Abstract—In this study we propose an off line system for the
recognition of the fragmented handwritten numeric chains. Firstly, we realized a recognition system of the isolated
handwritten digits, in this part; the study is based mainly on the evaluation of neural network performances, trained with the gradient back propagation algorithm. The used parameters to form the input vector of the neural network are extracted on the binary images of the handwritten isolated digit by several
methods: the distribution sequence, sondes application, the Barr features, and the centered moments of the different
projections and profiles. Secondly, the study is extended for the reading of the fragmented handwritten numeric chains constituted of a variable number of digits. Vertical projection was used to segment the numeric chain at isolated digits and every digit (or segment) was presented separately to the entry of the system achieved in the first part (recognition system of the
isolated handwritten digits).
Index Terms—Handwritten numeric chains, optical characters recognition, neural networks, barr features, image processing, pattern recognition, features extraction.
Salim Ouchtati is with the Electronic Research Laboratory of Skikda, University of August 20, 1955, Route El Hadaik, Bp: 26 Skikda 21000, Algeria (e-mail: ouchtatisalim@ yahoo.fr).
Mohammed Rdjimi is with Computer Science Department Electronics Department, University of August 20, 1955, Route El Hadaik, Bp: 26 Skikda
21000, Algeria (e-mail: medredjimi@gmail.com).
Mouldi Bedda is with the Electrical Engineering Department, Al-Jouf University, Arabie Saoudite, Algeria (e-mail: mouldi_bedda@ yahoo.fr).
[PDF]
Cite: S. Ouchtati, M. Redjimi, and M. Bedda, "An Offline System for the Recognition of the Fragmented Handwritten Numeric Chains," International Journal of Future Computer and Communication vol. 4, no. 1, pp. 33-39, 2015.
