What is it about?
This article proposes a model of an efficient feature set extraction technique using statistical and structural features of the text image for script-independent character recognition (it has been tested on English and Urdu also).
Featured Image
Why is it important?
This article proposes a hybrid approach combining the structural features of the character and a mathematical model of curve fitting to simulate the best features of a character. A quadratic curve-fitting model is applied on each partition forming a feature vector of the coefficients of the optimally fitted curve. This vector is combined with the spatial distribution of the foreground pixels for each zone and hence script-independent feature representation. The approach has been evaluated experimentally on Devanagari scripts. The algorithm achieves an average recognition accuracy of 93.4%.
Perspectives
The approach of Quadratic Polynomial Curve Fitting used for generating a feature set has been experimentally derived by testing various degrees of polynomials. For n data points, the complexity of the algorithm is O(kn), where k is the number of iterations. As the image is divided into 25 zones, the complexity achieves O(25*kn) ≈ O(kn). As a measure of statistical comparison, the proposed approach gives accuracy of 93% in an established testbed environment.
Neeta Nain
Malaviya National Institute of Technology
Read the Original
This page is a summary of: A Hybrid Feature Extraction Algorithm for Devanagari Script, ACM Transactions on Asian and Low-Resource Language Information Processing, January 2016, ACM (Association for Computing Machinery),
DOI: 10.1145/2710018.
You can read the full text:
Contributors
The following have contributed to this page
