results, based on this
approach, are quite satisfactory for first stage classifier.
Document process applications can be found in almost all
computer systems and now is become widespread. Applications
like text edition, desktop publishing and graphics are often used
for most organizations and home offices. This technology base
has experimented a remarkable grown recently and besides the
efforts in enhancements, all methodology still requires manual
efforts to extract information, which means an exhausting task
generally not fault-tolerant and time consuming.
The simulation of complex phenomena, mainly those
related to nature, has been a big challenge for researchers. Vision
process functions and visual patterns recognition, are fields of
major interest for many of these researches.
Character recognition, as known as OCR (Optical Character
Recognition) is an important subset within the pattern
recognition area. OCR applications established some years ago
the basis for the works within the research community in order
to recognize and clarify pattern recognition and image
processing analysis as an individual field of science.
The research of character recognition starts on the years of
1870’s with the creation of the retina scanner. This device is an
image transmission system with the use of a photocell mosaic.