caa a22 4500 606160027 CHVBK 20210128100627.0 cr unu---uuuuu 210128e20151101xx s 000 0 eng 10.1007/s00521-015-1844-9 doi (NATIONALLICENCE)springer-10.1007/s00521-015-1844-9 An efficient segmentation technique for Devanagari offline handwritten scripts using the Feedforward Neural Network [Elektronische Daten] [Vijay Dhaka, Manoj Sharma] In this research work, we have proposed a segmentation technique for words and characters of Devanagari offline handwritten scripts. Due to complex structures and high unevenness in writing styles, recognition of words and characters from the unconstrained scripts has become a burning vicinity of interest for researchers. The proposed Pixel Plot and Trace and Re-plot and Re-trace (PPTRPRT) technique extracts text region from Devanagari offline handwritten scripts and lead iterative processes for segmentation of text lines along with skew and de-skew operations. The outcomes of iterations are used in pixel-space-based word segmentation, and the segmented words are used in segmentation of characters. Moreover, PPTRPRT perform various normalization steps to allow deviation in pen breadth and slant in inscription. Investigational outcome shows that the proposed technique is competent to segment characters from Devanagari offline handwritten scripts, and accuracy of outcomes is up to 99.578%. The Natural Computing Applications Forum, 2015 PPTRPRT nationallicence Trace nationallicence Devanagari nationallicence Offline nationallicence Handwritten nationallicence Segmentation nationallicence Dhaka Vijay Jaipur National University, 302017, Jagatpura, Jaipur, Rajasthan, India aut Sharma Manoj Jaipur National University, 302017, Jagatpura, Jaipur, Rajasthan, India aut Neural Computing and Applications Springer London 26/8(2015-11-01), 1881-1893 0941-0643 26:8<1881 2015 26 521 https://doi.org/10.1007/s00521-015-1844-9 text/html Onlinezugriff via DOI BK010053 XK010053 XK010000 Metadata rights reserved Springer special CC-BY-NC licence nationallicence 1 research-article jats NATIONALLICENCE NATIONALLICENCE NL-springer NATIONALLICENCE 856 40 https://doi.org/10.1007/s00521-015-1844-9 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Dhaka Vijay Jaipur National University, 302017, Jagatpura, Jaipur, Rajasthan, India aut NATIONALLICENCE 700 1- Sharma Manoj Jaipur National University, 302017, Jagatpura, Jaipur, Rajasthan, India aut NATIONALLICENCE 773 0- Neural Computing and Applications Springer London 26/8(2015-11-01), 1881-1893 0941-0643 26:8<1881 2015 26 521