New Holistic Handwritten Word Recognition and Its Application to French Legal Amount

Namane, Abderrahmane; Guessoum, Abderrezak; Meyrueis, Patrick

doi:10.1007/11551188_72

Cited by 5 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They are the most useful for script specific holistic recognition of handwritten words. The work by Namane, Guessoum, and Meyrueis (2005) has introduced a HWR in holistic way to recognize French bank cheques through an accurate extraction and representation of three zones, namely, lower zone, upper zone and middle zone from the off-line cursive word. They have used Hopfield model and MLP based classifiers for prototype recognition leading to HWR.…”

Section: Holistic Word Recognition Approaches Using High-level Featuresmentioning

confidence: 99%

A Holistic Approach for Handwritten Hindi Word Recognition

Nasipuri¹,

Sarkar

Malakar

et al. 2017

International Journal of Computer Vision and Image Processing

View full text Add to dashboard Cite

Holistic word recognition attempts to recognize the entire word image as a single pattern. In general, it performs better than segmentation based word recognition model for known, fixed and small sized lexicon. The present work deals with recognition of handwritten words in Hindi in holistic way. Features like area, aspect ratio, density, pixel ratio, longest run, centroid and projection length are extracted either from entire word image or from the hypothetically generated sub-images of the same. An 89-elements feature vector has been designed to represent each word in the feature space and five different classifiers have been used for measuring recognition performances. Considering the complexities of Hindi characters, the technique shows an impressive result using a Multilayer Perceptron (MLP) based classifier. Moreover, the technique shows scale and rotation invariant nature to a significant extent.

show abstract

Section: Holistic Word Recognition Approaches Using High-level Featuresmentioning

confidence: 99%